Ba2han commited on
Commit
9d1b2eb
·
verified ·
1 Parent(s): 9c27ee3

(Trained with Unsloth)

Browse files
config.json ADDED
@@ -0,0 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "GptOssForCausalLM"
4
+ ],
5
+ "attention_bias": true,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 199998,
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": 200017,
52
+ "rms_norm_eps": 1e-05,
53
+ "rope_scaling": {
54
+ "beta_fast": 32.0,
55
+ "beta_slow": 1.0,
56
+ "factor": 32.0,
57
+ "original_max_position_embeddings": 4096,
58
+ "rope_type": "yarn",
59
+ "truncate": false
60
+ },
61
+ "rope_theta": 150000,
62
+ "router_aux_loss_coef": 0.9,
63
+ "sliding_window": 128,
64
+ "swiglu_limit": 7.0,
65
+ "tie_word_embeddings": false,
66
+ "transformers_version": "4.56.0",
67
+ "unsloth_version": "2025.8.10",
68
+ "use_cache": true,
69
+ "vocab_size": 201088
70
+ }
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
+ ],
8
+ "max_length": 131072,
9
+ "pad_token_id": 200017,
10
+ "transformers_version": "4.56.0"
11
+ }
model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ae974fc561b460d34aa492fc74cb66ea5fe1e9d194a71217b8da1b17c560b93
3
+ size 5000192679
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17f46e1ce04d9f82d56ac4b880afa509f28a3c36b5b8a3ce07f8585f85f31af1
3
+ size 4996872197
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:684dce2046b5ec34a6d3092955644a38cefffad6a2b143d01a6e9f9ed1f54ff4
3
+ size 2656129928
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff