| { |
| "architectures": [ |
| "OlmoeForCausalLM" |
| ], |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "clip_qkv": null, |
| "eos_token_id": 151643, |
| "hidden_act": "silu", |
| "hidden_size": 1536, |
| "initializer_range": 0.02, |
| "intermediate_size": 1280, |
| "max_position_embeddings": 2048, |
| "model_type": "olmoe", |
| "norm_topk_prob": false, |
| "num_attention_heads": 24, |
| "num_experts": 16, |
| "num_experts_per_tok": 2, |
| "num_hidden_layers": 16, |
| "num_key_value_heads": 24, |
| "output_router_logits": false, |
| "pad_token_id": 151643, |
| "rms_norm_eps": 1e-05, |
| "rope_scaling": null, |
| "rope_theta": 32000, |
| "router_aux_loss_coef": 0.01, |
| "tie_word_embeddings": false, |
| "torch_dtype": "bfloat16", |
| "transformers_version": "4.47.1", |
| "use_cache": true, |
| "vocab_size": 151665 |
| } |
|
|