| { | |
| "_name_or_path": "/home/ahmet_cohere_com/HF_Final_weight_tie", | |
| "architectures": [ | |
| "CohereForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "auto_map": { | |
| "AutoConfig": "configuration_cohere.CohereConfig", | |
| "AutoModel": "modeling_cohere.CohereModel", | |
| "AutoModelForCausalLM": "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_max_length": 131072, | |
| "model_type": "cohere", | |
| "num_attention_heads": 64, | |
| "num_hidden_layers": 40, | |
| "num_key_value_heads": 64, | |
| "pad_token_id": 0, | |
| "pretraining_tp": 1, | |
| "rope_theta": 8000000.0, | |
| "torch_dtype": "float16", | |
| "transformers_version": "4.38.2", | |
| "use_cache": true, | |
| "vocab_size": 256000, | |
| "tie_word_embeddings": true, | |
| "quantization_config": { | |
| "quant_method": "exl2", | |
| "version": "0.0.16", | |
| "bits": 3.5, | |
| "head_bits": 6, | |
| "calibration": { | |
| "rows": 100, | |
| "length": 2048, | |
| "dataset": "(default)" | |
| } | |
| } | |
| } |