model1_sft_gguf : GGUF

• For text only LLMs: llama-cli -hf jerrycheng233/model1_sft_gguf --jinja
• For multimodal models: llama-mtmd-cli -hf jerrycheng233/model1_sft_gguf --jinja

Available Model files:

• DeepSeek-R1-Distill-Llama-8B.Q8_0.gguf

Note

The model's BOS token behavior was adjusted for GGUF compatibility. This was trained 2x faster with Unsloth