ryandeng commited on
Commit
feb1427
·
verified ·
1 Parent(s): a26404f

Upload folder using huggingface_hub

Browse files
Files changed (3) hide show
  1. config.json +78 -0
  2. generation_config.json +11 -0
  3. model.safetensors +3 -0
config.json ADDED
@@ -0,0 +1,78 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "GptOssForCausalLM"
4
+ ],
5
+ "attention_bias": true,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": null,
8
+ "dtype": "bfloat16",
9
+ "eos_token_id": 200002,
10
+ "experts_per_token": 4,
11
+ "head_dim": 64,
12
+ "hidden_act": "silu",
13
+ "hidden_size": 2880,
14
+ "initial_context_length": 4096,
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 2880,
17
+ "layer_types": [
18
+ "sliding_attention",
19
+ "full_attention",
20
+ "sliding_attention",
21
+ "full_attention",
22
+ "sliding_attention",
23
+ "full_attention",
24
+ "sliding_attention",
25
+ "full_attention",
26
+ "sliding_attention",
27
+ "full_attention",
28
+ "sliding_attention",
29
+ "full_attention",
30
+ "sliding_attention",
31
+ "full_attention",
32
+ "sliding_attention",
33
+ "full_attention",
34
+ "sliding_attention",
35
+ "full_attention",
36
+ "sliding_attention",
37
+ "full_attention",
38
+ "sliding_attention",
39
+ "full_attention",
40
+ "sliding_attention",
41
+ "full_attention"
42
+ ],
43
+ "max_position_embeddings": 131072,
44
+ "model_type": "gpt_oss",
45
+ "num_attention_heads": 64,
46
+ "num_experts_per_tok": 4,
47
+ "num_hidden_layers": 24,
48
+ "num_key_value_heads": 8,
49
+ "num_local_experts": 32,
50
+ "output_router_logits": false,
51
+ "pad_token_id": 199999,
52
+ "quantization_config": {
53
+ "modules_to_not_convert": [
54
+ "model.layers.*.self_attn",
55
+ "model.layers.*.mlp.router",
56
+ "model.embed_tokens",
57
+ "lm_head"
58
+ ],
59
+ "quant_method": "mxfp4"
60
+ },
61
+ "rms_norm_eps": 1e-05,
62
+ "rope_parameters": {
63
+ "beta_fast": 32.0,
64
+ "beta_slow": 1.0,
65
+ "factor": 32.0,
66
+ "original_max_position_embeddings": 4096,
67
+ "rope_theta": 150000,
68
+ "rope_type": "yarn",
69
+ "truncate": false
70
+ },
71
+ "router_aux_loss_coef": 0.9,
72
+ "sliding_window": 128,
73
+ "swiglu_limit": 7.0,
74
+ "tie_word_embeddings": false,
75
+ "transformers_version": "5.3.0",
76
+ "use_cache": true,
77
+ "vocab_size": 201088
78
+ }
generation_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 199998,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 200002,
6
+ 199999,
7
+ 200012
8
+ ],
9
+ "pad_token_id": 199999,
10
+ "transformers_version": "5.3.0"
11
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0ee8b764df1d96d5093db89699c411c76f55c793015c2147652b0d83181a754
3
+ size 13774588584