Article
New in llama.cpp: Model Management
ā¢
98
John Locke
johnlockejrr
AI & ML interests
NLP, OCR, AI
Recent Activity
upvoted
an
article
1 day ago
New in llama.cpp: Model Management
new activity
1 day ago
nvidia/nemotron-ocr-v1:Finetune `nvidia/nemotron-ocr-v1` recognition model
liked
a dataset
2 days ago
ai4bharat/BPCC
Organizations
upvoted
an
article
1 day ago
Finetune `nvidia/nemotron-ocr-v1` recognition model
1
#7 opened 6 days ago
by
johnlockejrr
liked
a
dataset
2 days ago
reacted to
ronantakizawa's
post with š
3 days ago
Post
5440
Thank you
@clem
(Co-Founder & CEO of Hugging Face) for sharing my dataset on X / Twitter!
ronantakizawa/github-top-developers
#github #dataset
ronantakizawa/github-top-developers
#github #dataset
- 4 replies
updated
a
dataset
5 days ago
liked
a
model
6 days ago
published
a
dataset
7 days ago
upvoted
an
article
8 days ago
Article
Efficient MultiModal Data Pipeline
- +3
ā¢
68
liked
a
dataset
11 days ago
reacted to
danielhanchen's
post with š„
12 days ago
Post
5245
NVIDIA releases Nemotron 3 Nano, a new 30B hybrid reasoning model! š„
Has 1M context window & best in class performance for SWE-Bench, reasoning & chat. Run the MoE model locally with 24GB RAM.
GGUF: unsloth/Nemotron-3-Nano-30B-A3B-GGUF
š Step-by-step Guide: https://docs.unsloth.ai/models/nemotron-3
Has 1M context window & best in class performance for SWE-Bench, reasoning & chat. Run the MoE model locally with 24GB RAM.
GGUF: unsloth/Nemotron-3-Nano-30B-A3B-GGUF
š Step-by-step Guide: https://docs.unsloth.ai/models/nemotron-3
- 1 reply
liked
2
models
23 days ago
reacted to
codelion's
post with š
24 days ago
Post
1600
I just published Ellora - 6 production-ready LoRA recipes for enhancing LLMs with specific capabilities. Each recipe costs under $100 to run and includes complete training code, data generation, and evaluation.
The 6 Recipes:
Recipe 1: Accuracy Recovery - Recover 75% of quantization losses with self-distillation
Recipe 2: Reasoning LoRA - Add structured thinking with GRPO (0% to 60% adoption, 75% quality boost)
Recipe 3: Tool Calling - Real execution on actual codebases
Recipe 4: Context Extension - Scale from 32K to 2M tokens (61x increase)
Recipe 5: Secure Code Generation - 97% vulnerability reduction using automated Semgrep analysis
Recipe 6: Execution-Aware World Models - Teaching models runtime behavior
Why Recipes?
Ellora provides methodologies, not frameworks. Use them with your existing tools (PEFT, LoRAX, vLLM, Unsloth, HuggingFace). Each recipe uses self-supervised data generation (Magpie approach) - no expensive human labeling required.
All recipes include Jupyter notebooks you can run immediately with clear success metrics.
GitHub: https://github.com/codelion/ellora
Full Article: https://huggingface.co/blog/codelion/ellora-lora-recipes
Built something with these recipes? I'd love to see what you create!
The 6 Recipes:
Recipe 1: Accuracy Recovery - Recover 75% of quantization losses with self-distillation
Recipe 2: Reasoning LoRA - Add structured thinking with GRPO (0% to 60% adoption, 75% quality boost)
Recipe 3: Tool Calling - Real execution on actual codebases
Recipe 4: Context Extension - Scale from 32K to 2M tokens (61x increase)
Recipe 5: Secure Code Generation - 97% vulnerability reduction using automated Semgrep analysis
Recipe 6: Execution-Aware World Models - Teaching models runtime behavior
Why Recipes?
Ellora provides methodologies, not frameworks. Use them with your existing tools (PEFT, LoRAX, vLLM, Unsloth, HuggingFace). Each recipe uses self-supervised data generation (Magpie approach) - no expensive human labeling required.
All recipes include Jupyter notebooks you can run immediately with clear success metrics.
GitHub: https://github.com/codelion/ellora
Full Article: https://huggingface.co/blog/codelion/ellora-lora-recipes
Built something with these recipes? I'd love to see what you create!
upvoted
a
changelog
25 days ago
Changelog
Duplicate Datasets
ā¢
86
upvoted
an
article
27 days ago
Article
Transformers v5: Simple model definitions powering the AI ecosystem
- +2
ā¢
256
liked
a
dataset
27 days ago
published
a
dataset
28 days ago
updated
a
dataset
28 days ago
reacted to
danielhanchen's
post with š„
30 days ago
Post
8449
Qwen3-Next can now be Run locally! (30GB RAM)
Instruct GGUF: unsloth/Qwen3-Next-80B-A3B-Instruct-GGUF
The models come in Thinking and Instruct versions and utilize a new architecture, allowing it to have ~10x faster inference than Qwen32B.
š Step-by-step Guide: https://docs.unsloth.ai/models/qwen3-next
Thinking GGUF: unsloth/Qwen3-Next-80B-A3B-Thinking-GGUF
Instruct GGUF: unsloth/Qwen3-Next-80B-A3B-Instruct-GGUF
The models come in Thinking and Instruct versions and utilize a new architecture, allowing it to have ~10x faster inference than Qwen32B.
š Step-by-step Guide: https://docs.unsloth.ai/models/qwen3-next
Thinking GGUF: unsloth/Qwen3-Next-80B-A3B-Thinking-GGUF
liked
a
model
about 1 month ago
