internlm/SWE-Fixer-Retriever-7B

Full fine-tune vs Qwen/Qwen2.5-7B. Fine-tune: 100% of the weights changed, across 28 of 28 layers.

Tensors changed: Embeddings 1/1, Norms 55/57, MLP 84/84, Attention 196/196, lm_head 1/1

2 derivatives checked

• featherless-ai-quants/internlm-SWE-Fixer-Retriever-7B-GGUF: Quantization
• tensorblock/SWE-Fixer-Retriever-7B-GGUF: Quantization

On the Hub · Downloads on Model Pulse