_id stringlengths 24 24 | id stringlengths 7 122 | author stringlengths 2 41 | baseModels null | downloads int64 0 207M | downloads_all_time int64 0 2.8B | gated stringclasses 3
values | created_at timestamp[us, tz=UTC]date 2022-03-02 23:29:04 2025-11-03 14:41:54 | last_modified timestamp[us, tz=UTC]date 2020-12-11 21:34:15 2026-03-25 18:02:31 | library_name stringclasses 36
values | likes int64 0 13.1k | trending_score float64 0 29 | model_index stringlengths 30 911k ⌀ | pipeline_tag stringclasses 46
values | safetensors stringlengths 30 122 ⌀ | siblings listlengths 1 10k | sha stringlengths 40 40 | tags listlengths 2 1.82k | gguf stringclasses 789
values | config stringlengths 2 53.7k ⌀ | transformers_info dict | card_data stringlengths 234 905k ⌀ | card stringlengths 0 638k ⌀ | spaces null |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
6698d8a0653e4babe21e1e7d | meta-llama/Llama-3.1-8B-Instruct | meta-llama | null | 8,274,422 | 132,511,001 | manual | 2024-07-18T08:56:00 | 2024-09-25T17:00:57 | transformers | 5,600 | 29 | null | text-generation | {"parameters": {"BF16": 8030261248}, "total": 8030261248} | [
".gitattributes",
"LICENSE",
"README.md",
"USE_POLICY.md",
"config.json",
"generation_config.json",
"model-00001-of-00004.safetensors",
"model-00002-of-00004.safetensors",
"model-00003-of-00004.safetensors",
"model-00004-of-00004.safetensors",
"model.safetensors.index.json",
"original/consolid... | 0e9e39f249a16976918f6564b8830bc894c89659 | [
"transformers",
"safetensors",
"llama",
"text-generation",
"facebook",
"meta",
"pytorch",
"llama-3",
"conversational",
"en",
"de",
"fr",
"it",
"pt",
"hi",
"es",
"th",
"arxiv:2204.05149",
"base_model:meta-llama/Llama-3.1-8B",
"base_model:finetune:meta-llama/Llama-3.1-8B",
"lic... | null | {"architectures": ["LlamaForCausalLM"], "model_type": "llama", "tokenizer_config": {"bos_token": "<|begin_of_text|>", "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n {%- set date_string = \"26 Jul 2024\" %}\n{%- endif %}\n{%- if not tools is defined %}\n {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n {%- set system_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n{%- else %}\n {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message + builtin tools #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if builtin_tools is defined or tools is not none %}\n {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{%- if builtin_tools is defined %}\n {{- \"Tools: \" + builtin_tools | reject('equalto', 'code_interpreter') | join(\", \") + \"\\n\\n\"}}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n {#- Extract the first user message so we can plug it in here #}\n {%- if messages | length != 0 %}\n {%- set first_user_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n {%- else %}\n {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n {%- elif 'tool_calls' in message %}\n {%- if not message.tool_calls|length == 1 %}\n {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n {%- endif %}\n {%- set tool_call = message.tool_calls[0].function %}\n {%- if builtin_tools is defined and tool_call.name in builtin_tools %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- \"<|python_tag|>\" + tool_call.name + \".call(\" }}\n {%- for arg_name, arg_val in tool_call.arguments | items %}\n {{- arg_name + '=\"' + arg_val + '\"' }}\n {%- if not loop.last %}\n {{- \", \" }}\n {%- endif %}\n {%- endfor %}\n {{- \")\" }}\n {%- else %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n {{- '\"parameters\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- \"}\" }}\n {%- endif %}\n {%- if builtin_tools is defined %}\n {#- This means we're in ipython mode #}\n {{- \"<|eom_id|>\" }}\n {%- else %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n {%- if message.content is mapping or message.content is iterable %}\n {{- message.content | tojson }}\n {%- else %}\n {{- message.content }}\n {%- endif %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n", "eos_token": "<|eot_id|>"}} | {
"auto_model": "AutoModelForCausalLM",
"custom_class": null,
"pipeline_tag": "text-generation",
"processor": "AutoTokenizer"
} | {"base_model": "meta-llama/Meta-Llama-3.1-8B", "datasets": null, "eval_results": null, "language": ["en", "de", "fr", "it", "pt", "hi", "es", "th"], "library_name": null, "license": "llama3.1", "license_name": null, "license_link": null, "metrics": null, "model_name": null, "pipeline_tag": "text-generation", "tags": ["facebook", "meta", "pytorch", "llama", "llama-3"], "extra_gated_prompt": "### LLAMA 3.1 COMMUNITY LICENSE AGREEMENT\nLlama 3.1 Version Release Date: July 23, 2024\n\"Agreement\" means the terms and conditions for use, reproduction, distribution and modification of the Llama Materials set forth herein.\n\"Documentation\" means the specifications, manuals and documentation accompanying Llama 3.1 distributed by Meta at https://llama.meta.com/doc/overview.\n\"Licensee\" or \"you\" means you, or your employer or any other person or entity (if you are entering into this Agreement on such person or entity\u2019s behalf), of the age required under applicable laws, rules or regulations to provide legal consent and that has legal authority to bind your employer or such other person or entity if you are entering in this Agreement on their behalf.\n\"Llama 3.1\" means the foundational large language models and software and algorithms, including machine-learning model code, trained model weights, inference-enabling code, training-enabling code, fine-tuning enabling code and other elements of the foregoing distributed by Meta at https://llama.meta.com/llama-downloads.\n\"Llama Materials\" means, collectively, Meta\u2019s proprietary Llama 3.1 and Documentation (and any portion thereof) made available under this Agreement.\n\"Meta\" or \"we\" means Meta Platforms Ireland Limited (if you are located in or, if you are an entity, your principal place of business is in the EEA or Switzerland) and Meta Platforms, Inc. (if you are located outside of the EEA or Switzerland).\n \n1. License Rights and Redistribution.\na. Grant of Rights. You are granted a non-exclusive, worldwide, non-transferable and royalty-free limited license under Meta\u2019s intellectual property or other rights owned by Meta embodied in the Llama Materials to use, reproduce, distribute, copy, create derivative works of, and make modifications to the Llama Materials.\nb. Redistribution and Use.\ni. If you distribute or make available the Llama Materials (or any derivative works thereof), or a product or service (including another AI model) that contains any of them, you shall (A) provide a copy of this Agreement with any such Llama Materials; and (B) prominently display \u201cBuilt with Llama\u201d on a related website, user interface, blogpost, about page, or product documentation. If you use the Llama Materials or any outputs or results of the Llama Materials to create, train, fine tune, or otherwise improve an AI model, which is distributed or made available, you shall also include \u201cLlama\u201d at the beginning of any such AI model name.\nii. If you receive Llama Materials, or any derivative works thereof, from a Licensee as part of an integrated end user product, then Section 2 of this Agreement will not apply to you.\niii. You must retain in all copies of the Llama Materials that you distribute the following attribution notice within a \u201cNotice\u201d text file distributed as a part of such copies: \u201cLlama 3.1 is licensed under the Llama 3.1 Community License, Copyright \u00a9 Meta Platforms, Inc. All Rights Reserved.\u201d\niv. Your use of the Llama Materials must comply with applicable laws and regulations (including trade compliance laws and regulations) and adhere to the Acceptable Use Policy for the Llama Materials (available at https://llama.meta.com/llama3_1/use-policy), which is hereby incorporated by reference into this Agreement.\n2. Additional Commercial Terms. If, on the Llama 3.1 version release date, the monthly active users of the products or services made available by or for Licensee, or Licensee\u2019s affiliates, is greater than 700 million monthly active users in the preceding calendar month, you must request a license from Meta, which Meta may grant to you in its sole discretion, and you are not authorized to exercise any of the rights under this Agreement unless or until Meta otherwise expressly grants you such rights.\n3. Disclaimer of Warranty. UNLESS REQUIRED BY APPLICABLE LAW, THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS THEREFROM ARE PROVIDED ON AN \u201cAS IS\u201d BASIS, WITHOUT WARRANTIES OF ANY KIND, AND META DISCLAIMS ALL WARRANTIES OF ANY KIND, BOTH EXPRESS AND IMPLIED, INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES OF TITLE, NON-INFRINGEMENT, MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE FOR DETERMINING THE APPROPRIATENESS OF USING OR REDISTRIBUTING THE LLAMA MATERIALS AND ASSUME ANY RISKS ASSOCIATED WITH YOUR USE OF THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS.\n4. Limitation of Liability. IN NO EVENT WILL META OR ITS AFFILIATES BE LIABLE UNDER ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, TORT, NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING OUT OF THIS AGREEMENT, FOR ANY LOST PROFITS OR ANY INDIRECT, SPECIAL, CONSEQUENTIAL, INCIDENTAL, EXEMPLARY OR PUNITIVE DAMAGES, EVEN IF META OR ITS AFFILIATES HAVE BEEN ADVISED OF THE POSSIBILITY OF ANY OF THE FOREGOING.\n5. Intellectual Property.\na. No trademark licenses are granted under this Agreement, and in connection with the Llama Materials, neither Meta nor Licensee may use any name or mark owned by or associated with the other or any of its affiliates, except as required for reasonable and customary use in describing and redistributing the Llama Materials or as set forth in this Section 5(a). Meta hereby grants you a license to use \u201cLlama\u201d (the \u201cMark\u201d) solely as required to comply with the last sentence of Section 1.b.i. You will comply with Meta\u2019s brand guidelines (currently accessible at https://about.meta.com/brand/resources/meta/company-brand/ ). All goodwill arising out of your use of the Mark will inure to the benefit of Meta.\nb. Subject to Meta\u2019s ownership of Llama Materials and derivatives made by or for Meta, with respect to any derivative works and modifications of the Llama Materials that are made by you, as between you and Meta, you are and will be the owner of such derivative works and modifications.\nc. If you institute litigation or other proceedings against Meta or any entity (including a cross-claim or counterclaim in a lawsuit) alleging that the Llama Materials or Llama 3.1 outputs or results, or any portion of any of the foregoing, constitutes infringement of intellectual property or other rights owned or licensable by you, then any licenses granted to you under this Agreement shall terminate as of the date such litigation or claim is filed or instituted. You will indemnify and hold harmless Meta from and against any claim by any third party arising out of or related to your use or distribution of the Llama Materials.\n6. Term and Termination. The term of this Agreement will commence upon your acceptance of this Agreement or access to the Llama Materials and will continue in full force and effect until terminated in accordance with the terms and conditions herein. Meta may terminate this Agreement if you are in breach of any term or condition of this Agreement. Upon termination of this Agreement, you shall delete and cease use of the Llama Materials. Sections 3, 4 and 7 shall survive the termination of this Agreement.\n7. Governing Law and Jurisdiction. This Agreement will be governed and construed under the laws of the State of California without regard to choice of law principles, and the UN Convention on Contracts for the International Sale of Goods does not apply to this Agreement. The courts of California shall have exclusive jurisdiction of any dispute arising out of this Agreement.\n### Llama 3.1 Acceptable Use Policy\nMeta is committed to promoting safe and fair use of its tools and features, including Llama 3.1. If you access or use Llama 3.1, you agree to this Acceptable Use Policy (\u201cPolicy\u201d). The most recent copy of this policy can be found at [https://llama.meta.com/llama3_1/use-policy](https://llama.meta.com/llama3_1/use-policy)\n#### Prohibited Uses\nWe want everyone to use Llama 3.1 safely and responsibly. You agree you will not use, or allow others to use, Llama 3.1 to:\n 1. Violate the law or others\u2019 rights, including to:\n 1. Engage in, promote, generate, contribute to, encourage, plan, incite, or further illegal or unlawful activity or content, such as:\n 1. Violence or terrorism\n 2. Exploitation or harm to children, including the solicitation, creation, acquisition, or dissemination of child exploitative content or failure to report Child Sexual Abuse Material\n 3. Human trafficking, exploitation, and sexual violence\n 4. The illegal distribution of information or materials to minors, including obscene materials, or failure to employ legally required age-gating in connection with such information or materials.\n 5. Sexual solicitation\n 6. Any other criminal activity\n 3. Engage in, promote, incite, or facilitate the harassment, abuse, threatening, or bullying of individuals or groups of individuals\n 4. Engage in, promote, incite, or facilitate discrimination or other unlawful or harmful conduct in the provision of employment, employment benefits, credit, housing, other economic benefits, or other essential goods and services\n 5. Engage in the unauthorized or unlicensed practice of any profession including, but not limited to, financial, legal, medical/health, or related professional practices\n 6. Collect, process, disclose, generate, or infer health, demographic, or other sensitive personal or private information about individuals without rights and consents required by applicable laws\n 7. Engage in or facilitate any action or generate any content that infringes, misappropriates, or otherwise violates any third-party rights, including the outputs or results of any products or services using the Llama Materials\n 8. Create, generate, or facilitate the creation of malicious code, malware, computer viruses or do anything else that could disable, overburden, interfere with or impair the proper working, integrity, operation or appearance of a website or computer system\n2. Engage in, promote, incite, facilitate, or assist in the planning or development of activities that present a risk of death or bodily harm to individuals, including use of Llama 3.1 related to the following:\n 1. Military, warfare, nuclear industries or applications, espionage, use for materials or activities that are subject to the International Traffic Arms Regulations (ITAR) maintained by the United States Department of State\n 2. Guns and illegal weapons (including weapon development)\n 3. Illegal drugs and regulated/controlled substances\n 4. Operation of critical infrastructure, transportation technologies, or heavy machinery\n 5. Self-harm or harm to others, including suicide, cutting, and eating disorders\n 6. Any content intended to incite or promote violence, abuse, or any infliction of bodily harm to an individual\n3. Intentionally deceive or mislead others, including use of Llama 3.1 related to the following:\n 1. Generating, promoting, or furthering fraud or the creation or promotion of disinformation\n 2. Generating, promoting, or furthering defamatory content, including the creation of defamatory statements, images, or other content\n 3. Generating, promoting, or further distributing spam\n 4. Impersonating another individual without consent, authorization, or legal right\n 5. Representing that the use of Llama 3.1 or outputs are human-generated\n 6. Generating or facilitating false online engagement, including fake reviews and other means of fake online engagement\n4. Fail to appropriately disclose to end users any known dangers of your AI system\nPlease report any violation of this Policy, software \u201cbug,\u201d or other problems that could lead to a violation of this Policy through one of the following means:\n * Reporting issues with the model: [https://github.com/meta-llama/llama-models/issues](https://github.com/meta-llama/llama-models/issues)\n * Reporting risky content generated by the model:\n developers.facebook.com/llama_output_feedback\n * Reporting bugs and security concerns: facebook.com/whitehat/info\n * Reporting violations of the Acceptable Use Policy or unlicensed uses of Meta Llama 3: LlamaUseReport@meta.com", "extra_gated_fields": {"First Name": "text", "Last Name": "text", "Date of birth": "date_picker", "Country": "country", "Affiliation": "text", "Job title": {"type": "select", "options": ["Student", "Research Graduate", "AI researcher", "AI developer/engineer", "Reporter", "Other"]}, "geo": "ip_location", "By clicking Submit below I accept the terms of the license and acknowledge that the information I provide will be collected stored processed and shared in accordance with the Meta Privacy Policy": "checkbox"}, "extra_gated_description": "The information you provide will be collected, stored, processed and shared in accordance with the [Meta Privacy Policy](https://www.facebook.com/privacy/policy/).", "extra_gated_button_content": "Submit"} | null | null |
67fddfa9a7fe1f21ec1d3026 | microsoft/bitnet-b1.58-2B-4T | microsoft | null | 15,956 | 188,323 | False | 2025-04-15T04:25:13 | 2025-12-17T18:13:05 | transformers | 1,398 | 25 | null | text-generation | null | [
".gitattributes",
"LICENSE",
"README.md",
"config.json",
"data_summary_card.md",
"generation_config.json",
"model.safetensors",
"special_tokens_map.json",
"tokenizer.json",
"tokenizer_config.json"
] | 04c3b9ad9361b824064a1f25ea60a8be9599b127 | [
"transformers",
"safetensors",
"bitnet",
"text-generation",
"chat",
"large-language-model",
"conversational",
"custom_code",
"en",
"arxiv:2504.12285",
"license:mit",
"endpoints_compatible",
"deploy:azure",
"region:us"
] | null | {"architectures": ["BitNetForCausalLM"], "auto_map": {"AutoConfig": "configuration_bitnet.BitNetConfig", "AutoModelForCausalLM": "modeling_bitnet.BitNetForCausalLM"}, "model_type": "bitnet", "quantization_config": {"quant_method": "bitnet"}, "tokenizer_config": {"bos_token": "<|begin_of_text|>", "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = message['role'] | capitalize + ': '+ message['content'] | trim + '<|eot_id|>' %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ 'Assistant: ' }}{% endif %}", "eos_token": "<|eot_id|>"}} | {
"auto_model": "AutoModelForCausalLM",
"custom_class": null,
"pipeline_tag": "text-generation",
"processor": "AutoTokenizer"
} | {"base_model": null, "datasets": null, "eval_results": null, "language": ["en"], "library_name": "transformers", "license": "mit", "license_name": null, "license_link": "https://huggingface.co/microsoft/bitnet-b1.58-2B-4T/blob/main/LICENSE", "metrics": null, "model_name": null, "pipeline_tag": "text-generation", "tags": ["chat", "bitnet", "text-generation", "large-language-model"]} | # BitNet b1.58 2B4T - Scaling Native 1-bit LLM
This repository contains the weights for **BitNet b1.58 2B4T**, the first open-source, native 1-bit Large Language Model (LLM) at the 2-billion parameter scale, developed by Microsoft Research.
