Hugging Face's logo

unsloth
/
DeepSeek-V4-Pro

Text Generation
Transformers
Safetensors
deepseek_v4
8-bit precision
fp8
Model card Files
xet
 Community
danielhanchen commited on
Commit
9caaca3
·
verified ·
1 Parent(s): 249c19e

Mirror worker 4

Browse files
Files changed (10) hide show
  1. config.json +66 -0
  2. model-00004-of-00064.safetensors +3 -0
  3. model-00012-of-00064.safetensors +3 -0
  4. model-00020-of-00064.safetensors +3 -0
  5. model-00028-of-00064.safetensors +3 -0
  6. model-00036-of-00064.safetensors +3 -0
  7. model-00044-of-00064.safetensors +3 -0
  8. model-00052-of-00064.safetensors +3 -0
  9. model-00060-of-00064.safetensors +3 -0
  10. tokenizer_config.json +34 -0
config.json ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "DeepseekV4ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 0,
8
+ "eos_token_id": 1,
9
+ "hc_eps": 1e-06,
10
+ "hc_mult": 4,
11
+ "hc_sinkhorn_iters": 20,
12
+ "head_dim": 512,
13
+ "hidden_act": "silu",
14
+ "hidden_size": 7168,
15
+ "index_head_dim": 128,
16
+ "index_n_heads": 64,
17
+ "index_topk": 1024,
18
+ "initializer_range": 0.02,
19
+ "max_position_embeddings": 1048576,
20
+ "model_type": "deepseek_v4",
21
+ "moe_intermediate_size": 3072,
22
+ "n_routed_experts": 384,
23
+ "n_shared_experts": 1,
24
+ "norm_topk_prob": true,
25
+ "num_attention_heads": 128,
26
+ "num_experts_per_tok": 6,
27
+ "num_hidden_layers": 61,
28
+ "num_hash_layers": 3,
29
+ "num_key_value_heads": 1,
30
+ "num_nextn_predict_layers": 1,
31
+ "o_groups": 16,
32
+ "o_lora_rank": 1024,
33
+ "q_lora_rank": 1536,
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": 16,
50
+ "original_max_position_embeddings": 65536,
51
+ "type": "yarn"
52
+ },
53
+ "rope_theta": 10000,
54
+ "routed_scaling_factor": 2.5,
55
+ "scoring_func": "sqrtsoftplus",
56
+ "sliding_window": 128,
57
+ "swiglu_limit": 10.0,
58
+ "tie_word_embeddings": false,
59
+ "topk_method": "noaux_tc",
60
+ "torch_dtype": "bfloat16",
61
+ "transformers_version": "4.57.1",
62
+ "use_cache": true,
63
+ "vocab_size": 129280,
64
+ "compress_rope_theta": 160000,
65
+ "compress_ratios": [128, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 0]
66
+ }
model-00004-of-00064.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff448399c432294cf2c32fef0f2d0c45198dba478ccbb26fdbe3d9470a9e3401
3
+ size 13910006752
model-00012-of-00064.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aeec3cfca08c45c7325e36b3c936da1d6e1fe4b2293fa5ae9183d907595c912c
3
+ size 13903805136
model-00020-of-00064.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b42f5ba06ac82c53ddff70ac98b96a568f91455d5fde37615535d89c4050c982
3
+ size 13903805136
model-00028-of-00064.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:626dff2e694137259aa316f944c045eb584d035ddc13e5bc70c451653af4801a
3
+ size 13903805136
model-00036-of-00064.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2eccd1b26083d32bec90c735824ce5a29976b661cb9acba93cf9d54eb39adda
3
+ size 13903805136
model-00044-of-00064.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:033fb548ce2d348ba5d4832077b3ca23e4d3a6a0648ab54e6e06a94ea243b346
3
+ size 13903805136
model-00052-of-00064.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:590d0b044b0215aec29a736ffce2d733c3c47287025599d8117de36a6331c97a
3
+ size 13903805136
model-00060-of-00064.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf96a777bcbaca05d9b04b71cea6d0d431352e1415ee8d2876c099c1861260a3
3
+ size 13903805136
tokenizer_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_eos_token": false,
4
+ "bos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "<｜begin▁of▁sentence｜>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "clean_up_tokenization_spaces": false,
13
+ "eos_token": {
14
+ "__type": "AddedToken",
15
+ "content": "<｜end▁of▁sentence｜>",
16
+ "lstrip": false,
17
+ "normalized": true,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "legacy": true,
22
+ "model_max_length": 1048576,
23
+ "pad_token": {
24
+ "__type": "AddedToken",
25
+ "content": "<｜end▁of▁sentence｜>",
26
+ "lstrip": false,
27
+ "normalized": true,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ },
31
+ "sp_model_kwargs": {},
32
+ "unk_token": null,
33
+ "tokenizer_class": "PreTrainedTokenizerFast"
34
+ }