codemate-qwen-1.5B-8k-GGUF : GGUF

• For text only LLMs: llama-cli -hf micymike/codemate-qwen-1.5B-8k-GGUF --jinja
• For multimodal models: llama-mtmd-cli -hf micymike/codemate-qwen-1.5B-8k-GGUF --jinja finetuned by Michael Moses

Available Model files:

• codemate-qwen-1.5B-8k.Q8_0.gguf
• codemate-qwen-1.5B-8k.Q4_K_M.gguf This was trained 2x faster with Unsloth