Trained on a corpus of 4 trillion tokens, this model demonstrates that native 1-bit LLMs can achieve performance comparable to leading open-weight, full-precision models of similar size, while offering substantial advantages in computational efficiency (memory, energy, latency).
➡️ **Technical Report:** [BitNet b1.58 2B4T Technical Report](https://arxiv.org/abs/2504.12285)
➡️ **Official Inference Code:** [microsoft/BitNet (bitnet.cpp)](https://github.com/microsoft/BitNet)
## Model Variants
Several versions of the model weights are available on Hugging Face:
* [**`microsoft/bitnet-b1.58-2B-4T`**](https://huggingface.co/microsoft/bitnet-b1.58-2B-4T) (This repository): Contains the packed 1.58-bit weights optimized for efficient inference. **Use this for deployment.**
* [**`microsoft/bitnet-b1.58-2B-4T-bf16`**](https://huggingface.co/microsoft/bitnet-b1.58-2B-4T-bf16): Contains the master weights in BF16 format. **Use this only for training or fine-tuning purposes.**
* [**`microsoft/bitnet-b1.58-2B-4T-gguf`**](https://huggingface.co/microsoft/bitnet-b1.58-2B-4T-gguf): Contains the model weights in GGUF format, compatible with the `bitnet.cpp` library for CPU inference.
## Model Details
* **Architecture:** Transformer-based, modified with `BitLinear` layers (BitNet framework).
* Uses Rotary Position Embeddings (RoPE).
* Uses squared ReLU (ReLU²) activation in FFN layers.
* Employs [`subln`](https://proceedings.mlr.press/v202/wang23u.html) normalization.
* No bias terms in linear or normalization layers.
* **Quantization:** Native 1.58-bit weights and 8-bit activations (W1.58A8).
* Weights are quantized to ternary values {-1, 0, +1} using absmean quantization during the forward pass.
* Activations are quantized to 8-bit integers using absmax quantization (per-token).
* **Crucially, the model was *trained from scratch* with this quantization scheme, not post-training quantized.**
* **Parameters:** ~2 Billion
* **Training Tokens:** 4 Trillion
* **Context Length:** Maximum sequence length of **4096 tokens**.
* *Recommendation:* For optimal performance on tasks requiring very long contexts (beyond the pre-training length or for specialized long-reasoning tasks), we recommend performing intermediate long-sequence adaptation/training before the final fine-tuning stage.
* **Training Stages:**
1. **Pre-training:** Large-scale training on public text/code and synthetic math data using a two-stage learning rate and weight decay schedule.
2. **Supervised Fine-tuning (SFT):** Fine-tuned on instruction-following and conversational datasets using sum loss aggregation and specific hyperparameter tuning.
3. **Direct Preference Optimization (DPO):** Aligned with human preferences using preference pairs.
* **Tokenizer:** LLaMA 3 Tokenizer (vocab size: 128,256).
## How to Use (with `transformers`)
**VERY IMPORTANT NOTE ON EFFICIENCY**
> Please do NOT expect performance efficiency gains (in terms of speed, latency, or energy consumption) when using this model with the standard transformers library, even with the required fork.
>
> The current execution paths within transformers do not contain the specialized, highly optimized computational kernels required to leverage the advantages of the BitNet architecture. Running the model via transformers will likely result in inference speeds and energy usage comparable to, or potentially worse than, standard full-precision models within this framework on both CPU and GPU.
>
> While you might observe reduced memory usage due to the quantized weights, the primary computational efficiency benefits are not accessible through this standard transformers usage path.
>
> For achieving the efficiency benefits demonstrated in the technical paper, you MUST use the dedicated C++ implementation: [bitnet.cpp](https://github.com/microsoft/BitNet).
### Requirements
```bash
pip install git+https://github.com/huggingface/transformers.git@096f25ae1f501a084d8ff2dcaf25fbc2bd60eba4
```
### Example
```python
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
model_id = "microsoft/bitnet-b1.58-2B-4T"
# Load tokenizer and model
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
model_id,
torch_dtype=torch.bfloat16
)
# Apply the chat template
messages = [
{"role": "system", "content": "You are a helpful AI assistant."},
{"role": "user", "content": "How are you?"},
]
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
chat_input = tokenizer(prompt, return_tensors="pt").to(model.device)
# Generate response
chat_outputs = model.generate(**chat_input, max_new_tokens=50)
response = tokenizer.decode(chat_outputs[0][chat_input['input_ids'].shape[-1]:], skip_special_tokens=True) # Decode only the response part
print("\nAssistant Response:", response)
```
## How to Use (with `bitnet.cpp`)
Please refer to the [bitnet.cpp](https://github.com/microsoft/BitNet) GitHub repository for detailed compilation steps, usage examples, and command-line options.
## Evaluation
BitNet b1.58 2B4T was evaluated against leading open-weight full-precision LLMs of similar size. Below are the key results (all models are instruction-tuned versions):
| Benchmark | LLaMA 3.2 1B | Gemma-3 1B | Qwen2.5 1.5B | SmolLM2 1.7B | MiniCPM 2B | **BitNet b1.58 2B** |
|--------------------------------|--------------|------------|--------------|--------------|------------|---------------------|
| **Memory (Non-emb)** | 2GB | 1.4GB | 2.6GB | 3.2GB | 4.8GB | **0.4GB** |
| **Latency (CPU Decoding)** | 48ms | 41ms | 65ms | 67ms | 124ms | **29ms** |
| **Energy (Estimated)** | 0.258J | 0.186J | 0.347J | 0.425J | 0.649J | **0.028J** |
| **Training Tokens (Pre-train)**| 9T* | 2T** | 18T | 11T | 1.1T | 4T |
| ARC-Challenge | 37.80 | 38.40 | 46.67 | 43.52 | 44.80 | **49.91** |
| ARC-Easy | 63.17 | 63.13 | **76.01** | 62.92 | 72.14 | 74.79 |
| OpenbookQA | 34.80 | 38.80 | 40.80 | **46.00** | 40.20 | 41.60 |
| BoolQ | 64.65 | 74.22 | 78.04 | 75.78 | **80.67** | 80.18 |
| HellaSwag | 60.80 | 57.69 | 68.28 | **71.71** | 70.81 | 68.44 |
| PIQA | 74.21 | 71.93 | 76.12 | 76.12 | 76.66 | **77.09** |
| WinoGrande | 59.51 | 58.48 | 62.83 | 68.98 | 61.80 | **71.90** |
| CommonsenseQA | 58.48 | 42.10 | **76.41** | 63.55 | 71.74 | 71.58 |
| TruthfulQA | 43.80 | 38.66 | **46.67** | 39.90 | 41.41 | 45.31 |
| TriviaQA | 37.60 | 23.49 | 38.37 | **45.97** | 34.13 | 33.57 |
| MMLU | 45.58 | 39.91 | **60.25** | 49.24 | 51.82 | 53.17 |
| HumanEval+ | 31.10 | 37.20 | **50.60** | 28.00 | 43.90 | 38.40 |
| GSM8K | 38.21 | 31.16 | 56.79 | 45.11 | 4.40 | **58.38** |
| MATH-500 | 23.00 | 42.00 | **53.00** | 17.60 | 14.80 | 43.40 |
| IFEval | 62.71 | **66.67** | 50.12 | 57.91 | 36.81 | 53.48 |
| MT-bench | 5.43 | 6.40 | 6.12 | 5.50 | **6.57** | 5.85 |
| **Average** | 44.90 | 43.74 | **55.23** | 48.70 | 42.05 | 54.19 |
*LLaMA 3.2 1B uses pruning & distillation.
**Gemma-3 1B uses distillation.
## License
The model weights and code are released under the [MIT License](https://huggingface.co/microsoft/bitnet-b1.58-2B-4T/blob/main/LICENSE).
## Bias, Risks, and Limitations
Predictions may perpetuate biases present in the training data.
There is limited support for non-English languages and underrepresented domains.
There is a risk of generating inaccurate or harmful content.
The Bitnet model has an elevated defect rate when responding to election-critical queries, which may result in incorrect or unauthoritative election critical information being presented. We are working to improve the model's performance in this area. Users should verify information related to elections with the election authority in their region.
## Disclaimer
We do not recommend using BitNet b1.58 in commercial or real-world applications without further testing and development. This model is intended for research and development purposes. While efforts have been made to align it using SFT and DPO, it may still produce outputs that are unexpected, biased, or inaccurate. Please use responsibly. | null |
654a84cadff2f49007ce6c37 | openai/whisper-large-v3 | openai | null | 4,972,713 | 114,620,320 | False | 2023-11-07T18:41:14 | 2024-08-12T10:20:10 | transformers | 5,504 | 23 | null | automatic-speech-recognition | null | [
".gitattributes",
"README.md",
"added_tokens.json",
"config.json",
"flax_model.msgpack",
"generation_config.json",
"merges.txt",
"model.fp32-00001-of-00002.safetensors",
"model.fp32-00002-of-00002.safetensors",
"model.safetensors",
"model.safetensors.index.fp32.json",
"normalizer.json",
"pre... | 06f233fe06e710322aca913c1bc4249a0d71fce1 | [
"transformers",
"pytorch",
"jax",
"safetensors",
"whisper",
"automatic-speech-recognition",
"audio",
"hf-asr-leaderboard",
"en",
"zh",
"de",
"es",
"ru",
"ko",
"fr",
"ja",
"pt",
"tr",
"pl",
"ca",
"nl",
"ar",
"sv",
"it",
"id",
"hi",
"fi",
"vi",
"he",
"uk",
"... | null | {"architectures": ["WhisperForConditionalGeneration"], "model_type": "whisper", "tokenizer_config": {"bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "pad_token": "<|endoftext|>", "unk_token": "<|endoftext|>"}} | {
"auto_model": "AutoModelForSpeechSeq2Seq",
"custom_class": null,
"pipeline_tag": "automatic-speech-recognition",
"processor": "AutoProcessor"
} | {"base_model": null, "datasets": null, "eval_results": null, "language": ["en", "zh", "de", "es", "ru", "ko", "fr", "ja", "pt", "tr", "pl", "ca", "nl", "ar", "sv", "it", "id", "hi", "fi", "vi", "he", "uk", "el", "ms", "cs", "ro", "da", "hu", "ta", "no", "th", "ur", "hr", "bg", "lt", "la", "mi", "ml", "cy", "sk", "te", "fa", "lv", "bn", "sr", "az", "sl", "kn", "et", "mk", "br", "eu", "is", "hy", "ne", "mn", "bs", "kk", "sq", "sw", "gl", "mr", "pa", "si", "km", "sn", "yo", "so", "af", "oc", "ka", "be", "tg", "sd", "gu", "am", "yi", "lo", "uz", "fo", "ht", "ps", "tk", "nn", "mt", "sa", "lb", "my", "bo", "tl", "mg", "as", "tt", "haw", "ln", "ha", "ba", "jw", "su"], "library_name": null, "license": "apache-2.0", "license_name": null, "license_link": null, "metrics": null, "model_name": null, "pipeline_tag": "automatic-speech-recognition", "tags": ["audio", "automatic-speech-recognition", "hf-asr-leaderboard"], "widget": [{"example_title": "Librispeech sample 1", "src": "https://cdn-media.huggingface.co/speech_samples/sample1.flac"}, {"example_title": "Librispeech sample 2", "src": "https://cdn-media.huggingface.co/speech_samples/sample2.flac"}]} | # Whisper
Whisper is a state-of-the-art model for automatic speech recognition (ASR) and speech translation, proposed in the paper
[Robust Speech Recognition via Large-Scale Weak Supervision](https://huggingface.co/papers/2212.04356) by Alec Radford
et al. from OpenAI. Trained on >5M hours of labeled data, Whisper demonstrates a strong ability to generalise to many
datasets and domains in a zero-shot setting.
Whisper large-v3 has the same architecture as the previous [large](https://huggingface.co/openai/whisper-large) and [large-v2](https://huggingface.co/openai/whisper-large-v2)
models, except for the following minor differences:
1. The spectrogram input uses 128 Mel frequency bins instead of 80
2. A new language token for Cantonese
The Whisper large-v3 model was trained on 1 million hours of weakly labeled audio and 4 million hours of pseudo-labeled
audio collected using Whisper [large-v2](https://huggingface.co/openai/whisper-large-v2) . The model was trained for 2.0 epochs over this mixture dataset.
The large-v3 model shows improved performance over a wide variety of languages, showing 10% to 20% reduction of errors
compared to Whisper [large-v2](https://huggingface.co/openai/whisper-large-v2) . For more details on the different checkpoints available, refer to the section [Model details](#model-details).
**Disclaimer**: Content for this model card has partly been written by the 🤗 Hugging Face team, and partly copied and
pasted from the original model card.
## Usage
Whisper large-v3 is supported in Hugging Face 🤗 Transformers. To run the model, first install the Transformers
library. For this example, we'll also install 🤗 Datasets to load toy audio dataset from the Hugging Face Hub, and
🤗 Accelerate to reduce the model loading time:
```bash
pip install --upgrade pip
pip install --upgrade transformers datasets[audio] accelerate
```
The model can be used with the [`pipeline`](https://huggingface.co/docs/transformers/main_classes/pipelines#transformers.AutomaticSpeechRecognitionPipeline)
class to transcribe audios of arbitrary length:
```python
import torch
from transformers import AutoModelForSpeechSeq2Seq, AutoProcessor, pipeline
from datasets import load_dataset
device = "cuda:0" if torch.cuda.is_available() else "cpu"
torch_dtype = torch.float16 if torch.cuda.is_available() else torch.float32
model_id = "openai/whisper-large-v3"
model = AutoModelForSpeechSeq2Seq.from_pretrained(
model_id, torch_dtype=torch_dtype, low_cpu_mem_usage=True, use_safetensors=True
)
model.to(device)
processor = AutoProcessor.from_pretrained(model_id)
pipe = pipeline(
"automatic-speech-recognition",
model=model,
tokenizer=processor.tokenizer,
feature_extractor=processor.feature_extractor,
torch_dtype=torch_dtype,
device=device,
)
dataset = load_dataset("distil-whisper/librispeech_long", "clean", split="validation")
sample = dataset[0]["audio"]
result = pipe(sample)
print(result["text"])
```
To transcribe a local audio file, simply pass the path to your audio file when you call the pipeline:
```python
result = pipe("audio.mp3")
```
Multiple audio files can be transcribed in parallel by specifying them as a list and setting the `batch_size` parameter:
```python
result = pipe(["audio_1.mp3", "audio_2.mp3"], batch_size=2)
```
Transformers is compatible with all Whisper decoding strategies, such as temperature fallback and condition on previous
tokens. The following example demonstrates how to enable these heuristics:
```python
generate_kwargs = {
"max_new_tokens": 448,
"num_beams": 1,
"condition_on_prev_tokens": False,
"compression_ratio_threshold": 1.35, # zlib compression ratio threshold (in token space)
"temperature": (0.0, 0.2, 0.4, 0.6, 0.8, 1.0),
"logprob_threshold": -1.0,
"no_speech_threshold": 0.6,
"return_timestamps": True,
}
result = pipe(sample, generate_kwargs=generate_kwargs)
```
Whisper predicts the language of the source audio automatically. If the source audio language is known *a-priori*, it
can be passed as an argument to the pipeline:
```python
result = pipe(sample, generate_kwargs={"language": "english"})
```
By default, Whisper performs the task of *speech transcription*, where the source audio language is the same as the target
text language. To perform *speech translation*, where the target text is in English, set the task to `"translate"`:
```python
result = pipe(sample, generate_kwargs={"task": "translate"})
```
Finally, the model can be made to predict timestamps. For sentence-level timestamps, pass the `return_timestamps` argument:
```python
result = pipe(sample, return_timestamps=True)
print(result["chunks"])
```
And for word-level timestamps:
```python
result = pipe(sample, return_timestamps="word")
print(result["chunks"])
```
The above arguments can be used in isolation or in combination. For example, to perform the task of speech transcription
where the source audio is in French, and we want to return sentence-level timestamps, the following can be used:
```python
result = pipe(sample, return_timestamps=True, generate_kwargs={"language": "french", "task": "translate"})
print(result["chunks"])
```
<details>
<summary> For more control over the generation parameters, use the model + processor API directly: </summary>
```python
import torch
from transformers import AutoModelForSpeechSeq2Seq, AutoProcessor
from datasets import Audio, load_dataset
device = "cuda:0" if torch.cuda.is_available() else "cpu"
torch_dtype = torch.float16 if torch.cuda.is_available() else torch.float32
model_id = "openai/whisper-large-v3"
model = AutoModelForSpeechSeq2Seq.from_pretrained(
model_id, torch_dtype=torch_dtype, low_cpu_mem_usage=True
)
model.to(device)
processor = AutoProcessor.from_pretrained(model_id)
dataset = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
dataset = dataset.cast_column("audio", Audio(processor.feature_extractor.sampling_rate))
sample = dataset[0]["audio"]
inputs = processor(
sample["array"],
sampling_rate=sample["sampling_rate"],
return_tensors="pt",
truncation=False,
padding="longest",
return_attention_mask=True,
)
inputs = inputs.to(device, dtype=torch_dtype)
gen_kwargs = {
"max_new_tokens": 448,
"num_beams": 1,
"condition_on_prev_tokens": False,
"compression_ratio_threshold": 1.35, # zlib compression ratio threshold (in token space)
"temperature": (0.0, 0.2, 0.4, 0.6, 0.8, 1.0),
"logprob_threshold": -1.0,
"no_speech_threshold": 0.6,
"return_timestamps": True,
}
pred_ids = model.generate(**inputs, **gen_kwargs)
pred_text = processor.batch_decode(pred_ids, skip_special_tokens=True, decode_with_timestamps=False)
print(pred_text)
```
</details>
## Additional Speed & Memory Improvements
You can apply additional speed and memory improvements to Whisper to further reduce the inference speed and VRAM
requirements.
### Chunked Long-Form
Whisper has a receptive field of 30-seconds. To transcribe audios longer than this, one of two long-form algorithms are
required:
1. **Sequential:** uses a "sliding window" for buffered inference, transcribing 30-second slices one after the other
2. **Chunked:** splits long audio files into shorter ones (with a small overlap between segments), transcribes each segment independently, and stitches the resulting transcriptions at the boundaries
The sequential long-form algorithm should be used in either of the following scenarios:
1. Transcription accuracy is the most important factor, and speed is less of a consideration
2. You are transcribing **batches** of long audio files, in which case the latency of sequential is comparable to chunked, while being up to 0.5% WER more accurate
Conversely, the chunked algorithm should be used when:
1. Transcription speed is the most important factor
2. You are transcribing a **single** long audio file
By default, Transformers uses the sequential algorithm. To enable the chunked algorithm, pass the `chunk_length_s`
parameter to the `pipeline`. For large-v3, a chunk length of 30-seconds is optimal. To activate batching over long
audio files, pass the argument `batch_size`:
```python
import torch
from transformers import AutoModelForSpeechSeq2Seq, AutoProcessor, pipeline
from datasets import load_dataset
device = "cuda:0" if torch.cuda.is_available() else "cpu"
torch_dtype = torch.float16 if torch.cuda.is_available() else torch.float32
model_id = "openai/whisper-large-v3"
model = AutoModelForSpeechSeq2Seq.from_pretrained(
model_id, torch_dtype=torch_dtype, low_cpu_mem_usage=True
)
model.to(device)
processor = AutoProcessor.from_pretrained(model_id)
pipe = pipeline(
"automatic-speech-recognition",
model=model,
tokenizer=processor.tokenizer,
feature_extractor=processor.feature_extractor,
chunk_length_s=30,
batch_size=16, # batch size for inference - set based on your device
torch_dtype=torch_dtype,
device=device,
)
dataset = load_dataset("distil-whisper/librispeech_long", "clean", split="validation")
sample = dataset[0]["audio"]
result = pipe(sample)
print(result["text"])
```
#### Torch compile
The Whisper forward pass is compatible with [`torch.compile`](https://pytorch.org/docs/stable/generated/torch.compile.html)
for 4.5x speed-ups.
**Note:** `torch.compile` is currently not compatible with the Chunked long-form algorithm or Flash Attention 2 ⚠️
```python
import torch
from torch.nn.attention import SDPBackend, sdpa_kernel
from transformers import AutoModelForSpeechSeq2Seq, AutoProcessor, pipeline
from datasets import load_dataset
from tqdm import tqdm
torch.set_float32_matmul_precision("high")
device = "cuda:0" if torch.cuda.is_available() else "cpu"
torch_dtype = torch.float16 if torch.cuda.is_available() else torch.float32
model_id = "openai/whisper-large-v3"
model = AutoModelForSpeechSeq2Seq.from_pretrained(
model_id, torch_dtype=torch_dtype, low_cpu_mem_usage=True
).to(device)
# Enable static cache and compile the forward pass
model.generation_config.cache_implementation = "static"
model.generation_config.max_new_tokens = 256
model.forward = torch.compile(model.forward, mode="reduce-overhead", fullgraph=True)
processor = AutoProcessor.from_pretrained(model_id)
pipe = pipeline(
"automatic-speech-recognition",
model=model,
tokenizer=processor.tokenizer,
feature_extractor=processor.feature_extractor,
torch_dtype=torch_dtype,
device=device,
)
dataset = load_dataset("distil-whisper/librispeech_long", "clean", split="validation")
sample = dataset[0]["audio"]
# 2 warmup steps
for _ in tqdm(range(2), desc="Warm-up step"):
with sdpa_kernel(SDPBackend.MATH):
result = pipe(sample.copy(), generate_kwargs={"min_new_tokens": 256, "max_new_tokens": 256})
# fast run
with sdpa_kernel(SDPBackend.MATH):
result = pipe(sample.copy())
print(result["text"])
```
#### Flash Attention 2
We recommend using [Flash-Attention 2](https://huggingface.co/docs/transformers/main/en/perf_infer_gpu_one#flashattention-2) if your GPU supports it and you are not using [torch.compile](#torch-compile).
To do so, first install [Flash Attention](https://github.com/Dao-AILab/flash-attention):
```
pip install flash-attn --no-build-isolation
```
Then pass `attn_implementation="flash_attention_2"` to `from_pretrained`:
```python
model = AutoModelForSpeechSeq2Seq.from_pretrained(model_id, torch_dtype=torch_dtype, low_cpu_mem_usage=True, attn_implementation="flash_attention_2")
```
#### Torch Scale-Product-Attention (SDPA)
If your GPU does not support Flash Attention, we recommend making use of PyTorch [scaled dot-product attention (SDPA)](https://pytorch.org/docs/stable/generated/torch.nn.functional.scaled_dot_product_attention.html).
This attention implementation is activated **by default** for PyTorch versions 2.1.1 or greater. To check
whether you have a compatible PyTorch version, run the following Python code snippet:
```python
from transformers.utils import is_torch_sdpa_available
print(is_torch_sdpa_available())
```
If the above returns `True`, you have a valid version of PyTorch installed and SDPA is activated by default. If it
returns `False`, you need to upgrade your PyTorch version according to the [official instructions](https://pytorch.org/get-started/locally/)
Once a valid PyTorch version is installed, SDPA is activated by default. It can also be set explicitly by specifying
`attn_implementation="sdpa"` as follows:
```python
model = AutoModelForSpeechSeq2Seq.from_pretrained(model_id, torch_dtype=torch_dtype, low_cpu_mem_usage=True, attn_implementation="sdpa")
```
For more information about how to use the SDPA refer to the [Transformers SDPA documentation](https://huggingface.co/docs/transformers/en/perf_infer_gpu_one#pytorch-scaled-dot-product-attention).
## Model details
Whisper is a Transformer based encoder-decoder model, also referred to as a _sequence-to-sequence_ model. There are two
flavours of Whisper model: English-only and multilingual. The English-only models were trained on the task of English
speech recognition. The multilingual models were trained simultaneously on multilingual speech recognition and speech
translation. For speech recognition, the model predicts transcriptions in the *same* language as the audio. For speech
translation, the model predicts transcriptions to a *different* language to the audio.
Whisper checkpoints come in five configurations of varying model sizes. The smallest four are available as English-only
and multilingual. The largest checkpoints are multilingual only. All ten of the pre-trained checkpoints
are available on the [Hugging Face Hub](https://huggingface.co/models?search=openai/whisper). The
checkpoints are summarised in the following table with links to the models on the Hub:
| Size | Parameters | English-only | Multilingual |
|----------|------------|------------------------------------------------------|-----------------------------------------------------|
| tiny | 39 M | [✓](https://huggingface.co/openai/whisper-tiny.en) | [✓](https://huggingface.co/openai/whisper-tiny) |
| base | 74 M | [✓](https://huggingface.co/openai/whisper-base.en) | [✓](https://huggingface.co/openai/whisper-base) |
| small | 244 M | [✓](https://huggingface.co/openai/whisper-small.en) | [✓](https://huggingface.co/openai/whisper-small) |
| medium | 769 M | [✓](https://huggingface.co/openai/whisper-medium.en) | [✓](https://huggingface.co/openai/whisper-medium) |
| large | 1550 M | x | [✓](https://huggingface.co/openai/whisper-large) |
| large-v2 | 1550 M | x | [✓](https://huggingface.co/openai/whisper-large-v2) |
| large-v3 | 1550 M | x | [✓](https://huggingface.co/openai/whisper-large-v3) |
## Fine-Tuning
The pre-trained Whisper model demonstrates a strong ability to generalise to different datasets and domains. However,
its predictive capabilities can be improved further for certain languages and tasks through *fine-tuning*. The blog
post [Fine-Tune Whisper with 🤗 Transformers](https://huggingface.co/blog/fine-tune-whisper) provides a step-by-step
guide to fine-tuning the Whisper model with as little as 5 hours of labelled data.
### Evaluated Use
The primary intended users of these models are AI researchers studying robustness, generalization, capabilities, biases, and constraints of the current model. However, Whisper is also potentially quite useful as an ASR solution for developers, especially for English speech recognition. We recognize that once models are released, it is impossible to restrict access to only “intended” uses or to draw reasonable guidelines around what is or is not research.
The models are primarily trained and evaluated on ASR and speech translation to English tasks. They show strong ASR results in ~10 languages. They may exhibit additional capabilities, particularly if fine-tuned on certain tasks like voice activity detection, speaker classification, or speaker diarization but have not been robustly evaluated in these areas. We strongly recommend that users perform robust evaluations of the models in a particular context and domain before deploying them.
In particular, we caution against using Whisper models to transcribe recordings of individuals taken without their consent or purporting to use these models for any kind of subjective classification. We recommend against use in high-risk domains like decision-making contexts, where flaws in accuracy can lead to pronounced flaws in outcomes. The models are intended to transcribe and translate speech, use of the model for classification is not only not evaluated but also not appropriate, particularly to infer human attributes.
## Training Data
The large-v3 checkpoint is trained on 1 million hours of weakly labeled audio and 4 million hours of pseudo-labeled audio collected using Whisper large-v2.
As discussed in [the accompanying paper](https://cdn.openai.com/papers/whisper.pdf), we see that performance on transcription in a given language is directly correlated with the amount of training data we employ in that language.
## Performance and Limitations
Our studies show that, over many existing ASR systems, the models exhibit improved robustness to accents, background noise, technical language, as well as zero shot translation from multiple languages into English; and that accuracy on speech recognition and translation is near the state-of-the-art level.
However, because the models are trained in a weakly supervised manner using large-scale noisy data, the predictions may include texts that are not actually spoken in the audio input (i.e. hallucination). We hypothesize that this happens because, given their general knowledge of language, the models combine trying to predict the next word in audio with trying to transcribe the audio itself.
Our models perform unevenly across languages, and we observe lower accuracy on low-resource and/or low-discoverability languages or languages where we have less training data. The models also exhibit disparate performance on different accents and dialects of particular languages, which may include higher word error rate across speakers of different genders, races, ages, or other demographic criteria. Our full evaluation results are presented in [the paper accompanying this release](https://cdn.openai.com/papers/whisper.pdf).
In addition, the sequence-to-sequence architecture of the model makes it prone to generating repetitive texts, which can be mitigated to some degree by beam search and temperature scheduling but not perfectly. Further analysis on these limitations are provided in [the paper](https://cdn.openai.com/papers/whisper.pdf). It is likely that this behavior and hallucinations may be worse on lower-resource and/or lower-discoverability languages.
## Broader Implications
We anticipate that Whisper models’ transcription capabilities may be used for improving accessibility tools. While Whisper models cannot be used for real-time transcription out of the box – their speed and size suggest that others may be able to build applications on top of them that allow for near-real-time speech recognition and translation. The real value of beneficial applications built on top of Whisper models suggests that the disparate performance of these models may have real economic implications.
There are also potential dual use concerns that come with releasing Whisper. While we hope the technology will be used primarily for beneficial purposes, making ASR technology more accessible could enable more actors to build capable surveillance technologies or scale up existing surveillance efforts, as the speed and accuracy allow for affordable automatic transcription and translation of large volumes of audio communication. Moreover, these models may have some capabilities to recognize specific individuals out of the box, which in turn presents safety concerns related both to dual use and disparate performance. In practice, we expect that the cost of transcription is not the limiting factor of scaling up surveillance projects.
### BibTeX entry and citation info
```bibtex
@misc{radford2022whisper,
doi = {10.48550/ARXIV.2212.04356},
url = {https://arxiv.org/abs/2212.04356},
author = {Radford, Alec and Kim, Jong Wook and Xu, Tao and Brockman, Greg and McLeavey, Christine and Sutskever, Ilya},
title = {Robust Speech Recognition via Large-Scale Weak Supervision},
publisher = {arXiv},
year = {2022},
copyright = {arXiv.org perpetual, non-exclusive license}
}
``` | null |
621ffdc136468d709f180294 | sentence-transformers/all-MiniLM-L6-v2 | sentence-transformers | null | 206,994,378 | 2,377,711,760 | False | 2022-03-02T23:29:05 | 2025-03-06T13:37:44 | sentence-transformers | 4,607 | 22 | null | sentence-similarity | {"parameters": {"I64": 512, "F32": 22713216}, "total": 22713728} | [
".gitattributes",
"1_Pooling/config.json",
"README.md",
"config.json",
"config_sentence_transformers.json",
"data_config.json",
"model.safetensors",
"modules.json",
"onnx/model.onnx",
"onnx/model_O1.onnx",
"onnx/model_O2.onnx",
"onnx/model_O3.onnx",
"onnx/model_O4.onnx",
"onnx/model_qint8_... | c9745ed1d9f207416be6d2e6f8de32d1f16199bf | [
"sentence-transformers",
"pytorch",
"tf",
"rust",
"onnx",
"safetensors",
"openvino",
"bert",
"feature-extraction",
"sentence-similarity",
"transformers",
"en",
"dataset:s2orc",
"dataset:flax-sentence-embeddings/stackexchange_xml",
"dataset:ms_marco",
"dataset:gooaq",
"dataset:yahoo_a... | null | {"architectures": ["BertModel"], "model_type": "bert", "tokenizer_config": {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}} | {
"auto_model": "AutoModel",
"custom_class": null,
"pipeline_tag": "feature-extraction",
"processor": "AutoTokenizer"
} | {"base_model": null, "datasets": ["s2orc", "flax-sentence-embeddings/stackexchange_xml", "ms_marco", "gooaq", "yahoo_answers_topics", "code_search_net", "search_qa", "eli5", "snli", "multi_nli", "wikihow", "natural_questions", "trivia_qa", "embedding-data/sentence-compression", "embedding-data/flickr30k-captions", "embedding-data/altlex", "embedding-data/simple-wiki", "embedding-data/QQP", "embedding-data/SPECTER", "embedding-data/PAQ_pairs", "embedding-data/WikiAnswers"], "eval_results": null, "language": "en", "library_name": "sentence-transformers", "license": "apache-2.0", "license_name": null, "license_link": null, "metrics": null, "model_name": null, "pipeline_tag": "sentence-similarity", "tags": ["sentence-transformers", "feature-extraction", "sentence-similarity", "transformers"]} | # all-MiniLM-L6-v2
This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 384 dimensional dense vector space and can be used for tasks like clustering or semantic search.
## Usage (Sentence-Transformers)
Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
```
pip install -U sentence-transformers
```
Then you can use the model like this:
```python
from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]
model = SentenceTransformer('sentence-transformers/all-MiniLM-L6-v2')
embeddings = model.encode(sentences)
print(embeddings)
```
## Usage (HuggingFace Transformers)
Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.
