Hugging Face's logo

EpistemeAI
/
gpt-oss-20b-stem-4bit

Text Generation
Transformers
Safetensors
English
gpt_oss
text-generation-inference
unsloth
conversational
Model card Files
xet
 Community
legolasyiu commited on
Commit
cd31fa8
·
verified ·
1 Parent(s): 1c84d01

(Trained with Unsloth)

Browse files
Files changed (1) hide show
  1. config.json +67 -105
config.json CHANGED
@@ -1,107 +1,69 @@
1
  {
2
- "architectures": [
3
- "GptOssForCausalLM"
4
- ],
5
- "attention_bias": true,
6
- "attention_dropout": 0.0,
7
- "eos_token_id": 200002,
8
- "experts_per_token": 4,
9
- "head_dim": 64,
10
- "hidden_act": "silu",
11
- "hidden_size": 2880,
12
- "initial_context_length": 4096,
13
- "initializer_range": 0.02,
14
- "intermediate_size": 2880,
15
- "layer_types": [
16
- "sliding_attention",
17
- "full_attention",
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
- ],
41
- "max_position_embeddings": 131072,
42
- "model_type": "gpt_oss",
43
- "num_attention_heads": 64,
44
- "num_experts_per_tok": 4,
45
- "num_hidden_layers": 24,
46
- "num_key_value_heads": 8,
47
- "num_local_experts": 32,
48
- "output_router_logits": false,
49
- "pad_token_id": 199999,
50
- "quantization_config": {
51
- "bnb_4bit_compute_dtype": "float16",
52
- "bnb_4bit_quant_type": "nf4",
53
- "bnb_4bit_use_double_quant": true,
54
- "llm_int8_enable_fp32_cpu_offload": false,
55
- "llm_int8_has_fp16_weight": false,
56
- "llm_int8_skip_modules": [
57
- "model.layers.0.mlp.router.linear",
58
- "model.layers.1.mlp.router.linear",
59
- "model.layers.2.mlp.router.linear",
60
- "model.layers.3.mlp.router.linear",
61
- "model.layers.4.mlp.router.linear",
62
- "model.layers.5.mlp.router.linear",
63
- "model.layers.6.mlp.router.linear",
64
- "model.layers.7.mlp.router.linear",
65
- "model.layers.8.mlp.router.linear",
66
- "model.layers.9.mlp.router.linear",
67
- "model.layers.10.mlp.router.linear",
68
- "model.layers.11.mlp.router.linear",
69
- "model.layers.12.mlp.router.linear",
70
- "model.layers.13.mlp.router.linear",
71
- "model.layers.14.mlp.router.linear",
72
- "model.layers.15.mlp.router.linear",
73
- "model.layers.16.mlp.router.linear",
74
- "model.layers.17.mlp.router.linear",
75
- "model.layers.18.mlp.router.linear",
76
- "model.layers.19.mlp.router.linear",
77
- "model.layers.20.mlp.router.linear",
78
- "model.layers.21.mlp.router.linear",
79
- "model.layers.22.mlp.router.linear",
80
- "model.layers.23.mlp.router.linear",
81
- "lm_head"
82
  ],
83
- "llm_int8_threshold": 6.0,
84
- "load_in_4bit": true,
85
- "load_in_8bit": false,
86
- "quant_method": "bitsandbytes"
87
- },
88
- "rms_norm_eps": 1e-05,
89
- "rope_scaling": {
90
- "beta_fast": 32.0,
91
- "beta_slow": 1.0,
92
- "factor": 32.0,
93
- "original_max_position_embeddings": 4096,
94
- "rope_type": "yarn",
95
- "truncate": false
96
- },
97
- "rope_theta": 150000,
98
- "router_aux_loss_coef": 0.9,
99
- "sliding_window": 128,
100
- "swiglu_limit": 7.0,
101
- "tie_word_embeddings": false,
102
- "torch_dtype": "float16",
103
- "transformers_version": "4.55.4",
104
- "unsloth_version": "2025.9.5",
105
- "use_cache": true,
106
- "vocab_size": 201088
107
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  {
2
+ "architectures": [
3
+ "GptOssForCausalLM"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4
  ],
5
+ "attention_bias": true,
6
+ "attention_dropout": 0.0,
7
+ "eos_token_id": 200002,
8
+ "experts_per_token": 4,
9
+ "head_dim": 64,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 2880,
12
+ "initial_context_length": 4096,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 2880,
15
+ "layer_types": [
16
+ "sliding_attention",
17
+ "full_attention",
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
+ ],
41
+ "max_position_embeddings": 131072,
42
+ "model_type": "gpt_oss",
43
+ "num_attention_heads": 64,
44
+ "num_experts_per_tok": 4,
45
+ "num_hidden_layers": 24,
46
+ "num_key_value_heads": 8,
47
+ "num_local_experts": 32,
48
+ "output_router_logits": false,
49
+ "pad_token_id": 199999,
50
+ "rms_norm_eps": 1e-05,
51
+ "rope_scaling": {
52
+ "beta_fast": 32.0,
53
+ "beta_slow": 1.0,
54
+ "factor": 32.0,
55
+ "original_max_position_embeddings": 4096,
56
+ "rope_type": "yarn",
57
+ "truncate": false
58
+ },
59
+ "rope_theta": 150000,
60
+ "router_aux_loss_coef": 0.9,
61
+ "sliding_window": 128,
62
+ "swiglu_limit": 7.0,
63
+ "tie_word_embeddings": false,
64
+ "torch_dtype": "float16",
65
+ "transformers_version": "4.55.4",
66
+ "unsloth_version": "2025.9.5",
67
+ "use_cache": true,
68
+ "vocab_size": 201088
69
+ }