CHANGEDPROMPTqwen2.5-500M-grpo-after-sft-both-sysprompt-nothinking-GGUF-2 : GGUF

• For text only LLMs: ./llama.cpp/llama-cli -hf CHANGEDPROMPTqwen2.5-500M-grpo-after-sft-both-sysprompt-nothinking-GGUF-2 --jinja
• For multimodal models: ./llama.cpp/llama-mtmd-cli -hf CHANGEDPROMPTqwen2.5-500M-grpo-after-sft-both-sysprompt-nothinking-GGUF-2 --jinja

Available Model files:

• qwen2.5-0.5b-instruct.Q5_K_M.gguf
• qwen2.5-0.5b-instruct.Q8_0.gguf
• qwen2.5-0.5b-instruct.Q4_K_M.gguf

Ollama

An Ollama Modelfile is included for easy deployment. This was trained 2x faster with Unsloth