tsukasa-7b-qlora-gptq / config.json
ludis's picture
updated to mistral 7b base 0.2 from 0.1
21bc665 verified
raw
history blame contribute delete
973 Bytes
{
"_name_or_path": "models/limarp-7b-qlora-lora/merged/",
"architectures": [
"MistralForCausalLM"
],
"attention_dropout": 0.0,
"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,
"quantization_config": {
"bits": 4,
"damp_percent": 0.1,
"desc_act": true,
"group_size": -1,
"is_marlin_format": false,
"model_file_base_name": null,
"model_name_or_path": null,
"quant_method": "gptq",
"static_groups": false,
"sym": true,
"true_sequential": true
},
"rms_norm_eps": 1e-05,
"rope_theta": 1000000.0,
"sliding_window": null,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.40.0.dev0",
"use_cache": false,
"vocab_size": 32003
}