| { | |
| "_sliding_window_pattern": 4, | |
| "architectures": [ | |
| "EagleCohereForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 2, | |
| "dtype": "bfloat16", | |
| "eos_token_id": 255001, | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 2048, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 768, | |
| "layer_norm_eps": 1e-05, | |
| "layer_switch": 4, | |
| "layer_types": [ | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention" | |
| ], | |
| "logit_scale": 1.0, | |
| "max_position_embeddings": 5000000, | |
| "model_type": "cohere2", | |
| "norm_type": "rms_norm", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 3, | |
| "num_key_value_heads": 4, | |
| "order_of_interleaved_layers": "local_attn_first", | |
| "pad_token_id": 0, | |
| "position_embedding_type": "rope_gptj", | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": null, | |
| "rope_style": "interleave", | |
| "rope_theta": 50000, | |
| "rotary_pct": 1.0, | |
| "sliding_window": 4096, | |
| "transformer_block_type": "parallel", | |
| "transformers_version": "4.56.2.4", | |
| "use_cache": true, | |
| "use_embedding_sharing": false, | |
| "use_gated_activation": true, | |
| "use_parallel_embedding": false, | |
| "use_qk_norm": false, | |
| "vocab_size": 262144 | |
| } | |