gz987/qwen2.5-7b-cabs-v0.4

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

Tensors changed: Embeddings 1/1, Norms 37/57, MLP 84/84, Attention 189/196, lm_head 1/1

1 derivatives checked

• mradermacher/qwen2.5-7b-cabs-v0.4-i1-GGUF: Quantization

On the Hub · Downloads on Model Pulse