Based on Meta-Llama-3-8b-Instruct, and is governed by Meta Llama 3 License agreement: https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct
DPO fine tuning method using the following datasets:
- https://huggingface.co/datasets/Intel/orca_dpo_pairs
- https://huggingface.co/datasets/argilla/distilabel-math-preference-dpo
- https://huggingface.co/datasets/unalignment/toxic-dpo-v0.2
- https://huggingface.co/datasets/M4-ai/prm_dpo_pairs_cleaned
- https://huggingface.co/datasets/jondurbin/truthy-dpo-v0.1
Instruct format:
<|begin_of_text|><|start_header_id|>system<|end_header_id|>
{{ system_prompt }}<|eot_id|><|start_header_id|>user<|end_header_id|>
{{ user_message_1 }}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
{{ model_answer_1 }}<|eot_id|><|start_header_id|>user<|end_header_id|>
{{ user_message_2 }}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
Quants:
FP16: https://huggingface.co/OwenArli/ArliAI-Llama-3-8B-Instruct-DPO-v0.1
GGUF: https://huggingface.co/OwenArli/ArliAI-Llama-3-8B-Instruct-DPO-v0.1-GGUF