flyfishxu commited on
Commit
7054501
·
1 Parent(s): fa79459

Add files using upload-large-folder tool

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .DS_Store +0 -0
  2. README.md +33 -0
  3. config.json +69 -0
  4. model-00001-of-00044.safetensors +3 -0
  5. model-00002-of-00044.safetensors +3 -0
  6. model-00003-of-00044.safetensors +3 -0
  7. model-00004-of-00044.safetensors +3 -0
  8. model-00005-of-00044.safetensors +3 -0
  9. model-00006-of-00044.safetensors +3 -0
  10. model-00007-of-00044.safetensors +3 -0
  11. model-00008-of-00044.safetensors +3 -0
  12. model-00009-of-00044.safetensors +3 -0
  13. model-00010-of-00044.safetensors +3 -0
  14. model-00011-of-00044.safetensors +3 -0
  15. model-00012-of-00044.safetensors +3 -0
  16. model-00013-of-00044.safetensors +3 -0
  17. model-00014-of-00044.safetensors +3 -0
  18. model-00015-of-00044.safetensors +3 -0
  19. model-00016-of-00044.safetensors +3 -0
  20. model-00017-of-00044.safetensors +3 -0
  21. model-00018-of-00044.safetensors +3 -0
  22. model-00019-of-00044.safetensors +3 -0
  23. model-00020-of-00044.safetensors +3 -0
  24. model-00021-of-00044.safetensors +3 -0
  25. model-00022-of-00044.safetensors +3 -0
  26. model-00023-of-00044.safetensors +3 -0
  27. model-00024-of-00044.safetensors +3 -0
  28. model-00025-of-00044.safetensors +3 -0
  29. model-00026-of-00044.safetensors +3 -0
  30. model-00027-of-00044.safetensors +3 -0
  31. model-00028-of-00044.safetensors +3 -0
  32. model-00029-of-00044.safetensors +3 -0
  33. model-00030-of-00044.safetensors +3 -0
  34. model-00031-of-00044.safetensors +3 -0
  35. model-00032-of-00044.safetensors +3 -0
  36. model-00033-of-00044.safetensors +3 -0
  37. model-00034-of-00044.safetensors +3 -0
  38. model-00035-of-00044.safetensors +3 -0
  39. model-00036-of-00044.safetensors +3 -0
  40. model-00037-of-00044.safetensors +3 -0
  41. model-00038-of-00044.safetensors +3 -0
  42. model-00039-of-00044.safetensors +3 -0
  43. model-00040-of-00044.safetensors +3 -0
  44. model-00041-of-00044.safetensors +3 -0
  45. model-00042-of-00044.safetensors +3 -0
  46. model-00043-of-00044.safetensors +3 -0
  47. model-00044-of-00044.safetensors +3 -0
  48. model.safetensors.index.json +0 -0
  49. special_tokens_map.json +23 -0
  50. tokenizer.json +0 -0
.DS_Store ADDED
Binary file (6.15 kB). View file
 
README.md ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: deepseek-ai/DeepSeek-R1
3
+ tags:
4
+ - mlx
5
+ ---
6
+
7
+ # mlx-community/DeepSeek-R1-2bit
8
+
9
+ The Model [mlx-community/DeepSeek-R1-2bit](https://huggingface.co/mlx-community/DeepSeek-R1-2bit) was
10
+ converted to MLX format from [deepseek-ai/DeepSeek-R1](https://huggingface.co/deepseek-ai/DeepSeek-R1)
11
+ using mlx-lm version **0.21.3**.
