DASD-4B-Thinking-2507-stage1 : GGUF

This model was finetuned and converted to GGUF format using Unsloth.

Example usage:

• For text only LLMs: ./llama.cpp/llama-cli -hf Jackrong/DASD-4B-Thinking-2507-stage1 --jinja
• For multimodal models: ./llama.cpp/llama-mtmd-cli -hf Jackrong/DASD-4B-Thinking-2507-stage1 --jinja

Available Model files:

• DASD-4B-Thinking-2507-GRPO-v2.Q8_0.gguf
• DASD-4B-Thinking-2507-GRPO-v2.Q4_K_M.gguf This was trained 2x faster with Unsloth