unsloth
/

Qwen2.5-Coder-3B-Instruct-GGUF

Inference Endpoints

Model card Files Files and versions Community

danielhanchen commited on 7 days ago

Commit

0f03efd

•

1 Parent(s): fe0bd83

Update README.md

Files changed (1) hide show

README.md +3 -0

README.md CHANGED Viewed

@@ -13,6 +13,9 @@ tags:
 - codeqwen
 ---
 # Finetune Llama 3.2, Qwen2.5, Gemma 2, Mistral 2-5x faster with 70% less memory via Unsloth!
 We have a Qwen 2.5 (all model sizes) [free Google Colab Tesla T4 notebook](https://colab.research.google.com/drive/1Kose-ucXO1IBaZq5BvbwWieuubP7hxvQ?usp=sharing).

 - codeqwen
 ---
+> [!NOTE]
+> Use 4bit quants (Q4_K_M) and above for 3B - lower quants will degrade accuracy
 # Finetune Llama 3.2, Qwen2.5, Gemma 2, Mistral 2-5x faster with 70% less memory via Unsloth!
 We have a Qwen 2.5 (all model sizes) [free Google Colab Tesla T4 notebook](https://colab.research.google.com/drive/1Kose-ucXO1IBaZq5BvbwWieuubP7hxvQ?usp=sharing).