{ "_sliding_window_pattern": 4, "architectures": [ "Cohere2ForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 5, "cache_implementation": "hybrid", "dtype": "bfloat16", "eos_token_id": 255001, "head_dim": 128, "hidden_act": "silu", "hidden_size": 12288, "initializer_range": 0.02, "intermediate_size": 36864, "layer_norm_eps": 1e-05, "layer_switch": 4, "layer_types": [ "sliding_attention", "sliding_attention", "sliding_attention", "full_attention", "sliding_attention", "sliding_attention", "sliding_attention", "full_attention", "sliding_attention", "sliding_attention", "sliding_attention", "full_attention", "sliding_attention", "sliding_attention", "sliding_attention", "full_attention", "sliding_attention", "sliding_attention", "sliding_attention", "full_attention", "sliding_attention", "sliding_attention", "sliding_attention", "full_attention", "sliding_attention", "sliding_attention", "sliding_attention", "full_attention", "sliding_attention", "sliding_attention", "sliding_attention", "full_attention", "sliding_attention", "sliding_attention", "sliding_attention", "full_attention", "sliding_attention", "sliding_attention", "sliding_attention", "full_attention", "sliding_attention", "sliding_attention", "sliding_attention", "full_attention", "sliding_attention", "sliding_attention", "sliding_attention", "full_attention", "sliding_attention", "sliding_attention", "sliding_attention", "full_attention", "sliding_attention", "sliding_attention", "sliding_attention", "full_attention", "sliding_attention", "sliding_attention", "sliding_attention", "full_attention", "sliding_attention", "sliding_attention", "sliding_attention", "full_attention" ], "logit_scale": 0.25, "max_position_embeddings": 8192, "model_type": "cohere2", "num_attention_heads": 96, "num_hidden_layers": 64, "num_key_value_heads": 8, "order_of_interleaved_layers": "local_attn_first", "pad_token_id": 0, "position_embedding_type": "rope_gptj", "quantization_config": { "autoround_version": "0.8.0.dev", "bits": 4, "damp_percent": 0.01, "data_type": "int", "desc_act": false, "group_size": 128, "provider": "auto-round", "quant_method": "gptq", "sym": true, "true_sequential": false }, "rope_scaling": null, "rope_theta": 50000, "rotary_pct": 1.0, "sliding_window": 4096, "transformers_version": "4.56.2", "use_cache": true, "use_embedding_sharing": true, "use_gated_activation": true, "use_parallel_block": true, "use_parallel_embedding": true, "use_qk_norm": false, "vocab_size": 256000, "torch_dtype": "float16" }