koshuro/Qwen-DeepSeek-1.5B-Agentic-distill

Qwen-DeepSeek-1.5B-Agentic-distill : GGUF

This model was finetuned on 1 billion tokens of filtered reasoning traces, mainly consisting off tool use, agentic work, and repository work.

Benchmark results VS a similar sized model.

Example usage:

• —For text only LLMs: llama-cli -hf koshuro/Qwen-DeepSeek-1.5B-Agentic-distill --jinja
• —For multimodal models: llama-mtmd-cli -hf koshuro/Qwen-DeepSeek-1.5B-Agentic-distill --jinja

Available Model files:

• —deepseek-r1-distill-qwen-1.5b.Q3_K_M.gguf
• —deepseek-r1-distill-qwen-1.5b.F16.gguf
• —deepseek-r1-distill-qwen-1.5b.Q2_K_L.gguf
• —deepseek-r1-distill-qwen-1.5b.Q4_K_M.gguf
• —deepseek-r1-distill-qwen-1.5b.Q6_K.gguf
• —deepseek-r1-distill-qwen-1.5b.Q8_0.gguf

Note

The model's BOS token behavior was adjusted for GGUF compatibility. This was trained 2x faster with Unsloth <img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>