| { |
| "architectures": [ |
| "GptOssForCausalLM" |
| ], |
| "attention_bias": true, |
| "attention_dropout": 0.0, |
| "dtype": "bfloat16", |
| "head_dim": 64, |
| "hidden_act": "silu", |
| "hidden_size": 8, |
| "initializer_range": 0.02, |
| "intermediate_size": 32, |
| "layer_types": [ |
| "sliding_attention", |
| "full_attention" |
| ], |
| "max_position_embeddings": 131072, |
| "model_type": "gpt_oss", |
| "num_attention_heads": 4, |
| "num_experts": 4, |
| "num_experts_per_tok": 2, |
| "num_hidden_layers": 2, |
| "num_key_value_heads": 2, |
| "num_local_experts": 128, |
| "output_router_logits": false, |
| "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": 150000.0, |
| "router_aux_loss_coef": 0.9, |
| "sliding_window": 128, |
| "tie_word_embeddings": false, |
| "transformers_version": "4.57.3", |
| "use_cache": true, |
| "vocab_size": 200019 |
| } |
|
|
