AlexCheema commited on
Commit
3cad8b5
·
verified ·
1 Parent(s): 7ca13bd

Add files using upload-large-folder tool

Browse files
Files changed (50) hide show
  1. README.md +37 -0
  2. config.json +66 -0
  3. generation_config.json +9 -0
  4. model-00001-of-00234.safetensors +3 -0
  5. model-00004-of-00234.safetensors +3 -0
  6. model-00015-of-00234.safetensors +3 -0
  7. model-00028-of-00234.safetensors +3 -0
  8. model-00033-of-00234.safetensors +3 -0
  9. model-00036-of-00234.safetensors +3 -0
  10. model-00039-of-00234.safetensors +3 -0
  11. model-00040-of-00234.safetensors +3 -0
  12. model-00045-of-00234.safetensors +3 -0
  13. model-00051-of-00234.safetensors +3 -0
  14. model-00052-of-00234.safetensors +3 -0
  15. model-00058-of-00234.safetensors +3 -0
  16. model-00072-of-00234.safetensors +3 -0
  17. model-00077-of-00234.safetensors +3 -0
  18. model-00078-of-00234.safetensors +3 -0
  19. model-00081-of-00234.safetensors +3 -0
  20. model-00084-of-00234.safetensors +3 -0
  21. model-00099-of-00234.safetensors +3 -0
  22. model-00112-of-00234.safetensors +3 -0
  23. model-00114-of-00234.safetensors +3 -0
  24. model-00117-of-00234.safetensors +3 -0
  25. model-00118-of-00234.safetensors +3 -0
  26. model-00120-of-00234.safetensors +3 -0
  27. model-00125-of-00234.safetensors +3 -0
  28. model-00138-of-00234.safetensors +3 -0
  29. model-00153-of-00234.safetensors +3 -0
  30. model-00156-of-00234.safetensors +3 -0
  31. model-00158-of-00234.safetensors +3 -0
  32. model-00159-of-00234.safetensors +3 -0
  33. model-00161-of-00234.safetensors +3 -0
  34. model-00164-of-00234.safetensors +3 -0
  35. model-00173-of-00234.safetensors +3 -0
  36. model-00180-of-00234.safetensors +3 -0
  37. model-00192-of-00234.safetensors +3 -0
  38. model-00197-of-00234.safetensors +3 -0
  39. model-00198-of-00234.safetensors +3 -0
  40. model-00200-of-00234.safetensors +3 -0
  41. model-00205-of-00234.safetensors +3 -0
  42. model-00218-of-00234.safetensors +3 -0
  43. model-00223-of-00234.safetensors +3 -0
  44. model-00225-of-00234.safetensors +3 -0
  45. model-00232-of-00234.safetensors +3 -0
  46. model-00234-of-00234.safetensors +3 -0
  47. model.safetensors.index.json +0 -0
  48. special_tokens_map.json +23 -0
  49. tokenizer.json +0 -0
  50. tokenizer_config.json +0 -0
README.md ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ library_name: mlx
4
+ base_model: deepseek-ai/DeepSeek-V3.2
5
+ base_model_relation: finetune
6
+ tags:
7
+ - mlx
8
+ pipeline_tag: text-generation
9
+ ---
10
+
11
+ # mlx-community/DeepSeek-V3.2
12
+
13
+ This model [mlx-community/DeepSeek-V3.2](https://huggingface.co/mlx-community/DeepSeek-V3.2) was
14
+ converted to MLX format from [deepseek-ai/DeepSeek-V3.2](https://huggingface.co/deepseek-ai/DeepSeek-V3.2)
15
+ using mlx-lm version **0.28.4**.
