manojkumarvohra/llama2-7B-Chat-8bit-guanaco-pico-adapter-hf

LLAMA2 7B Guanaco Pico Adapter

This is a 8Bit Quantized adapter over llama2-7b-chat-hf checkpoint. To use the merged version of this model refer: manojkumarvohra/llama2-7B-Chat-hf-8bit-guanaco-pico-finetuned => https://huggingface.co/manojkumarvohra/llama2-7B-Chat-hf-8bit-guanaco-pico-finetuned This is only meant for learning purpose and is not recommended to be used for any business purpose.

Training procedure

The following bitsandbytes quantization config was used during training:

• —loadin8bit: True
• —loadin4bit: False
• —llmint8threshold: 6.0
• —llmint8skip_modules: None
• —llmint8enablefp32cpu_offload: False
• —llmint8hasfp16weight: False
• —bnb4bitquant_type: fp4
• —bnb4bitusedoublequant: False
• —bnb4bitcompute_dtype: float32

The following bitsandbytes quantization config was used during training:

• —loadin8bit: True
• —loadin4bit: False
• —llmint8threshold: 6.0
• —llmint8skip_modules: None
• —llmint8enablefp32cpu_offload: False
• —llmint8hasfp16weight: False
• —bnb4bitquant_type: fp4
• —bnb4bitusedoublequant: False
• —bnb4bitcompute_dtype: float32

Framework versions

• —PEFT 0.4.0

• —PEFT 0.4.0