{ | |
"architectures": [ | |
"MistralForCausalLM" | |
], | |
"bos_token_id": 1, | |
"eos_token_id": 2, | |
"hidden_act": "silu", | |
"hidden_size": 1024, | |
"initializer_range": 0.02, | |
"intermediate_size": 4096, | |
"max_position_embeddings": 32768, | |
"model_type": "mistral", | |
"num_attention_heads": 32, | |
"num_hidden_layers": 12, | |
"num_key_value_heads": 8, | |
"quantization": { | |
"group_size": 64, | |
"bits": 8 | |
}, | |
"rms_norm_eps": 1e-06, | |
"rope_theta": 10000.0, | |
"sliding_window": 32, | |
"tie_word_embeddings": false, | |
"torch_dtype": "float16", | |
"transformers_version": "4.35.0", | |
"use_cache": true, | |
"vocab_size": 32005 | |
} |