win10/high-speed-mixing-7B-V2

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

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

2 derivatives checked

• mradermacher/high-speed-mixing-7B-V2-i1-GGUF: Quantization
• mradermacher/high-speed-mixing-7B-V2-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse