Hugging Face's logo

EasyDeL
/
gpt-oss-120b

Text Generation
JAX
easydel
gpt_oss
CausalLM
blocksparse
conversational
Model card Files
xet
Community
gpt-oss-120b
File size: 4,314 Bytes 
803cff0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
 
{
  "_external_rope_config_kwargs": {},
  "architectures": [
    "GptOssForCausalLM"
  ],
  "attention_bias": true,
  "attention_dropout": 0.0,
  "attn_mechanism": "vanilla",
  "backend": null,
  "bits": null,
  "blocksize_b": 1,
  "blocksize_k": 128,
  "blocksize_q": 128,
  "decode_attn_mechanism": null,
  "dtype": "bfloat16",
  "easy_method": "train",
  "eos_token_id": 200002,
  "experts_per_token": 4,
  "fcm_max_ratio": 0.0,
  "fcm_min_ratio": 0.0,
  "flash_attention_backward_pass_impl": "triton",
  "fsdp_is_ep_bound": true,
  "gradient_checkpointing": "",
  "gradient_checkpointing_targets": null,
  "hardware_abstraction": false,
  "head_dim": 64,
  "hidden_act": "silu",
  "hidden_size": 2880,
  "initial_context_length": 4096,
  "initializer_range": 0.02,
  "intermediate_size": 2880,
  "kv_cache_quantization_config": null,
  "kv_cache_sharding_sequence_axis_name": "sp",
  "layer_types": [
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "full_attention"
  ],
  "max_position_embeddings": 131072,
  "mlp_activations_limit": 7.0,
  "model_type": "gpt_oss",
  "moe_force_xla_gmm": false,
  "moe_method": "fused_moe",
  "moe_tiling_size_batch": 4,
  "moe_tiling_size_dim": 128,
  "moe_tiling_size_seqlen": 128,
  "num_attention_heads": 64,
  "num_experts_per_tok": 4,
  "num_hidden_layers": 36,
  "num_key_value_heads": 8,
  "num_local_experts": 128,
  "operation_configs": null,
  "output_router_logits": false,
  "pad_token_id": 199999,
  "pallas_k_block_size": 128,
  "pallas_m_block_size": 128,
  "pallas_n_block_size": 128,
  "partition_axis": {
    "attention_dim_axis": null,
    "attention_kv_dim_axis": null,
    "batch_axis": [
      "fsdp",
      "dp"
    ],
    "bias_head_sequence_axis": null,
    "bias_key_sequence_axis": null,
    "data_parallel_axis": "dp",
    "decode_attention_dim_axis": null,
    "decode_attention_kv_dim_axis": null,
    "decode_batch_axis": [
      "fsdp",
      "dp"
    ],
    "decode_head_axis": "tp",
    "decode_key_sequence_axis": "sp",
    "decode_kv_head_axis": "tp",
    "decode_query_sequence_axis": null,
    "expert_axis": "ep",
    "expert_gate_axis": null,
    "expert_parallel_axis": "ep",
    "fully_sharded_data_parallel_axis": "fsdp",
    "head_axis": "tp",
    "hidden_state_axis": "tp",
    "key_sequence_axis": "sp",
    "kv_head_axis": "tp",
    "mlp_intermediate_axis": "tp",
    "query_sequence_axis": "sp",
    "sequence_axis": "sp",
    "sequence_parallel_axis": "sp",
    "tensor_parallel_axis": "tp",
    "vocab_axis": "tp"
  },
  "platform": null,
  "precompute_masks": true,
  "pretraining_tp": 1,
  "quantization_config": null,
  "rms_norm_eps": 1e-05,
  "rope_scaling": {
    "beta_fast": 32.0,
    "beta_slow": 1.0,
    "factor": 32.0,
    "original_max_position_embeddings": 4096,
    "rope_type": "yarn",
    "truncate": false
  },
  "rope_theta": 150000,
  "router_aux_loss_coef": 0.9,
  "scan_attention_layers": false,
  "scan_mlp_chunk_size": 1024,
  "scan_ring_attention": true,
  "sequence_axis_name": "sp",
  "sharding_axis_dims": [
    1,
    -1,
    1,
    1,
    1
  ],
  "sharding_axis_names": [
    "dp",
    "fsdp",
    "ep",
    "tp",
    "sp"
  ],
  "sharding_dcn_axis_dims": null,
  "sliding_window": 128,
  "sp_is_ep_bound": true,
  "swiglu_limit": 7.0,
  "tie_word_embeddings": false,
  "transformers_version": "4.57.3",
  "use_cache": true,
  "use_expert_tensor_mode": false,
  "use_ring_of_experts": false,
  "use_scan_mlp": false,
  "use_sharded_kv_caching": false,
  "use_sharding_constraint": false,
  "vocab_size": 201088
}