```python
from transformers import AutoTokenizer, AutoModel
import torch
import torch.nn.functional as F
#Mean Pooling - Take attention mask into account for correct averaging
def mean_pooling(model_output, attention_mask):
token_embeddings = model_output[0] #First element of model_output contains all token embeddings
input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
# Sentences we want sentence embeddings for
sentences = ['This is an example sentence', 'Each sentence is converted']
# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained('sentence-transformers/all-MiniLM-L6-v2')
model = AutoModel.from_pretrained('sentence-transformers/all-MiniLM-L6-v2')
# Tokenize sentences
encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
# Compute token embeddings
with torch.no_grad():
model_output = model(**encoded_input)
# Perform pooling
sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
# Normalize embeddings
sentence_embeddings = F.normalize(sentence_embeddings, p=2, dim=1)
print("Sentence embeddings:")
print(sentence_embeddings)
```
------
## Background
The project aims to train sentence embedding models on very large sentence level datasets using a self-supervised
contrastive learning objective. We used the pretrained [`nreimers/MiniLM-L6-H384-uncased`](https://huggingface.co/nreimers/MiniLM-L6-H384-uncased) model and fine-tuned in on a
1B sentence pairs dataset. We use a contrastive learning objective: given a sentence from the pair, the model should predict which out of a set of randomly sampled other sentences, was actually paired with it in our dataset.
We developed this model during the
[Community week using JAX/Flax for NLP & CV](https://discuss.huggingface.co/t/open-to-the-community-community-week-using-jax-flax-for-nlp-cv/7104),
organized by Hugging Face. We developed this model as part of the project:
[Train the Best Sentence Embedding Model Ever with 1B Training Pairs](https://discuss.huggingface.co/t/train-the-best-sentence-embedding-model-ever-with-1b-training-pairs/7354). We benefited from efficient hardware infrastructure to run the project: 7 TPUs v3-8, as well as intervention from Googles Flax, JAX, and Cloud team member about efficient deep learning frameworks.
## Intended uses
Our model is intended to be used as a sentence and short paragraph encoder. Given an input text, it outputs a vector which captures
the semantic information. The sentence vector may be used for information retrieval, clustering or sentence similarity tasks.
By default, input text longer than 256 word pieces is truncated.
## Training procedure
### Pre-training
We use the pretrained [`nreimers/MiniLM-L6-H384-uncased`](https://huggingface.co/nreimers/MiniLM-L6-H384-uncased) model. Please refer to the model card for more detailed information about the pre-training procedure.
### Fine-tuning
We fine-tune the model using a contrastive objective. Formally, we compute the cosine similarity from each possible sentence pairs from the batch.
We then apply the cross entropy loss by comparing with true pairs.
#### Hyper parameters
We trained our model on a TPU v3-8. We train the model during 100k steps using a batch size of 1024 (128 per TPU core).
We use a learning rate warm up of 500. The sequence length was limited to 128 tokens. We used the AdamW optimizer with
a 2e-5 learning rate. The full training script is accessible in this current repository: `train_script.py`.
#### Training data
We use the concatenation from multiple datasets to fine-tune our model. The total number of sentence pairs is above 1 billion sentences.
We sampled each dataset given a weighted probability which configuration is detailed in the `data_config.json` file.
| Dataset | Paper | Number of training tuples |
|--------------------------------------------------------|:----------------------------------------:|:--------------------------:|
| [Reddit comments (2015-2018)](https://github.com/PolyAI-LDN/conversational-datasets/tree/master/reddit) | [paper](https://arxiv.org/abs/1904.06472) | 726,484,430 |
| [S2ORC](https://github.com/allenai/s2orc) Citation pairs (Abstracts) | [paper](https://aclanthology.org/2020.acl-main.447/) | 116,288,806 |
| [WikiAnswers](https://github.com/afader/oqa#wikianswers-corpus) Duplicate question pairs | [paper](https://doi.org/10.1145/2623330.2623677) | 77,427,422 |
| [PAQ](https://github.com/facebookresearch/PAQ) (Question, Answer) pairs | [paper](https://arxiv.org/abs/2102.07033) | 64,371,441 |
| [S2ORC](https://github.com/allenai/s2orc) Citation pairs (Titles) | [paper](https://aclanthology.org/2020.acl-main.447/) | 52,603,982 |
| [S2ORC](https://github.com/allenai/s2orc) (Title, Abstract) | [paper](https://aclanthology.org/2020.acl-main.447/) | 41,769,185 |
| [Stack Exchange](https://huggingface.co/datasets/flax-sentence-embeddings/stackexchange_xml) (Title, Body) pairs | - | 25,316,456 |
| [Stack Exchange](https://huggingface.co/datasets/flax-sentence-embeddings/stackexchange_xml) (Title+Body, Answer) pairs | - | 21,396,559 |
| [Stack Exchange](https://huggingface.co/datasets/flax-sentence-embeddings/stackexchange_xml) (Title, Answer) pairs | - | 21,396,559 |
| [MS MARCO](https://microsoft.github.io/msmarco/) triplets | [paper](https://doi.org/10.1145/3404835.3462804) | 9,144,553 |
| [GOOAQ: Open Question Answering with Diverse Answer Types](https://github.com/allenai/gooaq) | [paper](https://arxiv.org/pdf/2104.08727.pdf) | 3,012,496 |
| [Yahoo Answers](https://www.kaggle.com/soumikrakshit/yahoo-answers-dataset) (Title, Answer) | [paper](https://proceedings.neurips.cc/paper/2015/hash/250cf8b51c773f3f8dc8b4be867a9a02-Abstract.html) | 1,198,260 |
| [Code Search](https://huggingface.co/datasets/code_search_net) | - | 1,151,414 |
| [COCO](https://cocodataset.org/#home) Image captions | [paper](https://link.springer.com/chapter/10.1007%2F978-3-319-10602-1_48) | 828,395|
| [SPECTER](https://github.com/allenai/specter) citation triplets | [paper](https://doi.org/10.18653/v1/2020.acl-main.207) | 684,100 |
| [Yahoo Answers](https://www.kaggle.com/soumikrakshit/yahoo-answers-dataset) (Question, Answer) | [paper](https://proceedings.neurips.cc/paper/2015/hash/250cf8b51c773f3f8dc8b4be867a9a02-Abstract.html) | 681,164 |
| [Yahoo Answers](https://www.kaggle.com/soumikrakshit/yahoo-answers-dataset) (Title, Question) | [paper](https://proceedings.neurips.cc/paper/2015/hash/250cf8b51c773f3f8dc8b4be867a9a02-Abstract.html) | 659,896 |
| [SearchQA](https://huggingface.co/datasets/search_qa) | [paper](https://arxiv.org/abs/1704.05179) | 582,261 |
| [Eli5](https://huggingface.co/datasets/eli5) | [paper](https://doi.org/10.18653/v1/p19-1346) | 325,475 |
| [Flickr 30k](https://shannon.cs.illinois.edu/DenotationGraph/) | [paper](https://transacl.org/ojs/index.php/tacl/article/view/229/33) | 317,695 |
| [Stack Exchange](https://huggingface.co/datasets/flax-sentence-embeddings/stackexchange_xml) Duplicate questions (titles) | | 304,525 |
| AllNLI ([SNLI](https://nlp.stanford.edu/projects/snli/) and [MultiNLI](https://cims.nyu.edu/~sbowman/multinli/) | [paper SNLI](https://doi.org/10.18653/v1/d15-1075), [paper MultiNLI](https://doi.org/10.18653/v1/n18-1101) | 277,230 |
| [Stack Exchange](https://huggingface.co/datasets/flax-sentence-embeddings/stackexchange_xml) Duplicate questions (bodies) | | 250,519 |
| [Stack Exchange](https://huggingface.co/datasets/flax-sentence-embeddings/stackexchange_xml) Duplicate questions (titles+bodies) | | 250,460 |
| [Sentence Compression](https://github.com/google-research-datasets/sentence-compression) | [paper](https://www.aclweb.org/anthology/D13-1155/) | 180,000 |
| [Wikihow](https://github.com/pvl/wikihow_pairs_dataset) | [paper](https://arxiv.org/abs/1810.09305) | 128,542 |
| [Altlex](https://github.com/chridey/altlex/) | [paper](https://aclanthology.org/P16-1135.pdf) | 112,696 |
| [Quora Question Triplets](https://quoradata.quora.com/First-Quora-Dataset-Release-Question-Pairs) | - | 103,663 |
| [Simple Wikipedia](https://cs.pomona.edu/~dkauchak/simplification/) | [paper](https://www.aclweb.org/anthology/P11-2117/) | 102,225 |
| [Natural Questions (NQ)](https://ai.google.com/research/NaturalQuestions) | [paper](https://transacl.org/ojs/index.php/tacl/article/view/1455) | 100,231 |
| [SQuAD2.0](https://rajpurkar.github.io/SQuAD-explorer/) | [paper](https://aclanthology.org/P18-2124.pdf) | 87,599 |
| [TriviaQA](https://huggingface.co/datasets/trivia_qa) | - | 73,346 |
| **Total** | | **1,170,060,424** | | null |
67b79c8700245b72c5706777 | google/gemma-3-4b-it | google | null | 1,893,778 | 15,033,376 | manual | 2025-02-20T21:20:07 | 2025-03-21T20:20:53 | transformers | 1,254 | 21 | null | image-text-to-text | null | [
".gitattributes",
"README.md",
"added_tokens.json",
"chat_template.json",
"config.json",
"generation_config.json",
"model-00001-of-00002.safetensors",
"model-00002-of-00002.safetensors",
"model.safetensors.index.json",
"preprocessor_config.json",
"processor_config.json",
"special_tokens_map.js... | 093f9f388b31de276ce2de164bdc2081324b9767 | [
"transformers",
"safetensors",
"gemma3",
"image-text-to-text",
"conversational",
"arxiv:1905.07830",
"arxiv:1905.10044",
"arxiv:1911.11641",
"arxiv:1904.09728",
"arxiv:1705.03551",
"arxiv:1911.01547",
"arxiv:1907.10641",
"arxiv:1903.00161",
"arxiv:2009.03300",
"arxiv:2304.06364",
"arxi... | null | {"architectures": ["Gemma3ForConditionalGeneration"], "model_type": "gemma3", "processor_config": {"chat_template": "{{ bos_token }}\n{%- if messages[0]['role'] == 'system' -%}\n {%- if messages[0]['content'] is string -%}\n {%- set first_user_prefix = messages[0]['content'] + '\n\n' -%}\n {%- else -%}\n {%- set first_user_prefix = messages[0]['content'][0]['text'] + '\n\n' -%}\n {%- endif -%}\n {%- set loop_messages = messages[1:] -%}\n{%- else -%}\n {%- set first_user_prefix = \"\" -%}\n {%- set loop_messages = messages -%}\n{%- endif -%}\n{%- for message in loop_messages -%}\n {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}\n {{ raise_exception(\"Conversation roles must alternate user/assistant/user/assistant/...\") }}\n {%- endif -%}\n {%- if (message['role'] == 'assistant') -%}\n {%- set role = \"model\" -%}\n {%- else -%}\n {%- set role = message['role'] -%}\n {%- endif -%}\n {{ '<start_of_turn>' + role + '\n' + (first_user_prefix if loop.first else \"\") }}\n {%- if message['content'] is string -%}\n {{ message['content'] | trim }}\n {%- elif message['content'] is iterable -%}\n {%- for item in message['content'] -%}\n {%- if item['type'] == 'image' -%}\n {{ '<start_of_image>' }}\n {%- elif item['type'] == 'text' -%}\n {{ item['text'] | trim }}\n {%- endif -%}\n {%- endfor -%}\n {%- else -%}\n {{ raise_exception(\"Invalid content type\") }}\n {%- endif -%}\n {{ '<end_of_turn>\n' }}\n{%- endfor -%}\n{%- if add_generation_prompt -%}\n {{'<start_of_turn>model\n'}}\n{%- endif -%}\n"}, "tokenizer_config": {"bos_token": "<bos>", "chat_template": "{{ bos_token }}\n{%- if messages[0]['role'] == 'system' -%}\n {%- if messages[0]['content'] is string -%}\n {%- set first_user_prefix = messages[0]['content'] + '\n\n' -%}\n {%- else -%}\n {%- set first_user_prefix = messages[0]['content'][0]['text'] + '\n\n' -%}\n {%- endif -%}\n {%- set loop_messages = messages[1:] -%}\n{%- else -%}\n {%- set first_user_prefix = \"\" -%}\n {%- set loop_messages = messages -%}\n{%- endif -%}\n{%- for message in loop_messages -%}\n {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}\n {{ raise_exception(\"Conversation roles must alternate user/assistant/user/assistant/...\") }}\n {%- endif -%}\n {%- if (message['role'] == 'assistant') -%}\n {%- set role = \"model\" -%}\n {%- else -%}\n {%- set role = message['role'] -%}\n {%- endif -%}\n {{ '<start_of_turn>' + role + '\n' + (first_user_prefix if loop.first else \"\") }}\n {%- if message['content'] is string -%}\n {{ message['content'] | trim }}\n {%- elif message['content'] is iterable -%}\n {%- for item in message['content'] -%}\n {%- if item['type'] == 'image' -%}\n {{ '<start_of_image>' }}\n {%- elif item['type'] == 'text' -%}\n {{ item['text'] | trim }}\n {%- endif -%}\n {%- endfor -%}\n {%- else -%}\n {{ raise_exception(\"Invalid content type\") }}\n {%- endif -%}\n {{ '<end_of_turn>\n' }}\n{%- endfor -%}\n{%- if add_generation_prompt -%}\n {{'<start_of_turn>model\n'}}\n{%- endif -%}\n", "eos_token": "<eos>", "pad_token": "<pad>", "unk_token": "<unk>", "use_default_system_prompt": false}} | {
"auto_model": "AutoModelForImageTextToText",
"custom_class": null,
"pipeline_tag": "image-text-to-text",
"processor": "AutoProcessor"
} | {"base_model": "google/gemma-3-4b-pt", "datasets": null, "eval_results": null, "language": null, "library_name": "transformers", "license": "gemma", "license_name": null, "license_link": null, "metrics": null, "model_name": null, "pipeline_tag": "image-text-to-text", "tags": null, "extra_gated_heading": "Access Gemma on Hugging Face", "extra_gated_prompt": "To access Gemma on Hugging Face, you\u2019re required to review and agree to Google\u2019s usage license. To do this, please ensure you\u2019re logged in to Hugging Face and click below. Requests are processed immediately.", "extra_gated_button_content": "Acknowledge license"} | null | null |
68913522f16f3c8aaffccf1f | openai/gpt-oss-120b | openai | null | 4,491,676 | 29,125,641 | False | 2025-08-04T22:33:06 | 2025-08-26T17:25:03 | transformers | 4,608 | 21 | null | text-generation | {"parameters": {"BF16": 2167371072, "U8": 118244966400}, "total": 120412337472} | [
".gitattributes",
"LICENSE",
"README.md",
"USAGE_POLICY",
"chat_template.jinja",
"config.json",
"generation_config.json",
"metal/model.bin",
"model-00000-of-00014.safetensors",
"model-00001-of-00014.safetensors",
"model-00002-of-00014.safetensors",
"model-00003-of-00014.safetensors",
"model-... | b5c939de8f754692c1647ca79fbf85e8c1e70f8a | [
"transformers",
"safetensors",
"gpt_oss",
"text-generation",
"vllm",
"conversational",
"arxiv:2508.10925",
"license:apache-2.0",
"eval-results",
"endpoints_compatible",
"8-bit",
"mxfp4",
"deploy:azure",
"region:us"
] | null | {"architectures": ["GptOssForCausalLM"], "model_type": "gpt_oss", "quantization_config": {"quant_method": "mxfp4"}, "tokenizer_config": {"bos_token": "<|startoftext|>", "eos_token": "<|return|>", "pad_token": "<|endoftext|>"}, "chat_template_jinja": "{#-\n In addition to the normal inputs of `messages` and `tools`, this template also accepts the\n following kwargs:\n - \"builtin_tools\": A list, can contain \"browser\" and/or \"python\".\n - \"model_identity\": A string that optionally describes the model identity.\n - \"reasoning_effort\": A string that describes the reasoning effort, defaults to \"medium\".\n #}\n\n{#- Tool Definition Rendering ============================================== #}\n{%- macro render_typescript_type(param_spec, required_params, is_nullable=false) -%}\n {%- if param_spec.type == \"array\" -%}\n {%- if param_spec['items'] -%}\n {%- if param_spec['items']['type'] == \"string\" -%}\n {{- \"string[]\" }}\n {%- elif param_spec['items']['type'] == \"number\" -%}\n {{- \"number[]\" }}\n {%- elif param_spec['items']['type'] == \"integer\" -%}\n {{- \"number[]\" }}\n {%- elif param_spec['items']['type'] == \"boolean\" -%}\n {{- \"boolean[]\" }}\n {%- else -%}\n {%- set inner_type = render_typescript_type(param_spec['items'], required_params) -%}\n {%- if inner_type == \"object | object\" or inner_type|length > 50 -%}\n {{- \"any[]\" }}\n {%- else -%}\n {{- inner_type + \"[]\" }}\n {%- endif -%}\n {%- endif -%}\n {%- if param_spec.nullable -%}\n {{- \" | null\" }}\n {%- endif -%}\n {%- else -%}\n {{- \"any[]\" }}\n {%- if param_spec.nullable -%}\n {{- \" | null\" }}\n {%- endif -%}\n {%- endif -%}\n {%- elif param_spec.type is defined and param_spec.type is iterable and param_spec.type is not string and param_spec.type is not mapping and param_spec.type[0] is defined -%}\n {#- Handle array of types like [\"object\", \"object\"] from Union[dict, list] #}\n {%- if param_spec.type | length > 1 -%}\n {{- param_spec.type | join(\" | \") }}\n {%- else -%}\n {{- param_spec.type[0] }}\n {%- endif -%}\n {%- elif param_spec.oneOf -%}\n {#- Handle oneOf schemas - check for complex unions and fallback to any #}\n {%- set has_object_variants = false -%}\n {%- for variant in param_spec.oneOf -%}\n {%- if variant.type == \"object\" -%}\n {%- set has_object_variants = true -%}\n {%- endif -%}\n {%- endfor -%}\n {%- if has_object_variants and param_spec.oneOf|length > 1 -%}\n {{- \"any\" }}\n {%- else -%}\n {%- for variant in param_spec.oneOf -%}\n {{- render_typescript_type(variant, required_params) -}}\n {%- if variant.description %}\n {{- \"// \" + variant.description }}\n {%- endif -%}\n {%- if variant.default is defined %}\n {{ \"// default: \" + variant.default|tojson }}\n {%- endif -%}\n {%- if not loop.last %}\n {{- \" | \" }}\n {% endif -%}\n {%- endfor -%}\n {%- endif -%}\n {%- elif param_spec.type == \"string\" -%}\n {%- if param_spec.enum -%}\n {{- '\"' + param_spec.enum|join('\" | \"') + '\"' -}}\n {%- else -%}\n {{- \"string\" }}\n {%- if param_spec.nullable %}\n {{- \" | null\" }}\n {%- endif -%}\n {%- endif -%}\n {%- elif param_spec.type == \"number\" -%}\n {{- \"number\" }}\n {%- elif param_spec.type == \"integer\" -%}\n {{- \"number\" }}\n {%- elif param_spec.type == \"boolean\" -%}\n {{- \"boolean\" }}\n\n {%- elif param_spec.type == \"object\" -%}\n {%- if param_spec.properties -%}\n {{- \"{\\n\" }}\n {%- for prop_name, prop_spec in param_spec.properties.items() -%}\n {{- prop_name -}}\n {%- if prop_name not in (param_spec.required or []) -%}\n {{- \"?\" }}\n {%- endif -%}\n {{- \": \" }}\n {{ render_typescript_type(prop_spec, param_spec.required or []) }}\n {%- if not loop.last -%}\n {{-\", \" }}\n {%- endif -%}\n {%- endfor -%}\n {{- \"}\" }}\n {%- else -%}\n {{- \"object\" }}\n {%- endif -%}\n {%- else -%}\n {{- \"any\" }}\n {%- endif -%}\n{%- endmacro -%}\n\n{%- macro render_tool_namespace(namespace_name, tools) -%}\n {{- \"## \" + namespace_name + \"\\n\\n\" }}\n {{- \"namespace \" + namespace_name + \" {\\n\\n\" }}\n {%- for tool in tools %}\n {%- set tool = tool.function %}\n {{- \"// \" + tool.description + \"\\n\" }}\n {{- \"type \"+ tool.name + \" = \" }}\n {%- if tool.parameters and tool.parameters.properties %}\n {{- \"(_: {\\n\" }}\n {%- for param_name, param_spec in tool.parameters.properties.items() %}\n {%- if param_spec.description %}\n {{- \"// \" + param_spec.description + \"\\n\" }}\n {%- endif %}\n {{- param_name }}\n {%- if param_name not in (tool.parameters.required or []) -%}\n {{- \"?\" }}\n {%- endif -%}\n {{- \": \" }}\n {{- render_typescript_type(param_spec, tool.parameters.required or []) }}\n {%- if param_spec.default is defined -%}\n {%- if param_spec.enum %}\n {{- \", // default: \" + param_spec.default }}\n {%- elif param_spec.oneOf %}\n {{- \"// default: \" + param_spec.default }}\n {%- else %}\n {{- \", // default: \" + param_spec.default|tojson }}\n {%- endif -%}\n {%- endif -%}\n {%- if not loop.last %}\n {{- \",\\n\" }}\n {%- else %}\n {{- \",\\n\" }}\n {%- endif -%}\n {%- endfor %}\n {{- \"}) => any;\\n\\n\" }}\n {%- else -%}\n {{- \"() => any;\\n\\n\" }}\n {%- endif -%}\n {%- endfor %}\n {{- \"} // namespace \" + namespace_name }}\n{%- endmacro -%}\n\n{%- macro render_builtin_tools(browser_tool, python_tool) -%}\n {%- if browser_tool %}\n {{- \"## browser\\n\\n\" }}\n {{- \"// Tool for browsing.\\n\" }}\n {{- \"// The `cursor` appears in brackets before each browsing display: `[{cursor}]`.\\n\" }}\n {{- \"// Cite information from the tool using the following format:\\n\" }}\n {{- \"// `\u3010{cursor}\u2020L{line_start}(-L{line_end})?\u3011`, for example: `\u30106\u2020L9-L11\u3011` or `\u30108\u2020L3\u3011`.\\n\" }}\n {{- \"// Do not quote more than 10 words directly from the tool output.\\n\" }}\n {{- \"// sources=web (default: web)\\n\" }}\n {{- \"namespace browser {\\n\\n\" }}\n {{- \"// Searches for information related to `query` and displays `topn` results.\\n\" }}\n {{- \"type search = (_: {\\n\" }}\n {{- \"query: string,\\n\" }}\n {{- \"topn?: number, // default: 10\\n\" }}\n {{- \"source?: string,\\n\" }}\n {{- \"}) => any;\\n\\n\" }}\n {{- \"// Opens the link `id` from the page indicated by `cursor` starting at line number `loc`, showing `num_lines` lines.\\n\" }}\n {{- \"// Valid link ids are displayed with the formatting: `\u3010{id}\u2020.*\u3011`.\\n\" }}\n {{- \"// If `cursor` is not provided, the most recent page is implied.\\n\" }}\n {{- \"// If `id` is a string, it is treated as a fully qualified URL associated with `source`.\\n\" }}\n {{- \"// If `loc` is not provided, the viewport will be positioned at the beginning of the document or centered on the most relevant passage, if available.\\n\" }}\n {{- \"// Use this function without `id` to scroll to a new location of an opened page.\\n\" }}\n {{- \"type open = (_: {\\n\" }}\n {{- \"id?: number | string, // default: -1\\n\" }}\n {{- \"cursor?: number, // default: -1\\n\" }}\n {{- \"loc?: number, // default: -1\\n\" }}\n {{- \"num_lines?: number, // default: -1\\n\" }}\n {{- \"view_source?: boolean, // default: false\\n\" }}\n {{- \"source?: string,\\n\" }}\n {{- \"}) => any;\\n\\n\" }}\n {{- \"// Finds exact matches of `pattern` in the current page, or the page given by `cursor`.\\n\" }}\n {{- \"type find = (_: {\\n\" }}\n {{- \"pattern: string,\\n\" }}\n {{- \"cursor?: number, // default: -1\\n\" }}\n {{- \"}) => any;\\n\\n\" }}\n {{- \"} // namespace browser\\n\\n\" }}\n {%- endif -%}\n\n {%- if python_tool %}\n {{- \"## python\\n\\n\" }}\n {{- \"Use this tool to execute Python code in your chain of thought. The code will not be shown to the user. This tool should be used for internal reasoning, but not for code that is intended to be visible to the user (e.g. when creating plots, tables, or files).\\n\\n\" }}\n {{- \"When you send a message containing Python code to python, it will be executed in a stateful Jupyter notebook environment. python will respond with the output of the execution or time out after 120.0 seconds. The drive at '/mnt/data' can be used to save and persist user files. Internet access for this session is UNKNOWN. Depends on the cluster.\\n\\n\" }}\n {%- endif -%}\n{%- endmacro -%}\n\n{#- System Message Construction ============================================ #}\n{%- macro build_system_message() -%}\n {%- if model_identity is not defined %}\n {%- set model_identity = \"You are ChatGPT, a large language model trained by OpenAI.\" %}\n {%- endif %}\n {{- model_identity + \"\\n\" }}\n {{- \"Knowledge cutoff: 2024-06\\n\" }}\n {{- \"Current date: \" + strftime_now(\"%Y-%m-%d\") + \"\\n\\n\" }}\n {%- if reasoning_effort is not defined %}\n {%- set reasoning_effort = \"medium\" %}\n {%- endif %}\n {{- \"Reasoning: \" + reasoning_effort + \"\\n\\n\" }}\n {%- if builtin_tools %}\n {{- \"# Tools\\n\\n\" }}\n {%- set available_builtin_tools = namespace(browser=false, python=false) %}\n {%- for tool in builtin_tools %}\n {%- if tool == \"browser\" %}\n {%- set available_builtin_tools.browser = true %}\n {%- elif tool == \"python\" %}\n {%- set available_builtin_tools.python = true %}\n {%- endif %}\n {%- endfor %}\n {{- render_builtin_tools(available_builtin_tools.browser, available_builtin_tools.python) }}\n {%- endif -%}\n {{- \"# Valid channels: analysis, commentary, final. Channel must be included for every message.\" }}\n {%- if tools -%}\n {{- \"\\nCalls to these tools must go to the commentary channel: 'functions'.\" }}\n {%- endif -%}\n{%- endmacro -%}\n\n{#- Main Template Logic ================================================= #}\n{#- Set defaults #}\n\n{#- Render system message #}\n{{- \"<|start|>system<|message|>\" }}\n{{- build_system_message() }}\n{{- \"<|end|>\" }}\n\n{#- Extract developer message #}\n{%- if messages[0].role == \"developer\" or messages[0].role == \"system\" %}\n {%- set developer_message = messages[0].content %}\n {%- set loop_messages = messages[1:] %}\n{%- else %}\n {%- set developer_message = \"\" %}\n {%- set loop_messages = messages %}\n{%- endif %}\n\n{#- Render developer message #}\n{%- if developer_message or tools %}\n {{- \"<|start|>developer<|message|>\" }}\n {%- if developer_message %}\n {{- \"# Instructions\\n\\n\" }}\n {{- developer_message }}\n {{- \"\\n\\n\" }}\n {%- endif %}\n {%- if tools -%}\n {{- \"# Tools\\n\\n\" }}\n {{- render_tool_namespace(\"functions\", tools) }}\n {%- endif -%}\n {{- \"<|end|>\" }}\n{%- endif %}\n\n{#- Render messages #}\n{%- set last_tool_call = namespace(name=none) %}\n{%- for message in loop_messages -%}\n {#- At this point only assistant/user/tool messages should remain #}\n {%- if message.role == 'assistant' -%}\n {#- Checks to ensure the messages are being passed in the format we expect #}\n {%- if \"content\" in message %}\n {%- if \"<|channel|>analysis<|message|>\" in message.content or \"<|channel|>final<|message|>\" in message.content %}\n {{- raise_exception(\"You have passed a message containing <|channel|> tags in the content field. Instead of doing this, you should pass analysis messages (the string between '<|message|>' and '<|end|>') in the 'thinking' field, and final messages (the string between '<|message|>' and '<|end|>') in the 'content' field.\") }}\n {%- endif %}\n {%- endif %}\n {%- if \"thinking\" in message %}\n {%- if \"<|channel|>analysis<|message|>\" in message.thinking or \"<|channel|>final<|message|>\" in message.thinking %}\n {{- raise_exception(\"You have passed a message containing <|channel|> tags in the thinking field. Instead of doing this, you should pass analysis messages (the string between '<|message|>' and '<|end|>') in the 'thinking' field, and final messages (the string between '<|message|>' and '<|end|>') in the 'content' field.\") }}\n {%- endif %}\n {%- endif %}\n {%- if \"tool_calls\" in message %}\n {#- We need very careful handling here - we want to drop the tool call analysis message if the model #}\n {#- has output a later <|final|> message, but otherwise we want to retain it. This is the only case #}\n {#- when we render CoT/analysis messages in inference. #}\n {%- set future_final_message = namespace(found=false) %}\n {%- for future_message in loop_messages[loop.index:] %}\n {%- if future_message.role == 'assistant' and \"tool_calls\" not in future_message %}\n {%- set future_final_message.found = true %}\n {%- endif %}\n {%- endfor %}\n {#- We assume max 1 tool call per message, and so we infer the tool call name #}\n {#- in \"tool\" messages from the most recent assistant tool call name #}\n {%- set tool_call = message.tool_calls[0] %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {%- if message.content and message.thinking %}\n {{- raise_exception(\"Cannot pass both content and thinking in an assistant message with tool calls! Put the analysis message in one or the other, but not both.\") }}\n {%- elif message.content and not future_final_message.found %}\n {{- \"<|start|>assistant<|channel|>analysis<|message|>\" + message.content + \"<|end|>\" }}\n {%- elif message.thinking and not future_final_message.found %}\n {{- \"<|start|>assistant<|channel|>analysis<|message|>\" + message.thinking + \"<|end|>\" }}\n {%- endif %}\n {{- \"<|start|>assistant to=\" }}\n {{- \"functions.\" + tool_call.name + \"<|channel|>commentary \" }}\n {{- (tool_call.content_type if tool_call.content_type is defined else \"json\") + \"<|message|>\" }}\n {{- tool_call.arguments|tojson }}\n {{- \"<|call|>\" }}\n {%- set last_tool_call.name = tool_call.name %}\n {%- elif loop.last and not add_generation_prompt %}\n {#- Only render the CoT if the final turn is an assistant turn and add_generation_prompt is false #}\n {#- This is a situation that should only occur in training, never in inference. #}\n {%- if \"thinking\" in message %}\n {{- \"<|start|>assistant<|channel|>analysis<|message|>\" + message.thinking + \"<|end|>\" }}\n {%- endif %}\n {#- <|return|> indicates the end of generation, but <|end|> does not #}\n {#- <|return|> should never be an input to the model, but we include it as the final token #}\n {#- when training, so the model learns to emit it. #}\n {{- \"<|start|>assistant<|channel|>final<|message|>\" + message.content + \"<|return|>\" }}\n {%- else %}\n {#- CoT is dropped during all previous turns, so we never render it for inference #}\n {{- \"<|start|>assistant<|channel|>final<|message|>\" + message.content + \"<|end|>\" }}\n {%- set last_tool_call.name = none %}\n {%- endif %}\n {%- elif message.role == 'tool' -%}\n {%- if last_tool_call.name is none %}\n {{- raise_exception(\"Message has tool role, but there was no previous assistant message with a tool call!\") }}\n {%- endif %}\n {{- \"<|start|>functions.\" + last_tool_call.name }}\n {{- \" to=assistant<|channel|>commentary<|message|>\" + message.content|tojson + \"<|end|>\" }}\n {%- elif message.role == 'user' -%}\n {{- \"<|start|>user<|message|>\" + message.content + \"<|end|>\" }}\n {%- endif -%}\n{%- endfor -%}\n\n{#- Generation prompt #}\n{%- if add_generation_prompt -%}\n<|start|>assistant\n{%- endif -%}"} | {
"auto_model": "AutoModelForCausalLM",
"custom_class": null,
"pipeline_tag": "text-generation",
"processor": "AutoTokenizer"
} | {"base_model": null, "datasets": null, "eval_results": null, "language": null, "library_name": "transformers", "license": "apache-2.0", "license_name": null, "license_link": null, "metrics": null, "model_name": null, "pipeline_tag": "text-generation", "tags": ["vllm"]} | <p align="center">
<img alt="gpt-oss-120b" src="https://raw.githubusercontent.com/openai/gpt-oss/main/docs/gpt-oss-120b.svg">
</p>
<p align="center">
<a href="https://gpt-oss.com"><strong>Try gpt-oss</strong></a> ·
<a href="https://cookbook.openai.com/topic/gpt-oss"><strong>Guides</strong></a> ·
<a href="https://arxiv.org/abs/2508.10925"><strong>Model card</strong></a> ·
<a href="https://openai.com/index/introducing-gpt-oss/"><strong>OpenAI blog</strong></a>
</p>
<br>
Welcome to the gpt-oss series, [OpenAI’s open-weight models](https://openai.com/open-models) designed for powerful reasoning, agentic tasks, and versatile developer use cases.
We’re releasing two flavors of these open models:
- `gpt-oss-120b` — for production, general purpose, high reasoning use cases that fit into a single 80GB GPU (like NVIDIA H100 or AMD MI300X) (117B parameters with 5.1B active parameters)
- `gpt-oss-20b` — for lower latency, and local or specialized use cases (21B parameters with 3.6B active parameters)
Both models were trained on our [harmony response format](https://github.com/openai/harmony) and should only be used with the harmony format as it will not work correctly otherwise.
> [!NOTE]
> This model card is dedicated to the larger `gpt-oss-120b` model. Check out [`gpt-oss-20b`](https://huggingface.co/openai/gpt-oss-20b) for the smaller model.
# Highlights
* **Permissive Apache 2.0 license:** Build freely without copyleft restrictions or patent risk—ideal for experimentation, customization, and commercial deployment.
* **Configurable reasoning effort:** Easily adjust the reasoning effort (low, medium, high) based on your specific use case and latency needs.
* **Full chain-of-thought:** Gain complete access to the model’s reasoning process, facilitating easier debugging and increased trust in outputs. It’s not intended to be shown to end users.
* **Fine-tunable:** Fully customize models to your specific use case through parameter fine-tuning.
* **Agentic capabilities:** Use the models’ native capabilities for function calling, [web browsing](https://github.com/openai/gpt-oss/tree/main?tab=readme-ov-file#browser), [Python code execution](https://github.com/openai/gpt-oss/tree/main?tab=readme-ov-file#python), and Structured Outputs.
* **MXFP4 quantization:** The models were post-trained with MXFP4 quantization of the MoE weights, making `gpt-oss-120b` run on a single 80GB GPU (like NVIDIA H100 or AMD MI300X) and the `gpt-oss-20b` model run within 16GB of memory. All evals were performed with the same MXFP4 quantization.
---
# Inference examples
## Transformers
You can use `gpt-oss-120b` and `gpt-oss-20b` with Transformers. If you use the Transformers chat template, it will automatically apply the [harmony response format](https://github.com/openai/harmony). If you use `model.generate` directly, you need to apply the harmony format manually using the chat template or use our [openai-harmony](https://github.com/openai/harmony) package.
To get started, install the necessary dependencies to setup your environment:
```
pip install -U transformers kernels torch
```
Once, setup you can proceed to run the model by running the snippet below:
```py
from transformers import pipeline
import torch
model_id = "openai/gpt-oss-120b"
pipe = pipeline(
"text-generation",
model=model_id,
torch_dtype="auto",
device_map="auto",
)
messages = [
{"role": "user", "content": "Explain quantum mechanics clearly and concisely."},
]
outputs = pipe(
messages,
max_new_tokens=256,
)
print(outputs[0]["generated_text"][-1])
```
Alternatively, you can run the model via [`Transformers Serve`](https://huggingface.co/docs/transformers/main/serving) to spin up a OpenAI-compatible webserver:
```
transformers serve
transformers chat localhost:8000 --model-name-or-path openai/gpt-oss-120b
```
[Learn more about how to use gpt-oss with Transformers.](https://cookbook.openai.com/articles/gpt-oss/run-transformers)
## vLLM
vLLM recommends using [uv](https://docs.astral.sh/uv/) for Python dependency management. You can use vLLM to spin up an OpenAI-compatible webserver. The following command will automatically download the model and start the server.
```bash
uv pip install --pre vllm==0.10.1+gptoss \
--extra-index-url https://wheels.vllm.ai/gpt-oss/ \
--extra-index-url https://download.pytorch.org/whl/nightly/cu128 \
--index-strategy unsafe-best-match
vllm serve openai/gpt-oss-120b
```
[Learn more about how to use gpt-oss with vLLM.](https://cookbook.openai.com/articles/gpt-oss/run-vllm)
## PyTorch / Triton
To learn about how to use this model with PyTorch and Triton, check out our [reference implementations in the gpt-oss repository](https://github.com/openai/gpt-oss?tab=readme-ov-file#reference-pytorch-implementation).
## Ollama
If you are trying to run gpt-oss on consumer hardware, you can use Ollama by running the following commands after [installing Ollama](https://ollama.com/download).
```bash
# gpt-oss-120b
ollama pull gpt-oss:120b
ollama run gpt-oss:120b
```
[Learn more about how to use gpt-oss with Ollama.](https://cookbook.openai.com/articles/gpt-oss/run-locally-ollama)
#### LM Studio
If you are using [LM Studio](https://lmstudio.ai/) you can use the following commands to download.
```bash
# gpt-oss-120b
lms get openai/gpt-oss-120b
```
Check out our [awesome list](https://github.com/openai/gpt-oss/blob/main/awesome-gpt-oss.md) for a broader collection of gpt-oss resources and inference partners.
---
# Download the model
You can download the model weights from the [Hugging Face Hub](https://huggingface.co/collections/openai/gpt-oss-68911959590a1634ba11c7a4) directly from Hugging Face CLI:
```shell
# gpt-oss-120b
huggingface-cli download openai/gpt-oss-120b --include "original/*" --local-dir gpt-oss-120b/
pip install gpt-oss
python -m gpt_oss.chat model/
```
# Reasoning levels
You can adjust the reasoning level that suits your task across three levels:
* **Low:** Fast responses for general dialogue.
* **Medium:** Balanced speed and detail.
* **High:** Deep and detailed analysis.
The reasoning level can be set in the system prompts, e.g., "Reasoning: high".
# Tool use
The gpt-oss models are excellent for:
* Web browsing (using built-in browsing tools)
* Function calling with defined schemas
* Agentic operations like browser tasks
# Fine-tuning
Both gpt-oss models can be fine-tuned for a variety of specialized use cases.
This larger model `gpt-oss-120b` can be fine-tuned on a single H100 node, whereas the smaller [`gpt-oss-20b`](https://huggingface.co/openai/gpt-oss-20b) can even be fine-tuned on consumer hardware.
# Citation
```bibtex
@misc{openai2025gptoss120bgptoss20bmodel,
title={gpt-oss-120b & gpt-oss-20b Model Card},
author={OpenAI},
year={2025},
eprint={2508.10925},
archivePrefix={arXiv},
primaryClass={cs.CL},
url={https://arxiv.org/abs/2508.10925},
}
``` | null |
683f05dc98de733bf4c59f3d | Qwen/Qwen3-Embedding-0.6B | Qwen | null | 5,258,492 | 35,975,034 | False | 2025-06-03T14:25:32 | 2025-06-20T09:31:05 | sentence-transformers | 944 | 18 | null | feature-extraction | {"parameters": {"BF16": 595776512}, "total": 595776512} | [
".gitattributes",
"1_Pooling/config.json",
"README.md",
"config.json",
"config_sentence_transformers.json",
"generation_config.json",
"merges.txt",
"model.safetensors",
"modules.json",
"tokenizer.json",
"tokenizer_config.json",
"vocab.json"
] | c54f2e6e80b2d7b7de06f51cec4959f6b3e03418 | [
"sentence-transformers",
"safetensors",
"qwen3",
"text-generation",
"transformers",
"sentence-similarity",
"feature-extraction",
"text-embeddings-inference",
"arxiv:2506.05176",
"base_model:Qwen/Qwen3-0.6B-Base",
"base_model:finetune:Qwen/Qwen3-0.6B-Base",
"license:apache-2.0",
"endpoints_co... | null | {"architectures": ["Qwen3ForCausalLM"], "model_type": "qwen3", "tokenizer_config": {"bos_token": null, "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].role == 'system' %}\n {{- messages[0].content + '\\n\\n' }}\n {%- endif %}\n {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n {%- set index = (messages|length - 1) - loop.index0 %}\n {%- if ns.multi_step_tool and message.role == \"user\" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n {%- set ns.multi_step_tool = false %}\n {%- set ns.last_query_index = index %}\n {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {%- set content = message.content %}\n {%- set reasoning_content = '' %}\n {%- if message.reasoning_content is defined and message.reasoning_content is not none %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- if '</think>' in message.content %}\n {%- set content = message.content.split('</think>')[-1].lstrip('\\n') %}\n {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n {%- endif %}\n {%- endif %}\n {%- if loop.index0 > ns.last_query_index %}\n {%- if loop.last or (not loop.last and reasoning_content) %}\n {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and content) or (not loop.first) %}\n {{- '\\n' }}\n {%- endif %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments | tojson }}\n {%- endif %}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n {%- if enable_thinking is defined and enable_thinking is false %}\n {{- '<think>\\n\\n</think>\\n\\n' }}\n {%- endif %}\n{%- endif %}", "eos_token": "<|im_end|>", "pad_token": "<|endoftext|>", "unk_token": null}} | {
"auto_model": "AutoModelForCausalLM",
"custom_class": null,
"pipeline_tag": "text-generation",
"processor": "AutoTokenizer"
} | {"base_model": ["Qwen/Qwen3-0.6B-Base"], "datasets": null, "eval_results": null, "language": null, "library_name": null, "license": "apache-2.0", "license_name": null, "license_link": null, "metrics": null, "model_name": null, "pipeline_tag": null, "tags": ["transformers", "sentence-transformers", "sentence-similarity", "feature-extraction", "text-embeddings-inference"]} | # Qwen3-Embedding-0.6B
<p align="center">
<img src="https://qianwen-res.oss-accelerate-overseas.aliyuncs.com/logo_qwen3.png" width="400"/>
<p>
## Highlights
The Qwen3 Embedding model series is the latest proprietary model of the Qwen family, specifically designed for text embedding and ranking tasks. Building upon the dense foundational models of the Qwen3 series, it provides a comprehensive range of text embeddings and reranking models in various sizes (0.6B, 4B, and 8B). This series inherits the exceptional multilingual capabilities, long-text understanding, and reasoning skills of its foundational model. The Qwen3 Embedding series represents significant advancements in multiple text embedding and ranking tasks, including text retrieval, code retrieval, text classification, text clustering, and bitext mining.
**Exceptional Versatility**: The embedding model has achieved state-of-the-art performance across a wide range of downstream application evaluations. The 8B size embedding model ranks **No.1** in the MTEB multilingual leaderboard (as of June 5, 2025, score **70.58**), while the reranking model excels in various text retrieval scenarios.
**Comprehensive Flexibility**: The Qwen3 Embedding series offers a full spectrum of sizes (from 0.6B to 8B) for both embedding and reranking models, catering to diverse use cases that prioritize efficiency and effectiveness. Developers can seamlessly combine these two modules. Additionally, the embedding model allows for flexible vector definitions across all dimensions, and both embedding and reranking models support user-defined instructions to enhance performance for specific tasks, languages, or scenarios.
**Multilingual Capability**: The Qwen3 Embedding series offer support for over 100 languages, thanks to the multilingual capabilites of Qwen3 models. This includes various programming languages, and provides robust multilingual, cross-lingual, and code retrieval capabilities.
## Model Overview
**Qwen3-Embedding-0.6B** has the following features:
- Model Type: Text Embedding
- Supported Languages: 100+ Languages
- Number of Paramaters: 0.6B
- Context Length: 32k
- Embedding Dimension: Up to 1024, supports user-defined output dimensions ranging from 32 to 1024
For more details, including benchmark evaluation, hardware requirements, and inference performance, please refer to our [blog](https://qwenlm.github.io/blog/qwen3-embedding/), [GitHub](https://github.com/QwenLM/Qwen3-Embedding).
## Qwen3 Embedding Series Model list
| Model Type | Models | Size | Layers | Sequence Length | Embedding Dimension | MRL Support | Instruction Aware |
|------------------|----------------------|------|--------|-----------------|---------------------|-------------|----------------|
| Text Embedding | [Qwen3-Embedding-0.6B](https://huggingface.co/Qwen/Qwen3-Embedding-0.6B) | 0.6B | 28 | 32K | 1024 | Yes | Yes |
| Text Embedding | [Qwen3-Embedding-4B](https://huggingface.co/Qwen/Qwen3-Embedding-4B) | 4B | 36 | 32K | 2560 | Yes | Yes |
| Text Embedding | [Qwen3-Embedding-8B](https://huggingface.co/Qwen/Qwen3-Embedding-8B) | 8B | 36 | 32K | 4096 | Yes | Yes |
| Text Reranking | [Qwen3-Reranker-0.6B](https://huggingface.co/Qwen/Qwen3-Reranker-0.6B) | 0.6B | 28 | 32K | - | - | Yes |
| Text Reranking | [Qwen3-Reranker-4B](https://huggingface.co/Qwen/Qwen3-Reranker-4B) | 4B | 36 | 32K | - | - | Yes |
| Text Reranking | [Qwen3-Reranker-8B](https://huggingface.co/Qwen/Qwen3-Reranker-8B) | 8B | 36 | 32K | - | - | Yes |
> **Note**:
> - `MRL Support` indicates whether the embedding model supports custom dimensions for the final embedding.
> - `Instruction Aware` notes whether the embedding or reranking model supports customizing the input instruction according to different tasks.
> - Our evaluation indicates that, for most downstream tasks, using instructions (instruct) typically yields an improvement of 1% to 5% compared to not using them. Therefore, we recommend that developers create tailored instructions specific to their tasks and scenarios. In multilingual contexts, we also advise users to write their instructions in English, as most instructions utilized during the model training process were originally written in English.
## Usage
With Transformers versions earlier than 4.51.0, you may encounter the following error:
```
KeyError: 'qwen3'
```
### Sentence Transformers Usage
```python
# Requires transformers>=4.51.0
# Requires sentence-transformers>=2.7.0
from sentence_transformers import SentenceTransformer
# Load the model
model = SentenceTransformer("Qwen/Qwen3-Embedding-0.6B")
# We recommend enabling flash_attention_2 for better acceleration and memory saving,
# together with setting `padding_side` to "left":
# model = SentenceTransformer(
# "Qwen/Qwen3-Embedding-0.6B",
# model_kwargs={"attn_implementation": "flash_attention_2", "device_map": "auto"},
# tokenizer_kwargs={"padding_side": "left"},
# )
# The queries and documents to embed
queries = [
"What is the capital of China?",
"Explain gravity",
]
documents = [
"The capital of China is Beijing.",
"Gravity is a force that attracts two bodies towards each other. It gives weight to physical objects and is responsible for the movement of planets around the sun.",
]
# Encode the queries and documents. Note that queries benefit from using a prompt
# Here we use the prompt called "query" stored under `model.prompts`, but you can
# also pass your own prompt via the `prompt` argument
query_embeddings = model.encode(queries, prompt_name="query")
document_embeddings = model.encode(documents)
# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)
# tensor([[0.7646, 0.1414],
# [0.1355, 0.6000]])
```
### Transformers Usage
```python
# Requires transformers>=4.51.0
import torch
import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel
def last_token_pool(last_hidden_states: Tensor,
attention_mask: Tensor) -> Tensor:
left_padding = (attention_mask[:, -1].sum() == attention_mask.shape[0])
if left_padding:
return last_hidden_states[:, -1]
else:
sequence_lengths = attention_mask.sum(dim=1) - 1
batch_size = last_hidden_states.shape[0]
return last_hidden_states[torch.arange(batch_size, device=last_hidden_states.device), sequence_lengths]
def get_detailed_instruct(task_description: str, query: str) -> str:
return f'Instruct: {task_description}\nQuery:{query}'
# Each query must come with a one-sentence instruction that describes the task
task = 'Given a web search query, retrieve relevant passages that answer the query'
queries = [
get_detailed_instruct(task, 'What is the capital of China?'),
get_detailed_instruct(task, 'Explain gravity')
]
# No need to add instruction for retrieval documents
documents = [
"The capital of China is Beijing.",
"Gravity is a force that attracts two bodies towards each other. It gives weight to physical objects and is responsible for the movement of planets around the sun."
]
input_texts = queries + documents
tokenizer = AutoTokenizer.from_pretrained('Qwen/Qwen3-Embedding-0.6B', padding_side='left')
model = AutoModel.from_pretrained('Qwen/Qwen3-Embedding-0.6B')
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
# model = AutoModel.from_pretrained('Qwen/Qwen3-Embedding-0.6B', attn_implementation="flash_attention_2", torch_dtype=torch.float16).cuda()
max_length = 8192
# Tokenize the input texts
batch_dict = tokenizer(
input_texts,
padding=True,
truncation=True,
max_length=max_length,
return_tensors="pt",
)
batch_dict.to(model.device)
outputs = model(**batch_dict)
embeddings = last_token_pool(outputs.last_hidden_state, batch_dict['attention_mask'])
# normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:2] @ embeddings[2:].T)
print(scores.tolist())
# [[0.7645568251609802, 0.14142508804798126], [0.13549736142158508, 0.5999549627304077]]
```
### vLLM Usage
```python
# Requires vllm>=0.8.5
import torch
import vllm
from vllm import LLM
def get_detailed_instruct(task_description: str, query: str) -> str:
return f'Instruct: {task_description}\nQuery:{query}'
# Each query must come with a one-sentence instruction that describes the task
task = 'Given a web search query, retrieve relevant passages that answer the query'
queries = [
get_detailed_instruct(task, 'What is the capital of China?'),
get_detailed_instruct(task, 'Explain gravity')
]
# No need to add instruction for retrieval documents
documents = [
"The capital of China is Beijing.",
"Gravity is a force that attracts two bodies towards each other. It gives weight to physical objects and is responsible for the movement of planets around the sun."
