You can deploy this model and start earning money today!

lucasnhandang/
lab22-dpo-qwen2.5-vn-GGUF

Q4_K_M: Recommended balance of speed and quality (~4-bit).
Q5_K_M: Higher quality (~5-bit).

Name: lab22-dpo-qwen2.5-vn-GGUF
Availability: InStock

Views

No views yet

lucasnhandang/lab22-dpo-qwen2.5-vn-GGUF (GGUF Release)

Aligned using Direct Preference Optimization (DPO) on top of SFT-mini (unsloth/Qwen2.5-3B-bnb-4bit) with UltraFeedback & Vietnamese Alpaca.

bash

# llama.cpp
./llama-cli -m model-Q4_K_M.gguf -p "Giải thích thuật toán quicksort" -n 256