Text Generation
Transformers
Safetensors
Japanese
English
mistral
conversational
text-generation-inference
4-bit precision
awq
shisa-7B-v1-AWQ / config.json
TheBloke's picture
AWQ model commit
8bc45fb
raw
history blame
821 Bytes
{
"_name_or_path": "/workspace/process/augmxnt_shisa-7b-v1/source",
"architectures": [
"MistralForCausalLM"
],
"bos_token_id": 1,
"eos_token_id": 2,
"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,
"pad_token_id": 0,
"pretraining_tp": 1,
"quantization_config": {
"bits": 4,
"group_size": 128,
"quant_method": "awq",
"version": "gemm",
"zero_point": true
},
"rms_norm_eps": 1e-05,
"rope_theta": 10000.0,
"sliding_window": 4096,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.35.2",
"use_cache": true,
"vocab_size": 120128
}