]
input_texts = queries + documents
model = LLM(model="Qwen/Qwen3-Embedding-0.6B", task="embed")
outputs = model.embed(input_texts)
embeddings = torch.tensor([o.outputs.embedding for o in outputs])
scores = (embeddings[:2] @ embeddings[2:].T)
print(scores.tolist())
# [[0.7620252966880798, 0.14078938961029053], [0.1358368694782257, 0.6013815999031067]]
```
📌 **Tip**: We recommend that developers customize the `instruct` according to their specific scenarios, tasks, and languages. Our tests have shown that in most retrieval scenarios, not using an `instruct` on the query side can lead to a drop in retrieval performance by approximately 1% to 5%.
### Text Embeddings Inference (TEI) Usage
You can either run / deploy TEI on NVIDIA GPUs as:
```bash
docker run --gpus all -p 8080:80 -v hf_cache:/data --pull always ghcr.io/huggingface/text-embeddings-inference:cpu-1.7.2 --model-id Qwen/Qwen3-Embedding-0.6B --dtype float16
```
Or on CPU devices as:
```bash
docker run -p 8080:80 -v hf_cache:/data --pull always ghcr.io/huggingface/text-embeddings-inference:1.7.2 --model-id Qwen/Qwen3-Embedding-0.6B
```
And then, generate the embeddings sending a HTTP POST request as:
```bash
curl http://localhost:8080/embed \
-X POST \
-d '{"inputs": ["Instruct: Given a web search query, retrieve relevant passages that answer the query\nQuery: What is the capital of China?", "Instruct: Given a web search query, retrieve relevant passages that answer the query\nQuery: Explain gravity"]}' \
-H "Content-Type: application/json"
```
## Evaluation
### MTEB (Multilingual)
| Model | Size | Mean (Task) | Mean (Type) | Bitxt Mining | Class. | Clust. | Inst. Retri. | Multi. Class. | Pair. Class. | Rerank | Retri. | STS |
|----------------------------------|:-------:|:-------------:|:-------------:|:--------------:|:--------:|:--------:|:--------------:|:---------------:|:--------------:|:--------:|:--------:|:------:|
| NV-Embed-v2 | 7B | 56.29 | 49.58 | 57.84 | 57.29 | 40.80 | 1.04 | 18.63 | 78.94 | 63.82 | 56.72 | 71.10|
| GritLM-7B | 7B | 60.92 | 53.74 | 70.53 | 61.83 | 49.75 | 3.45 | 22.77 | 79.94 | 63.78 | 58.31 | 73.33|
| BGE-M3 | 0.6B | 59.56 | 52.18 | 79.11 | 60.35 | 40.88 | -3.11 | 20.1 | 80.76 | 62.79 | 54.60 | 74.12|
| multilingual-e5-large-instruct | 0.6B | 63.22 | 55.08 | 80.13 | 64.94 | 50.75 | -0.40 | 22.91 | 80.86 | 62.61 | 57.12 | 76.81|
| gte-Qwen2-1.5B-instruct | 1.5B | 59.45 | 52.69 | 62.51 | 58.32 | 52.05 | 0.74 | 24.02 | 81.58 | 62.58 | 60.78 | 71.61|
| gte-Qwen2-7b-Instruct | 7B | 62.51 | 55.93 | 73.92 | 61.55 | 52.77 | 4.94 | 25.48 | 85.13 | 65.55 | 60.08 | 73.98|
| text-embedding-3-large | - | 58.93 | 51.41 | 62.17 | 60.27 | 46.89 | -2.68 | 22.03 | 79.17 | 63.89 | 59.27 | 71.68|
| Cohere-embed-multilingual-v3.0 | - | 61.12 | 53.23 | 70.50 | 62.95 | 46.89 | -1.89 | 22.74 | 79.88 | 64.07 | 59.16 | 74.80|
| Gemini Embedding | - | 68.37 | 59.59 | 79.28 | 71.82 | 54.59 | 5.18 | **29.16** | 83.63 | 65.58 | 67.71 | 79.40|
| **Qwen3-Embedding-0.6B** | 0.6B | 64.33 | 56.00 | 72.22 | 66.83 | 52.33 | 5.09 | 24.59 | 80.83 | 61.41 | 64.64 | 76.17|
| **Qwen3-Embedding-4B** | 4B | 69.45 | 60.86 | 79.36 | 72.33 | 57.15 | **11.56** | 26.77 | 85.05 | 65.08 | 69.60 | 80.86|
| **Qwen3-Embedding-8B** | 8B | **70.58** | **61.69** | **80.89** | **74.00** | **57.65** | 10.06 | 28.66 | **86.40** | **65.63** | **70.88** | **81.08** |
> **Note**: For compared models, the scores are retrieved from MTEB online [leaderboard](https://huggingface.co/spaces/mteb/leaderboard) on May 24th, 2025.
### MTEB (Eng v2)
| MTEB English / Models | Param. | Mean(Task) | Mean(Type) | Class. | Clust. | Pair Class. | Rerank. | Retri. | STS | Summ. |
|--------------------------------|:--------:|:------------:|:------------:|:--------:|:--------:|:-------------:|:---------:|:--------:|:-------:|:-------:|
| multilingual-e5-large-instruct | 0.6B | 65.53 | 61.21 | 75.54 | 49.89 | 86.24 | 48.74 | 53.47 | 84.72 | 29.89 |
| NV-Embed-v2 | 7.8B | 69.81 | 65.00 | 87.19 | 47.66 | 88.69 | 49.61 | 62.84 | 83.82 | 35.21 |
| GritLM-7B | 7.2B | 67.07 | 63.22 | 81.25 | 50.82 | 87.29 | 49.59 | 54.95 | 83.03 | 35.65 |
| gte-Qwen2-1.5B-instruct | 1.5B | 67.20 | 63.26 | 85.84 | 53.54 | 87.52 | 49.25 | 50.25 | 82.51 | 33.94 |
| stella_en_1.5B_v5 | 1.5B | 69.43 | 65.32 | 89.38 | 57.06 | 88.02 | 50.19 | 52.42 | 83.27 | 36.91 |
| gte-Qwen2-7B-instruct | 7.6B | 70.72 | 65.77 | 88.52 | 58.97 | 85.9 | 50.47 | 58.09 | 82.69 | 35.74 |
| gemini-embedding-exp-03-07 | - | 73.3 | 67.67 | 90.05 | 59.39 | 87.7 | 48.59 | 64.35 | 85.29 | 38.28 |
| **Qwen3-Embedding-0.6B** | 0.6B | 70.70 | 64.88 | 85.76 | 54.05 | 84.37 | 48.18 | 61.83 | 86.57 | 33.43 |
| **Qwen3-Embedding-4B** | 4B | 74.60 | 68.10 | 89.84 | 57.51 | 87.01 | 50.76 | 68.46 | 88.72 | 34.39 |
| **Qwen3-Embedding-8B** | 8B | 75.22 | 68.71 | 90.43 | 58.57 | 87.52 | 51.56 | 69.44 | 88.58 | 34.83 |
### C-MTEB (MTEB Chinese)
| C-MTEB | Param. | Mean(Task) | Mean(Type) | Class. | Clust. | Pair Class. | Rerank. | Retr. | STS |
|------------------|--------|------------|------------|--------|--------|-------------|---------|-------|-------|
| multilingual-e5-large-instruct | 0.6B | 58.08 | 58.24 | 69.80 | 48.23 | 64.52 | 57.45 | 63.65 | 45.81 |
| bge-multilingual-gemma2 | 9B | 67.64 | 75.31 | 59.30 | 86.67 | 68.28 | 73.73 | 55.19 | - |
| gte-Qwen2-1.5B-instruct | 1.5B | 67.12 | 67.79 | 72.53 | 54.61 | 79.5 | 68.21 | 71.86 | 60.05 |
| gte-Qwen2-7B-instruct | 7.6B | 71.62 | 72.19 | 75.77 | 66.06 | 81.16 | 69.24 | 75.70 | 65.20 |
| ritrieve_zh_v1 | 0.3B | 72.71 | 73.85 | 76.88 | 66.5 | 85.98 | 72.86 | 76.97 | 63.92 |
| **Qwen3-Embedding-0.6B** | 0.6B | 66.33 | 67.45 | 71.40 | 68.74 | 76.42 | 62.58 | 71.03 | 54.52 |
| **Qwen3-Embedding-4B** | 4B | 72.27 | 73.51 | 75.46 | 77.89 | 83.34 | 66.05 | 77.03 | 61.26 |
| **Qwen3-Embedding-8B** | 8B | 73.84 | 75.00 | 76.97 | 80.08 | 84.23 | 66.99 | 78.21 | 63.53 |
## Citation
If you find our work helpful, feel free to give us a cite.
```
@article{qwen3embedding,
title={Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models},
author={Zhang, Yanzhao and Li, Mingxin and Long, Dingkun and Zhang, Xin and Lin, Huan and Yang, Baosong and Xie, Pengjun and Yang, An and Liu, Dayiheng and Lin, Junyang and Huang, Fei and Zhou, Jingren},
journal={arXiv preprint arXiv:2506.05176},
year={2025}
}
``` | null |
66e81cbcd683a3f4e5291bbf | Qwen/Qwen2.5-7B-Instruct | Qwen | null | 19,626,645 | 108,197,333 | False | 2024-09-16T11:55:40 | 2025-01-12T02:10:10 | transformers | 1,154 | 17 | null | text-generation | {"parameters": {"BF16": 7615616512}, "total": 7615616512} | [
".gitattributes",
"LICENSE",
"README.md",
"config.json",
"generation_config.json",
"merges.txt",
"model-00001-of-00004.safetensors",
"model-00002-of-00004.safetensors",
"model-00003-of-00004.safetensors",
"model-00004-of-00004.safetensors",
"model.safetensors.index.json",
"tokenizer.json",
"... | a09a35458c702b33eeacc393d103063234e8bc28 | [
"transformers",
"safetensors",
"qwen2",
"text-generation",
"chat",
"conversational",
"en",
"arxiv:2309.00071",
"arxiv:2407.10671",
"base_model:Qwen/Qwen2.5-7B",
"base_model:finetune:Qwen/Qwen2.5-7B",
"license:apache-2.0",
"text-generation-inference",
"endpoints_compatible",
"deploy:azure... | null | {"architectures": ["Qwen2ForCausalLM"], "model_type": "qwen2", "tokenizer_config": {"bos_token": null, "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n", "eos_token": "<|im_end|>", "pad_token": "<|endoftext|>", "unk_token": null}} | {
"auto_model": "AutoModelForCausalLM",
"custom_class": null,
"pipeline_tag": "text-generation",
"processor": "AutoTokenizer"
} | {"base_model": "Qwen/Qwen2.5-7B", "datasets": null, "eval_results": null, "language": ["en"], "library_name": "transformers", "license": "apache-2.0", "license_name": null, "license_link": "https://huggingface.co/Qwen/Qwen2.5-7B-Instruct/blob/main/LICENSE", "metrics": null, "model_name": null, "pipeline_tag": "text-generation", "tags": ["chat"]} | # Qwen2.5-7B-Instruct
<a href="https://chat.qwenlm.ai/" target="_blank" style="margin: 2px;">
<img alt="Chat" src="https://img.shields.io/badge/%F0%9F%92%9C%EF%B8%8F%20Qwen%20Chat%20-536af5" style="display: inline-block; vertical-align: middle;"/>
</a>
## Introduction
Qwen2.5 is the latest series of Qwen large language models. For Qwen2.5, we release a number of base language models and instruction-tuned language models ranging from 0.5 to 72 billion parameters. Qwen2.5 brings the following improvements upon Qwen2:
- Significantly **more knowledge** and has greatly improved capabilities in **coding** and **mathematics**, thanks to our specialized expert models in these domains.
- Significant improvements in **instruction following**, **generating long texts** (over 8K tokens), **understanding structured data** (e.g, tables), and **generating structured outputs** especially JSON. **More resilient to the diversity of system prompts**, enhancing role-play implementation and condition-setting for chatbots.
- **Long-context Support** up to 128K tokens and can generate up to 8K tokens.
- **Multilingual support** for over 29 languages, including Chinese, English, French, Spanish, Portuguese, German, Italian, Russian, Japanese, Korean, Vietnamese, Thai, Arabic, and more.
**This repo contains the instruction-tuned 7B Qwen2.5 model**, which has the following features:
- Type: Causal Language Models
- Training Stage: Pretraining & Post-training
- Architecture: transformers with RoPE, SwiGLU, RMSNorm, and Attention QKV bias
- Number of Parameters: 7.61B
- Number of Paramaters (Non-Embedding): 6.53B
- Number of Layers: 28
- Number of Attention Heads (GQA): 28 for Q and 4 for KV
- Context Length: Full 131,072 tokens and generation 8192 tokens
- Please refer to [this section](#processing-long-texts) for detailed instructions on how to deploy Qwen2.5 for handling long texts.
For more details, please refer to our [blog](https://qwenlm.github.io/blog/qwen2.5/), [GitHub](https://github.com/QwenLM/Qwen2.5), and [Documentation](https://qwen.readthedocs.io/en/latest/).
## Requirements
The code of Qwen2.5 has been in the latest Hugging face `transformers` and we advise you to use the latest version of `transformers`.
With `transformers<4.37.0`, you will encounter the following error:
```
KeyError: 'qwen2'
```
## Quickstart
Here provides a code snippet with `apply_chat_template` to show you how to load the tokenizer and model and how to generate contents.
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
model_name = "Qwen/Qwen2.5-7B-Instruct"
model = AutoModelForCausalLM.from_pretrained(
model_name,
torch_dtype="auto",
device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained(model_name)
prompt = "Give me a short introduction to large language model."
messages = [
{"role": "system", "content": "You are Qwen, created by Alibaba Cloud. You are a helpful assistant."},
{"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
messages,
tokenize=False,
add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
generated_ids = model.generate(
**model_inputs,
max_new_tokens=512
)
generated_ids = [
output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
```
### Processing Long Texts
The current `config.json` is set for context length up to 32,768 tokens.
To handle extensive inputs exceeding 32,768 tokens, we utilize [YaRN](https://arxiv.org/abs/2309.00071), a technique for enhancing model length extrapolation, ensuring optimal performance on lengthy texts.
For supported frameworks, you could add the following to `config.json` to enable YaRN:
```json
{
...,
"rope_scaling": {
"factor": 4.0,
"original_max_position_embeddings": 32768,
"type": "yarn"
}
}
```
For deployment, we recommend using vLLM.
Please refer to our [Documentation](https://qwen.readthedocs.io/en/latest/deployment/vllm.html) for usage if you are not familar with vLLM.
Presently, vLLM only supports static YARN, which means the scaling factor remains constant regardless of input length, **potentially impacting performance on shorter texts**.
We advise adding the `rope_scaling` configuration only when processing long contexts is required.
## Evaluation & Performance
Detailed evaluation results are reported in this [📑 blog](https://qwenlm.github.io/blog/qwen2.5/).
For requirements on GPU memory and the respective throughput, see results [here](https://qwen.readthedocs.io/en/latest/benchmark/speed_benchmark.html).
## Citation
If you find our work helpful, feel free to give us a cite.
