shisa-ai/shisa-v2-qwen2.5-7b
Full fine-tune vs Qwen/Qwen2.5-7B-Instruct. Fine-tune: 93% of the weights changed, across 28 of 28 layers.
Tensors changed: Embeddings 0/1, Norms 55/57, MLP 84/84, Attention 196/196, lm_head 1/1
5 derivatives checked
- mmnga/shisa-v2-qwen2.5-7b-gguf: Quantization
- mradermacher/shisa-v2-qwen2.5-7b-i1-GGUF: Quantization
- mradermacher/shisa-v2-qwen2.5-7b-GGUF: Same weights, converted
- DevQuasar/shisa-ai.shisa-v2-qwen2.5-7b-GGUF: Same weights, converted
- tatsuyaaaaaaa/shisa-v2-qwen2.5-7b-gguf: Same weights, converted
1 other repos hold byte-for-byte identical weight files.