{ "_name_or_path": "sanity/hf_ckpt/sanity_35b_i3_main_3k_20241020_063420_most_basket/ckpt-1149", "architectures": [ "CohereForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 5, "eos_token_id": 255001, "hidden_act": "silu", "hidden_size": 8192, "initializer_range": 0.02, "intermediate_size": 24576, "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": 8, "pad_token_id": 0, "rope_theta": 4000000, "torch_dtype": "float16", "transformers_version": "4.44.0", "use_cache": true, "use_qk_norm": false, "vocab_size": 256000, "quantization_config": { "quant_method": "exl2", "version": "0.2.3", "bits": 6.0, "head_bits": 8, "calibration": { "rows": 115, "length": 2048, "dataset": "(default)" } } }