sharpenb's picture
e0151ecc3d9af8ee8706e50da789b76af15dc8919a30ecc2cefec8fc73a5d476
c4a7cc3 verified
raw
history blame
1.18 kB
{
"_name_or_path": "/ceph/hdd/staff/charpent/.cache/modelsugtn439_25lmy0uc",
"architectures": [
"MistralForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 1,
"eos_token_id": 32000,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 14336,
"max_position_embeddings": 32768,
"model_type": "mistral",
"num_attention_heads": 32,
"num_hidden_layers": 32,
"num_key_value_heads": 8,
"quantization_config": {
"_load_in_4bit": false,
"_load_in_8bit": true,
"bnb_4bit_compute_dtype": "bfloat16",
"bnb_4bit_quant_storage": "uint8",
"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": [
"lm_head"
],
"llm_int8_threshold": 6.0,
"load_in_4bit": false,
"load_in_8bit": true,
"quant_method": "bitsandbytes"
},
"rms_norm_eps": 1e-05,
"rope_theta": 10000.0,
"sliding_window": 4096,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.42.4",
"use_cache": false,
"vocab_size": 32002
}