mbgenai/concise_speaker

1{2  "_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",3  "architectures": [4    "MistralForCausalLM"5  ],6  "attention_dropout": 0.0,7  "bos_token_id": 1,8  "eos_token_id": 2,9  "hidden_act": "silu",10  "hidden_size": 4096,11  "initializer_range": 0.02,12  "intermediate_size": 14336,13  "max_position_embeddings": 32768,14  "model_type": "mistral",15  "num_attention_heads": 32,16  "num_hidden_layers": 32,17  "num_key_value_heads": 8,18  "quantization_config": {19    "_load_in_4bit": true,20    "_load_in_8bit": false,21    "bnb_4bit_compute_dtype": "bfloat16",22    "bnb_4bit_quant_type": "nf4",23    "bnb_4bit_use_double_quant": false,24    "llm_int8_enable_fp32_cpu_offload": false,25    "llm_int8_has_fp16_weight": false,26    "llm_int8_skip_modules": null,27    "llm_int8_threshold": 6.0,28    "load_in_4bit": true,29    "load_in_8bit": false,30    "quant_method": "bitsandbytes"31  },32  "rms_norm_eps": 1e-05,33  "rope_theta": 1000000.0,34  "sliding_window": null,35  "tie_word_embeddings": false,36  "torch_dtype": "float32",37  "transformers_version": "4.38.2",38  "use_cache": false,39  "vocab_size": 3200040}41