| { |
| "architectures": [ |
| "Olmoe2ForCausalLM" |
| ], |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "clip_qkv": null, |
| "eos_token_id": 100257, |
| "hidden_act": "silu", |
| "hidden_size": 4096, |
| "initializer_range": 0.02, |
| "intermediate_size": 11008, |
| "max_position_embeddings": 4096, |
| "model_type": "olmoe2", |
| "norm_topk_prob": false, |
| "num_attention_heads": 32, |
| "num_experts": 2, |
| "num_experts_per_tok": 2, |
| "num_hidden_layers": 32, |
| "num_key_value_heads": 32, |
| "output_router_logits": false, |
| "pad_token_id": 100277, |
| "rms_norm_eps": 1e-06, |
| "rope_scaling": null, |
| "rope_theta": 500000, |
| "router_aux_loss_coef": 0.01, |
| "tie_word_embeddings": false, |
| "torch_dtype": "float32", |
| "transformers_version": "4.50.0.dev0", |
| "use_cache": true, |
| "vocab_size": 100352 |
| } |
|
|