1TuanPham/Instruct_en-vi_7500_1epoch_TheBloke_Mistralic-7B-1-GPTQ_LORA_CAUSAL_LM

Training procedure

The following bitsandbytes quantization config was used during training:

• —quant_method: gptq
• —bits: 4
• —tokenizer: None
• —dataset: None
• —group_size: 128
• —damp_percent: 0.1
• —desc_act: True
• —sym: True
• —true_sequential: True
• —usecudafp16: True
• —model_seqlen: 4096
• —blocknameto_quantize: model.layers
• —modulenameprecedingfirstblock: ['model.embed_tokens']
• —batch_size: 1
• —padtokenid: None
• —disable_exllama: False
• —maxinputlength: None

Framework versions

• —PEFT 0.5.0