12
+
13
+ ## Use with mlx
14
+
15
+ ```bash
16
+ pip install mlx-lm
17
+ ```
18
+
19
+ ```python
20
+ from mlx_lm import load, generate
21
+
22
+ model, tokenizer = load("mlx-community/DeepSeek-R1-2bit")
23
+
24
+ prompt = "hello"
25
+
26
+ if tokenizer.chat_template is not None:
27
+ messages = [{"role": "user", "content": prompt}]
28
+ prompt = tokenizer.apply_chat_template(
29
+ messages, add_generation_prompt=True
30
+ )
31
+
32
+ response = generate(model, tokenizer, prompt=prompt, verbose=True)
33
+ ```
config.json ADDED
@@ -0,0 +1,69 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "DeepseekV3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "auto_map": {
8
+ "AutoConfig": "configuration_deepseek.DeepseekV3Config",
9
+ "AutoModel": "modeling_deepseek.DeepseekV3Model",
10
+ "AutoModelForCausalLM": "modeling_deepseek.DeepseekV3ForCausalLM"
11
+ },
12
+ "aux_loss_alpha": 0.001,
13
+ "bos_token_id": 0,
14
+ "eos_token_id": 1,
15
+ "ep_size": 1,
16
+ "first_k_dense_replace": 3,
17
+ "hidden_act": "silu",
18
+ "hidden_size": 7168,
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 18432,
21
+ "kv_lora_rank": 512,
22
+ "max_position_embeddings": 163840,
23
+ "model_type": "deepseek_v3",
24
+ "moe_intermediate_size": 2048,
25
+ "moe_layer_freq": 1,
26
+ "n_group": 8,
27
+ "n_routed_experts": 256,
28
+ "n_shared_experts": 1,
29
+ "norm_topk_prob": true,
30
+ "num_attention_heads": 128,
31
+ "num_experts_per_tok": 8,
32
+ "num_hidden_layers": 61,
33
+ "num_key_value_heads": 128,
34
+ "num_nextn_predict_layers": 1,
35
+ "pretraining_tp": 1,
36
+ "q_lora_rank": 1536,
37
+ "qk_nope_head_dim": 128,
38
+ "qk_rope_head_dim": 64,
39
+ "quantization": {
40
+ "group_size": 64,
41
+ "bits": 2
42
+ },
43
+ "quantization_config": {
44
+ "group_size": 64,
45
+ "bits": 2
46
+ },
47
+ "rms_norm_eps": 1e-06,
48
+ "rope_scaling": {
49
+ "beta_fast": 32,
50
+ "beta_slow": 1,
51
+ "factor": 40,
52
+ "mscale": 1.0,
53
+ "mscale_all_dim": 1.0,
54
+ "original_max_position_embeddings": 4096,
55
+ "type": "yarn"
56
+ },
57
+ "rope_theta": 10000,
58
+ "routed_scaling_factor": 2.5,
59
+ "scoring_func": "sigmoid",
60
+ "seq_aux": true,
61
+ "tie_word_embeddings": false,
62
+ "topk_group": 4,
63
+ "topk_method": "noaux_tc",
64
+ "torch_dtype": "bfloat16",
65
+ "transformers_version": "4.46.3",
66
+ "use_cache": true,
67
+ "v_head_dim": 128,
68
+ "vocab_size": 129280
69
+ }
model-00001-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0848a3d937d4ae74c7152bb6e991865f24910adea92987ef6a3b1f4c5229dd2
3
+ size 4494328711
model-00002-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4bd70edd92c833054e9f0402214ada7a0a5500d4f7d3a070b3022c4d111ef93c
3
+ size 4773561886
model-00003-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36ab6dc634f8ce9a26a26d95434561b548865c95c7b19c1237cce54f5dc70c11
3
+ size 4773561880
model-00004-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd298f131917c59d6de701554161a3f7ac0312e279e609efb8f829936e803b93
3
+ size 4849501660
model-00005-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38a1178dce9338721c7e861d541a80822f3d919e9901121e6db6009777e69a04
3
+ size 4773561816
model-00006-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f55847119e83ede8574dd9424685a121e7f24da4465fc0dba74271d2ffb01125
3
+ size 4773561903
model-00007-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9bea77aa9d32dfb1ea30dd589f3d9801d6a3b6719909a6a4726cf2b318045253
3
+ size 4849501744
model-00008-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:786bad65ab0dc5d82e792dba1bbed8e23e332634e6e7590791af498543d66432
3
+ size 4773561900
model-00009-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2276d5818d3612b9d8f2b37396c435ef300e7f7d2d51a710c59f84a74ced6f71
3
+ size 4773561882
model-00010-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab7d396802cacf524e916f156bb8c6077513c2deeda541393b83de9f4f67874a
3
+ size 4849501716
model-00011-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:293e266a9b8f60f5a18f33a0f820ffaf2e73cf3bc0636ce65e83395775dfa391
3
+ size 4773561914
model-00012-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac7a373fe436f955fb67574a515f6c6bdaf259452ddcdfc75bdd13f9ba015d04
3
+ size 4773561894
model-00013-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c47e5e7dd20b02d0336429fe71fb6f0ccbccde8c2ff294a631a4346df7b75d4
3
+ size 4849501712
model-00014-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e761cf3c539a75f8e8a8b7383e1623c9c64d8e8125f6375f2df8e801c5cef52
3
+ size 4773561868
