| { |
| "architectures": [ |
| "GptOssForCausalLM" |
| ], |
| "attention_bias": true, |
| "attention_dropout": 0.0, |
| "bos_token_id": 1, |
| "eos_token_id": 2, |
| "head_dim": 64, |
| "hidden_act": "silu", |
| "hidden_size": 384, |
| "initializer_range": 0.02, |
| "intermediate_size": 512, |
| "layer_types": [ |
| "sliding_attention", |
| "full_attention" |
| ], |
| "max_position_embeddings": 8192, |
| "mlp_bias": false, |
| "model_type": "gpt_oss", |
| "num_attention_heads": 18, |
| "num_experts_per_tok": 4, |
| "num_hidden_layers": 2, |
| "num_key_value_heads": 2, |
| "num_local_experts": 64, |
| "output_router_logits": false, |
| "pad_token_id": 0, |
| "rms_norm_eps": 1e-05, |
| "rope_scaling": null, |
| "rope_theta": 150000.0, |
| "router_aux_loss_coef": 0.9, |
| "sliding_window": 128, |
| "tie_word_embeddings": false, |
| "torch_dtype": "float32", |
| "transformers_version": "4.55.0.dev0", |
| "use_cache": true, |
| "vocab_size": 201088 |
| } |
|
|
