--- base_model: unsloth/qwen2.5-coder-7b-instruct-bnb-4bit tags: - text-generation-inference - transformers - unsloth - qwen2 - trl - sft license: apache-2.0 language: - en --- # Xwen-Coder-7b - **Developed by:** TBuscagliaXsolla - **Finetuned fromm:** unsloth/qwen2.5-coder-7b-instruct-bnb-4bit ## Available Formats ### LORA Safetensors and Tokenizer - [tokenizer.json](tokenizer.json) - [adapter_model.safetensors](adapter_model.safetensors) ### Merged F16 for VLLM - [pytorch_model.bin.index.json](pytorch_model.bin.index.json) ### Merged GGUF Formats - [unsloth.Q8_0.gguf](unsloth.Q8_0.gguf) - [unsloth.Q4_K_M.gguf](unsloth.Q4_K_M.gguf) - [unsloth.Q5_K_M.gguf](unsloth.Q5_K_M.gguf) ## Unsloth Shoutout This qwen2 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library. [](https://github.com/unslothai/unsloth)