| { | |
| "_name_or_path": "CohereForAI/c4ai-command-r-v01", | |
| "architectures": [ | |
| "CohereForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "auto_map": { | |
| "AutoConfig": "CohereForAI/c4ai-command-r-v01--configuration_cohere.CohereConfig", | |
| "AutoModel": "CohereForAI/c4ai-command-r-v01--configuration_cohere.CohereModel", | |
| "AutoModelForCausalLM": "CohereForAI/c4ai-command-r-v01--modeling_cohere.CohereForCausalLM" | |
| }, | |
| "bos_token_id": 5, | |
| "eos_token_id": 255001, | |
| "hidden_act": "silu", | |
| "hidden_size": 8192, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 22528, | |
| "layer_norm_eps": 1e-05, | |
| "logit_scale": 0.0625, | |
| "max_position_embeddings": 8192, | |
| "model_type": "cohere", | |
| "num_attention_heads": 64, | |
| "num_hidden_layers": 40, | |
| "num_key_value_heads": 64, | |
| "pad_token_id": 0, | |
| "pretraining_tp": 1, | |
| "quantization_config": { | |
| "_load_in_4bit": true, | |
| "_load_in_8bit": false, | |
| "bnb_4bit_compute_dtype": "bfloat16", | |
| "bnb_4bit_quant_type": "fp4", | |
| "bnb_4bit_use_double_quant": false, | |
| "llm_int8_enable_fp32_cpu_offload": false, | |
| "llm_int8_has_fp16_weight": false, | |
| "llm_int8_skip_modules": null, | |
| "llm_int8_threshold": 6.0, | |
| "load_in_4bit": true, | |
| "load_in_8bit": false, | |
| "quant_method": "bitsandbytes" | |
| }, | |
| "rope_theta": 8000000.0, | |
| "torch_dtype": "float16", | |
| "transformers_version": "4.39.0.dev0", | |
| "use_cache": true, | |
| "vocab_size": 256000 | |
| } | |