Hugging Face's logo

stepnoy
/
gpt-oss-120b-NVFP4

Safetensors
gpt_oss
modelopt
Model card Files
xet
 Community
stepnoy commited on
Commit
e01638f
·
verified ·
1 Parent(s): a25e619

Add files using upload-large-folder tool

Browse files
Files changed (11) hide show
  1. config.json +84 -0
  2. generation_config.json +10 -0
  3. model-00001-of-00073.safetensors +3 -0
  4. model-00002-of-00073.safetensors +3 -0
  5. model-00003-of-00073.safetensors +3 -0
  6. model-00004-of-00073.safetensors +3 -0
  7. model-00005-of-00073.safetensors +3 -0
  8. model-00006-of-00073.safetensors +3 -0
  9. model-00007-of-00073.safetensors +3 -0
  10. model-00008-of-00073.safetensors +3 -0
  11. quant_amax.pth +3 -0
config.json ADDED
@@ -0,0 +1,84 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "GptOssForCausalLM"
4
+ ],
5
+ "attention_bias": true,
6
+ "attention_dropout": 0.0,
7
+ "dtype": "bfloat16",
8
+ "eos_token_id": 200002,
9
+ "experts_per_token": 4,
10
+ "head_dim": 64,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 2880,
13
+ "initial_context_length": 4096,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 2880,
16
+ "layer_types": [
17
+ "sliding_attention",
18
+ "full_attention",
19
+ "sliding_attention",
20
+ "full_attention",
21
+ "sliding_attention",
22
+ "full_attention",
23
+ "sliding_attention",
24
+ "full_attention",
25
+ "sliding_attention",
26
+ "full_attention",
27
+ "sliding_attention",
28
+ "full_attention",
29
+ "sliding_attention",
30
+ "full_attention",
31
+ "sliding_attention",
32
+ "full_attention",
33
+ "sliding_attention",
34
+ "full_attention",
35
+ "sliding_attention",
36
+ "full_attention",
37
+ "sliding_attention",
38
+ "full_attention",
39
+ "sliding_attention",
40
+ "full_attention",
41
+ "sliding_attention",
42
+ "full_attention",
43
+ "sliding_attention",
44
+ "full_attention",
45
+ "sliding_attention",
46
+ "full_attention",
47
+ "sliding_attention",
48
+ "full_attention",
49
+ "sliding_attention",
50
+ "full_attention",
51
+ "sliding_attention",
52
+ "full_attention"
53
+ ],
54
+ "max_position_embeddings": 131072,
55
+ "model_type": "gpt_oss",
56
+ "num_attention_heads": 64,
57
+ "num_experts_per_tok": 4,
58
+ "num_hidden_layers": 36,
59
+ "num_key_value_heads": 8,
60
+ "num_local_experts": 128,
61
+ "output_router_logits": false,
62
+ "pad_token_id": 199999,
63
+ "rms_norm_eps": 1e-05,
64
+ "rope_scaling": {
65
+ "beta_fast": 32.0,
66
+ "beta_slow": 1.0,
67
+ "factor": 32.0,
68
+ "original_max_position_embeddings": 4096,
69
+ "rope_type": "yarn",
70
+ "truncate": false
71
+ },
72
+ "rope_theta": 150000,
73
+ "router_aux_loss_coef": 0.9,
74
+ "sliding_window": 128,
75
+ "swiglu_limit": 7.0,
76
+ "tie_word_embeddings": false,
77
+ "transformers_version": "4.57.3",
78
+ "use_cache": false,
79
+ "vocab_size": 201088,
80
+ "quantization_config": {
81
+ "quant_method": "modelopt",
82
+ "kv_cache_quant_method": "nvfp4"
83
+ }
84
+ }
generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 199998,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 200002,
6
+ 199999
7
+ ],
8
+ "pad_token_id": 199999,
9
+ "transformers_version": "4.57.3"
10
+ }
model-00001-of-00073.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46c07681c83d1ebacaa32eaff09c8bed14c8f085bdafb80641351796f8822234
3
+ size 1212106064
model-00002-of-00073.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66f8d893fc4fbd27a07d2454114d5cc84821fa18d7575b625aa184b31ef0a572
3
+ size 4248207640
model-00003-of-00073.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a85e2a931591fd07a4ee3dd86e5b2c477246f396968545c12524ba1627fa0e1f
3
+ size 2177955264
model-00004-of-00073.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dda6a71a050e68fe98ddfc12c0e3e86234b29d2ee5a6ba9083cabcc9e173563f
3
+ size 4248207640
model-00005-of-00073.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42b1d73ff93f585de5b264ee03e8236b0df1252addc7a44f045265a2fc467645
3
+ size 2177955264
model-00006-of-00073.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01b81738668bce7b58ec8cef5e8c25b1e2b7afafcd1af7913da2788838263bd0
3
+ size 4248207640
model-00007-of-00073.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:672176a0da47dac45163a19af354b090286e56744af95db71521245e29840511
3
+ size 2177955264
model-00008-of-00073.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b43d83c403e92882c79cdfbeb8b80e30d0d7fe58329ab8d3a8a13db0c1d7c5d
3
+ size 4248207640
quant_amax.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f575c2b35a60b25d84f7ff9ecd3bc583497087b8e3c3e32b5e4ccf797be35e01
3
+ size 137537