MLX
Safetensors
NicoNico commited on
Commit
6489909
·
verified ·
1 Parent(s): 44ba2ed

Add files using upload-large-folder tool

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ model.safetensors.index.json filter=lfs diff=lfs merge=lfs -text
config.json CHANGED
@@ -1,3 +1,71 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:bda3917efe530201d73c2eff5f9f00d7d2635e356e40d113775ee498654f53c2
3
- size 1886
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/home/nianhui.guo/models/deepseek/models--deepseek-ai--DeepSeek-R1/snapshots/a157fa3d494497a54586a333a23df6c2143e7697/",
3
+ "architectures": [
4
+ "DeepseekV3ForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "auto_map": {
9
+ "AutoConfig": "configuration_deepseek.DeepseekV3Config",
10
+ "AutoModel": "modeling_deepseek.DeepseekV3Model",
11
+ "AutoModelForCausalLM": "modeling_deepseek.DeepseekV3ForCausalLM"
12
+ },
13
+ "aux_loss_alpha": 0.001,
14
+ "bos_token_id": 0,
15
+ "eos_token_id": 1,
16
+ "ep_size": 1,
17
+ "first_k_dense_replace": 3,
18
+ "hidden_act": "silu",
19
+ "hidden_size": 7168,
20
+ "initializer_range": 0.02,
21
+ "intermediate_size": 18432,
22
+ "kv_lora_rank": 512,
23
+ "max_position_embeddings": 163840,
24
+ "model_type": "deepseek_v3",
25
+ "moe_intermediate_size": 2048,
26
+ "moe_layer_freq": 1,
27
+ "n_group": 8,
28
+ "n_routed_experts": 256,
29
+ "n_shared_experts": 1,
30
+ "norm_topk_prob": true,
31
+ "num_attention_heads": 128,
32
+ "num_experts_per_tok": 8,
33
+ "num_hidden_layers": 61,
34
+ "num_key_value_heads": 128,
35
+ "num_nextn_predict_layers": 1,
36
+ "pretraining_tp": 1,
37
+ "q_lora_rank": 1536,
38
+ "qk_nope_head_dim": 128,
39
+ "qk_rope_head_dim": 64,
40
+ "quantization_config": {
41
+ "activation_scheme": "dynamic",
42
+ "modules_to_not_convert": null,
43
+ "quant_method": "fp8",
44
+ "weight_block_size": [
45
+ 128,
46
+ 128
47
+ ]
48
+ },
49
+ "rms_norm_eps": 1e-06,
50
+ "rope_scaling": {
51
+ "beta_fast": 32,
52
+ "beta_slow": 1,
53
+ "factor": 40,
54
+ "mscale": 1.0,
55
+ "mscale_all_dim": 1.0,
56
+ "original_max_position_embeddings": 4096,
57
+ "type": "yarn"
58
+ },
59
+ "rope_theta": 10000,
60
+ "routed_scaling_factor": 2.5,
61
+ "scoring_func": "sigmoid",
62
+ "seq_aux": true,
63
+ "tie_word_embeddings": false,
64
+ "topk_group": 4,
65
+ "topk_method": "noaux_tc",
66
+ "torch_dtype": "float32",
67
+ "transformers_version": "4.49.0",
68
+ "use_cache": true,
69
+ "v_head_dim": 128,
70
+ "vocab_size": 129280
71
+ }
generation_config.json CHANGED
@@ -1,3 +1,9 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:2e44d6fe8832f8e5d5720140f885c999289ea3afb15b84f9207afcf9ab63809f
3
- size 171
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "do_sample": true,
5
+ "eos_token_id": 1,
6
+ "temperature": 0.6,
7
+ "top_p": 0.95,
8
+ "transformers_version": "4.49.0"
9
+ }
model-00020-of-00073.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ae090c6e747d7ecc253481703c88fab5d2b41a3fc3c96a9cf7d229d2cf8b6f29
3
- size 4999353280
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90b3befb6b7ef72013c3b723b56e343f64660dc03382e52aaac1b6bbccfcc10f
3
+ size 1961091072
model-00071-of-00073.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:66325fc0ad5db347b2f0d19e0ae5ea013b2afef38a323ae7107f7dd943583811
3
- size 27327769320
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07aed8aae092fec1d6138a74419ef58cac176e8d9dec11eda307b0645c226a6d
3
+ size 4999354008
model-00072-of-00073.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f4315173f0f2ec3dd5ec9b278a189d923e359991f8dee11151831f1b9ec034a
3
+ size 4997778640
model-00073-of-00073.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:177959b0554c6dd4a2705af3435cc623fbc707041f8c3c5953e60184c8dd18a9
3
- size 3706745016
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c0d4941797482da09fdc68792cb5112b4737d1092be1eaa98c6d5e0658e7dfb
3
+ size 4156227192
model.safetensors.index.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:058e1001d832fb021c5cee8840ac4719c9bb1ff3d734aa2636e114021e0269ac
3
- size 19539771
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5aa3dfbc630c05df14e80eb583c148f830ba0614eba2f3f5c3a83c603c785444
3
+ size 20783505
special_tokens_map.json CHANGED
@@ -1,3 +1,23 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:59cda48bbe8bab9d61ffb410e6e3c07b6d98bff73cee7c88ff8b51f95f21ab1c
3
- size 485
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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 CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
The diff for this file is too large to render. See raw diff