model-00015-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3776923206c2708feb188ea13ddfb3ed64bf9b8ffa75077047ddb8d67c54cd69
3
+ size 4773561922
model-00016-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c148258511e0f8c8e521d0bedf810f23bad6b3739498a3beb275d1e60c2c989
3
+ size 4849501734
model-00017-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f40c50ee84f97eb9194abe9df391a8f138b04f2c0105eac4f2aed773dcac58c3
3
+ size 4773561886
model-00018-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6aa1e369672c387ab9a29f31ce6f15b1ecfa15ab23ea5d2ed10ea86d5c3e6592
3
+ size 4773561920
model-00019-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f0037eb4e95d7c5365442a628982b63265a62c73f96140862d2c587273c7b9b
3
+ size 4849501724
model-00020-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fdf7b101aacc75536740050a56eb1f457111af70e42d108b357e6bec5f2048c5
3
+ size 4773561896
model-00021-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ac793b26fea990797caba82f8d3657b08a369b50483f111e515b906b7e448e6
3
+ size 4773561918
model-00022-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0fec0ab2f672eec06af4b9a2d7c8ed247b8f738c19d5ba8dbbee9397fb15e5b5
3
+ size 4849501720
model-00023-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75ff75ab082ed12e3521b473e89a1ac6924ba81e98a7dd3216d739f367308c95
3
+ size 4773561868
model-00024-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8628cd35446b3be264d108375006ccf4ef14bbce7220bacb3f8559a95f64ec51
3
+ size 4773561916
model-00025-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c54f76ad0b2cbd36abe425ca902398f7491de8a4ce37d2a3cec5b856dee6167d
3
+ size 4849501764
model-00026-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd626cdd14437de46fe031a7ccac8bf1b535ca7c67b0c9d20bf58edab5954f6c
3
+ size 4773561928
model-00027-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b603a846a7d1c7792320b3b582a94a9025690d9714ec35ba2bd1d202ad8de8be
3
+ size 4773561922
model-00028-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8d55d4bf3bbee956fbb83a526104937608e6d6d9b86025d7767fca4986cdc84
3
+ size 4849501748
model-00029-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04bc4ff2df3c87b48a59fa58b805a00c0970202ecbf481bc0478e0fbdc7f7306
3
+ size 4773561928
model-00030-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa894e25d30544efcdd8b57d6857e143f8be4503ace04092a5db7326ef6f4827
3
+ size 4773561922
model-00031-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d85e076c32b4d72d54f52e61f05b0b45c749b04f14295b11b5bc8a5e5a915400
3
+ size 4849501722
model-00032-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f23b83e8344b9fa500663974e94509ee02cad46d6389d22a6c54dffb8c50a983
3
+ size 4773561926
model-00033-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e5052bccef619f89b0ab51b69d803557619d649a00c0976848706217063cba8
3
+ size 4773561920
model-00034-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:adaced73a3e90bacaa0fc96da17a1bef9d14aac4935593e198a5263c7660ead3
3
+ size 4849501718
model-00035-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:471844572802e61b2cd10c67c35bcb514d78979967c08ec7c641ca0242c21140
3
+ size 4773561928
model-00036-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32076165303b8f8ac52f02efe74d4f21600751ace43ba4aafcc85bf3eb384ae4
3
+ size 4773561922
model-00037-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9bc5971644b52c1ca27ac582673f2a388256e043e78066177377605aeebf26e
3
+ size 4849501748
model-00038-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18517c4e43837c3f53427ed9c79407a21fe219f79f6fd2db24fc0128de268d39
3
+ size 4773561910
model-00039-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5dbf8cdb319f7431d9ef4c71e6a1da6996948a652b7797ee9cf482ecdf72cd2a
3
+ size 4773561922
model-00040-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86ff659147ce49052e0a67d3b9ccdfff82447760059f69f77b9035ed5e6588f0
3
+ size 4849501712
model-00041-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80c351b3e610cc9c600996178be31da249440736e26beb9a597ce6bb53578749
3
+ size 4773561928
model-00042-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6bf7d7abae36f5ee9a26b25a5e6ad1cf5ce1df01fff97c916cfbd2f07d86be1
3
+ size 4773561922
model-00043-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e9499184b28e6178f4b2bf9b24bbfbf88a1b88833072758abf747d138f79fe7
3
+ size 4849501720
model-00044-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe09f21828855768c63a711d1a7944fe0e615d26278719bfefce100a74a4b2ed
3
+ size 3830281794
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