alfred-40B-1023-GPTQ / config.json
TheBloke's picture
GPTQ model commit
e3149d2
{
"_name_or_path": "/workspace/process/lightonai_alfred-40b-1023/source",
"alibi": false,
"apply_residual_connection_post_layernorm": false,
"architectures": [
"RWForCausalLM"
],
"attention_dropout": 0.0,
"auto_map": {
"AutoConfig": "configuration_RW.RWConfig",
"AutoModelForCausalLM": "modeling_RW.RWForCausalLM"
},
"bias": false,
"bos_token_id": 11,
"embedding_scaling_factor": 4,
"eos_token_id": 11,
"hidden_dropout": 0.0,
"hidden_size": 8192,
"initializer_range": 0.02,
"layer_norm_epsilon": 1e-05,
"model_type": "RefinedWeb",
"multi_query": true,
"n_head": 128,
"n_head_kv": 8,
"n_layer": 60,
"ntk_scaling_factor": 5,
"pad_token_id": 0,
"parallel_attn": true,
"pretraining_tp": 1,
"single_ln": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.35.0",
"use_cache": true,
"vanilla_scaling_factor": null,
"vocab_size": 65024,
"quantization_config": {
"bits": 4,
"group_size": -1,
"damp_percent": 0.1,
"desc_act": true,
"sym": true,
"true_sequential": true,
"model_name_or_path": null,
"model_file_base_name": "model",
"quant_method": "gptq"
}
}