| { |
| "_activation_native": false, |
| "_attention_cast_bf16": false, |
| "_deepep_async_combine": false, |
| "_deepep_buffer_size_gb": 2.0, |
| "_deepep_num_sms": 20, |
| "_ep_dispatch": "alltoall", |
| "_lm_head_fp32": true, |
| "_rmsnorm_mode": "native", |
| "_rope_native": false, |
| "_router_fp32": true, |
| "architectures": [ |
| "Olmo2ForCausalLM" |
| ], |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "bos_token_id": null, |
| "dtype": "float32", |
| "eos_token_id": 100257, |
| "head_dim": 128, |
| "hidden_act": "silu", |
| "hidden_size": 4096, |
| "initializer_range": 0.02, |
| "intermediate_size": 11008, |
| "max_position_embeddings": 4096, |
| "model_type": "olmo2", |
| "num_attention_heads": 32, |
| "num_hidden_layers": 32, |
| "num_key_value_heads": 32, |
| "pad_token_id": 100277, |
| "rms_norm_eps": 1e-06, |
| "rope_parameters": { |
| "rope_theta": 500000, |
| "rope_type": "default" |
| }, |
| "rope_theta": 500000, |
| "tie_word_embeddings": false, |
| "train_router": false, |
| "transformers_version": "5.5.0", |
| "use_cache": true, |
| "use_qk_norm": false, |
| "vocab_size": 100352 |
| } |
|
|