qingy2024 commited on
Commit
5ee3e90
·
verified ·
1 Parent(s): febecdf

(Trained with Unsloth)

Browse files
Files changed (3) hide show
  1. config.json +69 -0
  2. generation_config.json +11 -0
  3. tokenizer_config.json +1 -1
config.json ADDED
@@ -0,0 +1,69 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ ],
42
+ "max_position_embeddings": 131072,
43
+ "model_type": "gpt_oss",
44
+ "num_attention_heads": 64,
45
+ "num_experts_per_tok": 4,
46
+ "num_hidden_layers": 24,
47
+ "num_key_value_heads": 8,
48
+ "num_local_experts": 32,
49
+ "output_router_logits": false,
50
+ "pad_token_id": 199999,
51
+ "rms_norm_eps": 1e-05,
52
+ "rope_scaling": {
53
+ "beta_fast": 32.0,
54
+ "beta_slow": 1.0,
55
+ "factor": 32.0,
56
+ "original_max_position_embeddings": 4096,
57
+ "rope_type": "yarn",
58
+ "truncate": false
59
+ },
60
+ "rope_theta": 150000,
61
+ "router_aux_loss_coef": 0.9,
62
+ "sliding_window": 128,
63
+ "swiglu_limit": 7.0,
64
+ "tie_word_embeddings": false,
65
+ "transformers_version": "4.56.0",
66
+ "unsloth_version": "2025.9.4",
67
+ "use_cache": true,
68
+ "vocab_size": 201088
69
+ }
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": 199999,
10
+ "transformers_version": "4.56.0"
11
+ }
tokenizer_config.json CHANGED
@@ -179,6 +179,6 @@
179
  ],
180
  "model_max_length": 1000000000000000019884624838656,
181
  "pad_token": "<|endoftext|>",
182
- "padding_side": "right",
183
  "tokenizer_class": "PreTrainedTokenizerFast"
184
  }
 
179
  ],
180
  "model_max_length": 1000000000000000019884624838656,
181
  "pad_token": "<|endoftext|>",
182
+ "padding_side": "left",
183
  "tokenizer_class": "PreTrainedTokenizerFast"
184
  }