RiversHaveWings/minihf_evaluator_openllama_7b

minihfevaluatoropenllama_7b

minihf_evaluator_openllama_7b is a LoRA instruct fine-tune of OpenLLaMA 7B.

The sequence <|end|> was used to separate the prompt and response. The correct way to prompt the model is: Does 2 + 2 = 4?<|end|>. The tokenizer will prepend a BOS token (<s>) by default. The response will end with an EOS token (</s>).

Training procedure

minihf_evaluator_openllama_7b was fine-tuned for 100,000 examples on 90% Muennighoff/flan / 10% databricks/databricks-dolly-15k using batch size 4 per GPU on 8 40GB A100 GPUs. Examples where the prompt and response would not fit into 2,048 tokens were dropped. The fine-tuning was done using the following command:

accelerate launch make_evaluator.py --output-dir minihf_evaluator_openllama_7b

The following bitsandbytes quantization config was used during training:

• —loadin8bit: False
• —loadin4bit: True
• —llmint8threshold: 6.0
• —llmint8skip_modules: None
• —llmint8enablefp32cpu_offload: False
• —llmint8hasfp16weight: False
• —bnb4bitquant_type: nf4
• —bnb4bitusedoublequant: True
• —bnb4bitcompute_dtype: bfloat16

Framework versions

• —PEFT 0.4.0.dev0