16
+
17
+ ## Use with mlx
18
+
19
+ ```bash
20
+ pip install mlx-lm
21
+ ```
22
+
23
+ ```python
24
+ from mlx_lm import load, generate
25
+
26
+ model, tokenizer = load("mlx-community/DeepSeek-V3.2")
27
+
28
+ prompt = "hello"
29
+
30
+ if tokenizer.chat_template is not None:
31
+ messages = [{"role": "user", "content": prompt}]
32
+ prompt = tokenizer.apply_chat_template(
33
+ messages, add_generation_prompt=True
34
+ )
35
+
36
+ response = generate(model, tokenizer, prompt=prompt, verbose=True)
37
+ ```
config.json ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "DeepseekV32ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 0,
8
+ "eos_token_id": 1,
9
+ "ep_size": 1,
10
+ "first_k_dense_replace": 3,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 7168,
13
+ "index_head_dim": 128,
14
+ "index_n_heads": 64,
15
+ "index_topk": 2048,
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 18432,
18
+ "kv_lora_rank": 512,
19
+ "max_position_embeddings": 163840,
20
+ "model_type": "deepseek_v32",
21
+ "moe_intermediate_size": 2048,
22
+ "moe_layer_freq": 1,
23
+ "n_group": 8,
24
+ "n_routed_experts": 256,
25
+ "n_shared_experts": 1,
26
+ "norm_topk_prob": true,
27
+ "num_attention_heads": 128,
28
+ "num_experts_per_tok": 8,
29
+ "num_hidden_layers": 61,
30
+ "num_key_value_heads": 128,
31
+ "num_nextn_predict_layers": 1,
32
+ "q_lora_rank": 1536,
33
+ "qk_nope_head_dim": 128,
34
+ "qk_rope_head_dim": 64,
35
+ "quantization_config": {
36
+ "activation_scheme": "dynamic",
37
+ "fmt": "e4m3",
38
+ "quant_method": "fp8",
39
+ "scale_fmt": "ue8m0",
40
+ "weight_block_size": [
41
+ 128,
42
+ 128
43
+ ]
44
+ },
45
+ "rms_norm_eps": 1e-06,
46
+ "rope_scaling": {
47
+ "beta_fast": 32,
48
+ "beta_slow": 1,
49
+ "factor": 40,
50
+ "mscale": 1.0,
51
+ "mscale_all_dim": 1.0,
52
+ "original_max_position_embeddings": 4096,
53
+ "type": "yarn"
54
+ },
55
+ "rope_theta": 10000,
56
+ "routed_scaling_factor": 2.5,
57
+ "scoring_func": "sigmoid",
58
+ "tie_word_embeddings": false,
59
+ "topk_group": 4,
60
+ "topk_method": "noaux_tc",
61
+ "torch_dtype": "bfloat16",
62
+ "transformers_version": "4.44.2",
63
+ "use_cache": true,
64
+ "v_head_dim": 128,
65
+ "vocab_size": 129280
66
+ }
generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 1,
5
+ "do_sample": true,
6
+ "temperature": 1.0,
7
+ "top_p": 0.95,
8
+ "transformers_version": "4.46.3"
9
+ }
model-00001-of-00234.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:020cd3b0662502d7fb5871da679e78c0fdec8168aefb34bb88fb49fe9fd228e9
3
+ size 5173750991
model-00004-of-00234.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eda0c0c7a1cc6820ac478c059565ddf085fe0634aed02f51da62679523af625f
3
+ size 7516192927
model-00015-of-00234.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:caeac5d09f6db3c4adc8f9f63be393c3649bc610de9e63805934fa66627fb608
3
+ size 7516192929
model-00028-of-00234.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d40406105a1220a70939c6f28d22be02f67ac60d4cc8a40b9d9f0ffd6db8c57
3
+ size 7516192927
model-00033-of-00234.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e7d5e15f47bf547adb1a2a41c9324cea042d6fb16f222b0f9a5601be07c4c37
3
+ size 7516192930
model-00036-of-00234.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b4f23adc65d33253cbb2ab9820c9947bf8f664eb919e910a0d74b33c91a90ff
3
+ size 7516192928
model-00039-of-00234.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70b73bfa3a89cdd5239ea4054d934f1aa34f545c9d6f5061e5236c3106c30e76
3
+ size 7516192930
model-00040-of-00234.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57cadbe93581645bb93e398179b89194c3f8f0ff84d5f0dc99e7d0e27b986fcf
3
+ size 7516192928
model-00045-of-00234.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e20e5afb6f63c7d3dc6c190239ea66a196ee2b0a20d5546f14a6d88b914431fd
3
+ size 7516192930
model-00051-of-00234.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0d45e35beef8d529fba21dfefa2015d31b67ab55a36d3bac4e3998b1d129f34
3
+ size 7516192930
model-00052-of-00234.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea9049d6a426ffdfdcf3223e65870a32594a8fa5674f8876cbdd33b77a32f09d
3
+ size 7516192928
model-00058-of-00234.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25ecb49094f02d20c7dc7c2ae32e0b02777a49bc6fb56424bd33bbbe1de1f7d5
3
+ size 493915886
model-00072-of-00234.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7bca175927f38c26f8edb3fc4931110514c5afff2e38236dff1cd1bcdf61ac13
3
+ size 7516192928
model-00077-of-00234.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b37362bf7687bb974d9bff68c6e17f17140025cad0567989635bbafd62962114
3
+ size 7516192930
model-00078-of-00234.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6764169667d32dfbe3dca8e709dcc376cc52dfb01cefc0798c02cbced1c33885
