41 lines
966 B
JSON
41 lines
966 B
JSON
|
{
|
||
|
|
"_name_or_path": "mistral-awq",
|
||
|
|
"architectures": [
|
||
|
|
"MistralForCausalLM"
|
||
|
|
],
|
||
|
|
"attention_dropout": 0.0,
|
||
|
|
"bos_token_id": 1,
|
||
|
|
"eos_token_id": 2,
|
||
|
|
"head_dim": 128,
|
||
|
|
"hidden_act": "silu",
|
||
|
|
"hidden_size": 5120,
|
||
|
|
"initializer_range": 0.02,
|
||
|
|
"intermediate_size": 14336,
|
||
|
|
"max_position_embeddings": 1024000,
|
||
|
|
"model_type": "mistral",
|
||
|
|
"num_attention_heads": 32,
|
||
|
|
"num_hidden_layers": 40,
|
||
|
|
"num_key_value_heads": 8,
|
||
|
|
"quantization_config": {
|
||
|
|
"backend": "autoawq",
|
||
|
|
"bits": 4,
|
||
|
|
"do_fuse": false,
|
||
|
|
"exllama_config": null,
|
||
|
|
"fuse_max_seq_len": null,
|
||
|
|
"group_size": 128,
|
||
|
|
"modules_to_fuse": null,
|
||
|
|
"modules_to_not_convert": null,
|
||
|
|
"quant_method": "awq",
|
||
|
|
"version": "gemm",
|
||
|
|
"zero_point": true
|
||
|
|
},
|
||
|
|
"rms_norm_eps": 1e-05,
|
||
|
|
"rope_theta": 1000000.0,
|
||
|
|
"sliding_window": null,
|
||
|
|
"tie_word_embeddings": false,
|
||
|
|
"torch_dtype": "float16",
|
||
|
|
"transformers_version": "4.45.1",
|
||
|
|
"use_cache": false,
|
||
|
|
"vocab_size": 131074
|
||
|
|
}
|