```
@misc{qwen2.5,
title = {Qwen2.5: A Party of Foundation Models},
url = {https://qwenlm.github.io/blog/qwen2.5/},
author = {Qwen Team},
month = {September},
year = {2024}
}
@article{qwen2,
title={Qwen2 Technical Report},
author={An Yang and Baosong Yang and Binyuan Hui and Bo Zheng and Bowen Yu and Chang Zhou and Chengpeng Li and Chengyuan Li and Dayiheng Liu and Fei Huang and Guanting Dong and Haoran Wei and Huan Lin and Jialong Tang and Jialin Wang and Jian Yang and Jianhong Tu and Jianwei Zhang and Jianxin Ma and Jin Xu and Jingren Zhou and Jinze Bai and Jinzheng He and Junyang Lin and Kai Dang and Keming Lu and Keqin Chen and Kexin Yang and Mei Li and Mingfeng Xue and Na Ni and Pei Zhang and Peng Wang and Ru Peng and Rui Men and Ruize Gao and Runji Lin and Shijie Wang and Shuai Bai and Sinan Tan and Tianhang Zhu and Tianhao Li and Tianyu Liu and Wenbin Ge and Xiaodong Deng and Xiaohuan Zhou and Xingzhang Ren and Xinyu Zhang and Xipin Wei and Xuancheng Ren and Yang Fan and Yang Yao and Yichang Zhang and Yu Wan and Yunfei Chu and Yuqiong Liu and Zeyu Cui and Zhenru Zhang and Zhihao Fan},
journal={arXiv preprint arXiv:2407.10671},
year={2024}
}
``` | null |
680da718233834890aa01f51 | Qwen/Qwen3-0.6B | Qwen | null | 13,820,887 | 72,342,262 | False | 2025-04-27T03:40:08 | 2025-07-26T03:46:27 | transformers | 1,154 | 15 | null | text-generation | {"parameters": {"BF16": 751632384}, "total": 751632384} | [
".gitattributes",
"LICENSE",
"README.md",
"config.json",
"generation_config.json",
"merges.txt",
"model.safetensors",
"tokenizer.json",
"tokenizer_config.json",
"vocab.json"
] | c1899de289a04d12100db370d81485cdf75e47ca | [
"transformers",
"safetensors",
"qwen3",
"text-generation",
"conversational",
"arxiv:2505.09388",
"base_model:Qwen/Qwen3-0.6B-Base",
"base_model:finetune:Qwen/Qwen3-0.6B-Base",
"license:apache-2.0",
"text-generation-inference",
"endpoints_compatible",
"deploy:azure",
"region:us"
] | null | {"architectures": ["Qwen3ForCausalLM"], "model_type": "qwen3", "tokenizer_config": {"bos_token": null, "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].role == 'system' %}\n {{- messages[0].content + '\\n\\n' }}\n {%- endif %}\n {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n {%- set index = (messages|length - 1) - loop.index0 %}\n {%- if ns.multi_step_tool and message.role == \"user\" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n {%- set ns.multi_step_tool = false %}\n {%- set ns.last_query_index = index %}\n {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n {%- if message.content is string %}\n {%- set content = message.content %}\n {%- else %}\n {%- set content = '' %}\n {%- endif %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {%- set reasoning_content = '' %}\n {%- if message.reasoning_content is string %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- if '</think>' in content %}\n {%- set reasoning_content = content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n {%- set content = content.split('</think>')[-1].lstrip('\\n') %}\n {%- endif %}\n {%- endif %}\n {%- if loop.index0 > ns.last_query_index %}\n {%- if loop.last or (not loop.last and reasoning_content) %}\n {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and content) or (not loop.first) %}\n {{- '\\n' }}\n {%- endif %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments | tojson }}\n {%- endif %}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n {%- if enable_thinking is defined and enable_thinking is false %}\n {{- '<think>\\n\\n</think>\\n\\n' }}\n {%- endif %}\n{%- endif %}", "eos_token": "<|im_end|>", "pad_token": "<|endoftext|>", "unk_token": null}} | {
"auto_model": "AutoModelForCausalLM",
"custom_class": null,
"pipeline_tag": "text-generation",
"processor": "AutoTokenizer"
} | {"base_model": ["Qwen/Qwen3-0.6B-Base"], "datasets": null, "eval_results": null, "language": null, "library_name": "transformers", "license": "apache-2.0", "license_name": null, "license_link": "https://huggingface.co/Qwen/Qwen3-0.6B/blob/main/LICENSE", "metrics": null, "model_name": null, "pipeline_tag": "text-generation", "tags": null} | null | null |
68ea05fb43df37d95ad2491d | Qwen/Qwen3-VL-8B-Instruct | Qwen | null | 7,671,408 | 19,766,097 | False | 2025-10-11T07:23:39 | 2025-10-15T16:16:59 | transformers | 835 | 15 | null | image-text-to-text | {"parameters": {"BF16": 8767123696}, "total": 8767123696} | [
".gitattributes",
"README.md",
"chat_template.json",
"config.json",
"generation_config.json",
"merges.txt",
"model-00001-of-00004.safetensors",
"model-00002-of-00004.safetensors",
"model-00003-of-00004.safetensors",
"model-00004-of-00004.safetensors",
"model.safetensors.index.json",
"preproces... | 0c351dd01ed87e9c1b53cbc748cba10e6187ff3b | [
"transformers",
"safetensors",
"qwen3_vl",
"image-text-to-text",
"conversational",
"arxiv:2505.09388",
"arxiv:2502.13923",
"arxiv:2409.12191",
"arxiv:2308.12966",
"license:apache-2.0",
"endpoints_compatible",
"deploy:azure",
"region:us"
] | null | {"architectures": ["Qwen3VLForConditionalGeneration"], "model_type": "qwen3_vl", "processor_config": {"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].role == 'system' %}\n {%- if messages[0].content is string %}\n {{- messages[0].content }}\n {%- else %}\n {%- for content in messages[0].content %}\n {%- if 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '\\n\\n' }}\n {%- endif %}\n {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].content is string %}\n {{- messages[0].content }}\n {%- else %}\n {%- for content in messages[0].content %}\n {%- if 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- for message in messages %}\n {%- if message.role == \"user\" %}\n {{- '<|im_start|>' + message.role + '\\n' }}\n {%- if message.content is string %}\n {{- message.content }}\n {%- else %}\n {%- for content in message.content %}\n {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n {%- set image_count.value = image_count.value + 1 %}\n {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n <|vision_start|><|image_pad|><|vision_end|>\n {%- elif content.type == 'video' or 'video' in content %}\n {%- set video_count.value = video_count.value + 1 %}\n {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n <|vision_start|><|video_pad|><|vision_end|>\n {%- elif 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role + '\\n' }}\n {%- if message.content is string %}\n {{- message.content }}\n {%- else %}\n {%- for content_item in message.content %}\n {%- if 'text' in content_item %}\n {{- content_item.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and message.content) or (not loop.first) %}\n {{- '\\n' }}\n {%- endif %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments | tojson }}\n {%- endif %}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {%- if message.content is string %}\n {{- message.content }}\n {%- else %}\n {%- for content in message.content %}\n {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n {%- set image_count.value = image_count.value + 1 %}\n {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n <|vision_start|><|image_pad|><|vision_end|>\n {%- elif content.type == 'video' or 'video' in content %}\n {%- set video_count.value = video_count.value + 1 %}\n {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n <|vision_start|><|video_pad|><|vision_end|>\n {%- elif 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n"}, "tokenizer_config": {"bos_token": null, "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].role == 'system' %}\n {%- if messages[0].content is string %}\n {{- messages[0].content }}\n {%- else %}\n {%- for content in messages[0].content %}\n {%- if 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '\\n\\n' }}\n {%- endif %}\n {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].content is string %}\n {{- messages[0].content }}\n {%- else %}\n {%- for content in messages[0].content %}\n {%- if 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- for message in messages %}\n {%- if message.role == \"user\" %}\n {{- '<|im_start|>' + message.role + '\\n' }}\n {%- if message.content is string %}\n {{- message.content }}\n {%- else %}\n {%- for content in message.content %}\n {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n {%- set image_count.value = image_count.value + 1 %}\n {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n <|vision_start|><|image_pad|><|vision_end|>\n {%- elif content.type == 'video' or 'video' in content %}\n {%- set video_count.value = video_count.value + 1 %}\n {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n <|vision_start|><|video_pad|><|vision_end|>\n {%- elif 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role + '\\n' }}\n {%- if message.content is string %}\n {{- message.content }}\n {%- else %}\n {%- for content_item in message.content %}\n {%- if 'text' in content_item %}\n {{- content_item.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and message.content) or (not loop.first) %}\n {{- '\\n' }}\n {%- endif %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments | tojson }}\n {%- endif %}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {%- if message.content is string %}\n {{- message.content }}\n {%- else %}\n {%- for content in message.content %}\n {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n {%- set image_count.value = image_count.value + 1 %}\n {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n <|vision_start|><|image_pad|><|vision_end|>\n {%- elif content.type == 'video' or 'video' in content %}\n {%- set video_count.value = video_count.value + 1 %}\n {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n <|vision_start|><|video_pad|><|vision_end|>\n {%- elif 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n", "eos_token": "<|im_end|>", "pad_token": "<|endoftext|>", "unk_token": null}} | {
"auto_model": "AutoModelForImageTextToText",
"custom_class": null,
"pipeline_tag": "image-text-to-text",
"processor": "AutoProcessor"
} | {"base_model": null, "datasets": null, "eval_results": null, "language": null, "library_name": "transformers", "license": "apache-2.0", "license_name": null, "license_link": null, "metrics": null, "model_name": null, "pipeline_tag": "image-text-to-text", "tags": null} | null | null |
67c35be6eae05d8f94fae4c2 | google/gemma-3-12b-it | google | null | 2,388,254 | 11,845,815 | manual | 2025-03-01T19:11:34 | 2025-03-21T20:28:56 | transformers | 694 | 14 | null | image-text-to-text | null | [
".gitattributes",
"README.md",
"added_tokens.json",
"chat_template.json",
"config.json",
"generation_config.json",
"model-00001-of-00005.safetensors",
"model-00002-of-00005.safetensors",
"model-00003-of-00005.safetensors",
"model-00004-of-00005.safetensors",
"model-00005-of-00005.safetensors",
... | 96b6f1eccf38110c56df3a15bffe176da04bfd80 | [
"transformers",
"safetensors",
"gemma3",
"image-text-to-text",
"conversational",
"arxiv:1905.07830",
"arxiv:1905.10044",
"arxiv:1911.11641",
"arxiv:1904.09728",
"arxiv:1705.03551",
"arxiv:1911.01547",
"arxiv:1907.10641",
"arxiv:1903.00161",
"arxiv:2009.03300",
"arxiv:2304.06364",
"arxi... | null | {"architectures": ["Gemma3ForConditionalGeneration"], "model_type": "gemma3", "processor_config": {"chat_template": "{{ bos_token }}\n{%- if messages[0]['role'] == 'system' -%}\n {%- if messages[0]['content'] is string -%}\n {%- set first_user_prefix = messages[0]['content'] + '\n\n' -%}\n {%- else -%}\n {%- set first_user_prefix = messages[0]['content'][0]['text'] + '\n\n' -%}\n {%- endif -%}\n {%- set loop_messages = messages[1:] -%}\n{%- else -%}\n {%- set first_user_prefix = \"\" -%}\n {%- set loop_messages = messages -%}\n{%- endif -%}\n{%- for message in loop_messages -%}\n {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}\n {{ raise_exception(\"Conversation roles must alternate user/assistant/user/assistant/...\") }}\n {%- endif -%}\n {%- if (message['role'] == 'assistant') -%}\n {%- set role = \"model\" -%}\n {%- else -%}\n {%- set role = message['role'] -%}\n {%- endif -%}\n {{ '<start_of_turn>' + role + '\n' + (first_user_prefix if loop.first else \"\") }}\n {%- if message['content'] is string -%}\n {{ message['content'] | trim }}\n {%- elif message['content'] is iterable -%}\n {%- for item in message['content'] -%}\n {%- if item['type'] == 'image' -%}\n {{ '<start_of_image>' }}\n {%- elif item['type'] == 'text' -%}\n {{ item['text'] | trim }}\n {%- endif -%}\n {%- endfor -%}\n {%- else -%}\n {{ raise_exception(\"Invalid content type\") }}\n {%- endif -%}\n {{ '<end_of_turn>\n' }}\n{%- endfor -%}\n{%- if add_generation_prompt -%}\n {{'<start_of_turn>model\n'}}\n{%- endif -%}\n"}, "tokenizer_config": {"bos_token": "<bos>", "chat_template": "{{ bos_token }}\n{%- if messages[0]['role'] == 'system' -%}\n {%- if messages[0]['content'] is string -%}\n {%- set first_user_prefix = messages[0]['content'] + '\n\n' -%}\n {%- else -%}\n {%- set first_user_prefix = messages[0]['content'][0]['text'] + '\n\n' -%}\n {%- endif -%}\n {%- set loop_messages = messages[1:] -%}\n{%- else -%}\n {%- set first_user_prefix = \"\" -%}\n {%- set loop_messages = messages -%}\n{%- endif -%}\n{%- for message in loop_messages -%}\n {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}\n {{ raise_exception(\"Conversation roles must alternate user/assistant/user/assistant/...\") }}\n {%- endif -%}\n {%- if (message['role'] == 'assistant') -%}\n {%- set role = \"model\" -%}\n {%- else -%}\n {%- set role = message['role'] -%}\n {%- endif -%}\n {{ '<start_of_turn>' + role + '\n' + (first_user_prefix if loop.first else \"\") }}\n {%- if message['content'] is string -%}\n {{ message['content'] | trim }}\n {%- elif message['content'] is iterable -%}\n {%- for item in message['content'] -%}\n {%- if item['type'] == 'image' -%}\n {{ '<start_of_image>' }}\n {%- elif item['type'] == 'text' -%}\n {{ item['text'] | trim }}\n {%- endif -%}\n {%- endfor -%}\n {%- else -%}\n {{ raise_exception(\"Invalid content type\") }}\n {%- endif -%}\n {{ '<end_of_turn>\n' }}\n{%- endfor -%}\n{%- if add_generation_prompt -%}\n {{'<start_of_turn>model\n'}}\n{%- endif -%}\n", "eos_token": "<eos>", "pad_token": "<pad>", "unk_token": "<unk>", "use_default_system_prompt": false}} | {
"auto_model": "AutoModelForImageTextToText",
"custom_class": null,
"pipeline_tag": "image-text-to-text",
"processor": "AutoProcessor"
} | {"base_model": "google/gemma-3-12b-pt", "datasets": null, "eval_results": null, "language": null, "library_name": "transformers", "license": "gemma", "license_name": null, "license_link": null, "metrics": null, "model_name": null, "pipeline_tag": "image-text-to-text", "tags": null, "extra_gated_heading": "Access Gemma on Hugging Face", "extra_gated_prompt": "To access Gemma on Hugging Face, you\u2019re required to review and agree to Google\u2019s usage license. To do this, please ensure you\u2019re logged in to Hugging Face and click below. Requests are processed immediately.", "extra_gated_button_content": "Acknowledge license"} | null | null |
680da79d48c19d19cf82ab5e | Qwen/Qwen3-8B | Qwen | null | 9,232,475 | 42,210,523 | False | 2025-04-27T03:42:21 | 2025-07-26T03:49:13 | transformers | 1,005 | 14 | null | text-generation | {"parameters": {"BF16": 8190735360}, "total": 8190735360} | [
".gitattributes",
"LICENSE",
"README.md",
"config.json",
"generation_config.json",
"merges.txt",
"model-00001-of-00005.safetensors",
"model-00002-of-00005.safetensors",
"model-00003-of-00005.safetensors",
"model-00004-of-00005.safetensors",
"model-00005-of-00005.safetensors",
"model.safetensor... | b968826d9c46dd6066d109eabc6255188de91218 | [
"transformers",
"safetensors",
"qwen3",
"text-generation",
"conversational",
"arxiv:2309.00071",
"arxiv:2505.09388",
"base_model:Qwen/Qwen3-8B-Base",
"base_model:finetune:Qwen/Qwen3-8B-Base",
"license:apache-2.0",
"text-generation-inference",
"endpoints_compatible",
"deploy:azure",
"region... | null | {"architectures": ["Qwen3ForCausalLM"], "model_type": "qwen3", "tokenizer_config": {"bos_token": null, "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].role == 'system' %}\n {{- messages[0].content + '\\n\\n' }}\n {%- endif %}\n {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n {%- set index = (messages|length - 1) - loop.index0 %}\n {%- if ns.multi_step_tool and message.role == \"user\" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n {%- set ns.multi_step_tool = false %}\n {%- set ns.last_query_index = index %}\n {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n {%- if message.content is string %}\n {%- set content = message.content %}\n {%- else %}\n {%- set content = '' %}\n {%- endif %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {%- set reasoning_content = '' %}\n {%- if message.reasoning_content is string %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- if '</think>' in content %}\n {%- set reasoning_content = content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n {%- set content = content.split('</think>')[-1].lstrip('\\n') %}\n {%- endif %}\n {%- endif %}\n {%- if loop.index0 > ns.last_query_index %}\n {%- if loop.last or (not loop.last and reasoning_content) %}\n {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and content) or (not loop.first) %}\n {{- '\\n' }}\n {%- endif %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments | tojson }}\n {%- endif %}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n {%- if enable_thinking is defined and enable_thinking is false %}\n {{- '<think>\\n\\n</think>\\n\\n' }}\n {%- endif %}\n{%- endif %}", "eos_token": "<|im_end|>", "pad_token": "<|endoftext|>", "unk_token": null}} | {
"auto_model": "AutoModelForCausalLM",
"custom_class": null,
"pipeline_tag": "text-generation",
"processor": "AutoTokenizer"
} | {"base_model": ["Qwen/Qwen3-8B-Base"], "datasets": null, "eval_results": null, "language": null, "library_name": "transformers", "license": "apache-2.0", "license_name": null, "license_link": "https://huggingface.co/Qwen/Qwen3-8B/blob/main/LICENSE", "metrics": null, "model_name": null, "pipeline_tag": "text-generation", "tags": null} | null | null |
End of preview. Expand in Data Studio
README.md exists but content is empty.
- Downloads last month
- -