{ "architectures": [ "Cohere2ForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "attention_probs_dropout_prob": 0.1, "bos_token_id": 5, "dtype": "float32", "eos_token_id": 255001, "head_dim": 8, "hidden_act": "gelu", "hidden_dropout_prob": 0.1, "hidden_size": 32, "initializer_range": 0.02, "intermediate_size": 37, "is_decoder": true, "layer_norm_eps": 1e-05, "layer_types": [ "sliding_attention", "sliding_attention" ], "logit_scale": 0.0625, "max_position_embeddings": 512, "model_type": "cohere2", "num_attention_heads": 4, "num_hidden_layers": 2, "num_key_value_heads": 4, "pad_token_id": 0, "rope_parameters": { "rope_theta": 10000.0, "rope_type": "default" }, "sliding_window": 4096, "tie_word_embeddings": true, "transformers_version": "5.16.0.dev0", "type_vocab_size": 16, "use_cache": true, "vocab_size": 255029 }