shisa-ai/shisa-v2-qwen2.5-32b

Full fine-tune vs Qwen/Qwen2.5-32B-Instruct. Fine-tune: 98% of the weights changed, across 64 of 64 layers.

Tensors changed: Embeddings 0/1, Norms 127/129, MLP 192/192, Attention 448/448, lm_head 1/1

3 derivatives checked

• mradermacher/shisa-v2-qwen2.5-32b-i1-GGUF: Quantization
• mradermacher/shisa-v2-qwen2.5-32b-GGUF: Quantization
• DevQuasar/shisa-ai.shisa-v2-qwen2.5-32b-GGUF: Same weights, converted

1 other repos hold byte-for-byte identical weight files.

On the Hub · Downloads on Model Pulse