{ "model_type": "cohere2", "architectures": [ "Cohere2ForCausalLM" ], "vocab_size": 256000, "max_position_embeddings": 131072, "hidden_size": 12288, "logit_scale": 0.25, "intermediate_size": 36864, "num_hidden_layers": 64, "num_attention_heads": 96, "num_key_value_heads": 8, "hidden_act": "silu", "initializer_range": 0.02, "layer_norm_eps": 1e-05, "use_cache": false, "rope_theta": 50000, "rope_scaling": null, "attention_bias": false, "attention_dropout": 0.0, "sliding_window": 4096, "sliding_window_pattern": 4, "head_dim": 128, "cache_implementation": "hybrid", "return_dict": true, "output_hidden_states": false, "output_attentions": false, "torchscript": false, "torch_dtype": "float16", "use_bfloat16": false, "tf_legacy_loss": false, "pruned_heads": {}, "tie_word_embeddings": true, "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "diversity_penalty": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": null, "finetuning_task": null, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "tokenizer_class": null, "prefix": null, "bos_token_id": 5, "pad_token_id": 0, "eos_token_id": 255001, "sep_token_id": null, "decoder_start_token_id": null, "task_specific_params": null, "problem_type": null, "_name_or_path": "/home/share-hdd/frj/genai/model/c4ai-command-a-03-2025", "_attn_implementation_autoset": true, "transformers_version": "4.49.0", "order_of_interleaved_layers": "local_attn_first", "position_embedding_type": "rope_gptj", "rotary_pct": 1.0, "use_embedding_sharing": true, "use_gated_activation": true, "use_parallel_block": true, "use_parallel_embedding": true }