3
+ size 493915886
model-00081-of-00234.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a84b8130bfc9c24560694686367e4a600765cbdf7eb2c6f76bf653e41309c09
3
+ size 7516192930
model-00084-of-00234.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b80084399f56905bab4d8f8c3be9c29372ecffe7dbe71ed13656f813e3e589f
3
+ size 7516192928
model-00099-of-00234.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4aa79ab13793e11e3da82cdc028719ba760055c2e45696278328fbcc85a244d
3
+ size 7516192930
model-00112-of-00234.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80083c1437aed778354968dfaf67d4ce02cca0c37b0f9f0ee000fc89de0e853a
3
+ size 7516192928
model-00114-of-00234.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8286cda1a95940da5d18b658050987065ebec562d8fb62c3c85743004ea775a
3
+ size 493915890
model-00117-of-00234.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:122d5edca82583365af3ae0b15e3eac84d834ef4d213a72856e60af951cf6d59
3
+ size 7516192930
model-00118-of-00234.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1cbfeb28a92e1054d215bf7cf58ed219325cd754bd5bb429db39b6dc9dcc18f8
3
+ size 493915900
model-00120-of-00234.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fdf2ab7cd8b673b7f50c747eca9ef84ddbbafded6d161a9ea297ddf3728354f6
3
+ size 7516192928
model-00125-of-00234.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dcc48e05c1869d88deb698faa4548d4e1645fd909600d00576141853e3d63bfd
3
+ size 7516192930
model-00138-of-00234.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:acbe06009f641077582fc189ada9aa3949693deb0c681a799d1f459e63a41a95
3
+ size 493915884
model-00153-of-00234.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b87db1546148384ca6b5c9fe2cec3dc4527de63898fcf1b7258efbe434e39932
3
+ size 7516192930
model-00156-of-00234.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:779757616e6d84856fe011ed15d26367de16a4613047a833bb05274750505440
3
+ size 7516192928
model-00158-of-00234.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc079fec0047499e41703f2fe0c4ac5504e9febda60e4e3b0d0709854eeb353b
3
+ size 493915890
model-00159-of-00234.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24da5cfe50e1bde58a0f4b42af1f0bc55d9b9e6320e9d37a62488742ad9ab5ac
3
+ size 7516192930
model-00161-of-00234.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac71fa7cffcca27e3e973e22cef470c3139c9a0ab43b0e105339b8d55041b49f
3
+ size 7516192930
model-00164-of-00234.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed68777cac5ea29066a0180a21c1acbfd299799e09e876ea773fd3514beebd0e
3
+ size 7516192928
model-00173-of-00234.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3024fdf14a819f5c2c2c4ddacd2a673360ad0921c6774bd7cd2464836a8abcb7
3
+ size 7516192930
model-00180-of-00234.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:221a556ec788d32b1512c49d8667e737c3645419c8a5c722c7275a70c7728bfd
3
+ size 7516192928
model-00192-of-00234.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:817820c10566dd127122d15dae3a2cab35fa4e551b01b26404d9e3fe549b7eb3
3
+ size 7516192928
model-00197-of-00234.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f052a4d67dc91def65ca10cced2ac2a62e16fad2d59c3f22acfe46a5b92ea9bd
3
+ size 7516192930
model-00198-of-00234.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1df977a7fb50cc220922d19621a4e58e00ef9e3beb972c201b93aad5fb34e5ac
3
+ size 493915882
model-00200-of-00234.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a57d3ef79b897802841169516c0566e0b9dc7a1b56c3a99c58e089a2be22ad17
3
+ size 7516192928
model-00205-of-00234.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd7d019cf9009dc3b07b593779a50e1e848d00ee6d085e3d95718a51756cdde3
3
+ size 7516192930
model-00218-of-00234.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f21393f3a687cb5e1ab2c5e64d734d5a7d9afad3007655e61a2eab2dc3c5a976
3
+ size 493915900
model-00223-of-00234.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62dc670ea2aee988b479fc814299d6410581b1a0a19ca1fd7f29f5767a3d6847
3
+ size 7516192930
model-00225-of-00234.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:daf66d5bd8b40c06cd96746d70d34b8a3bb5c6ec7649d8248f03341b024bc73c
3
+ size 7516192930
model-00232-of-00234.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:937eef1823088b2856a1bcc057b36cb08ef652158c1243054e8e8ffffc5eab6a
3
+ size 7516192928
model-00234-of-00234.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:edb17d036f48901f6c794169934f9f8952706525e3d1af93e0ffc8361c3c35d2
3
+ size 1945153580
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin▁of▁sentence|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|end▁of▁sentence|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|end▁of▁sentence|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff