natzx94/EsDrac-v1-7B

Full fine-tune vs Qwen/Qwen2.5-7B-Instruct. Fine-tune: 93% of the weights changed, across 28 of 28 layers.

Tensors changed: Embeddings 1/1, Norms 0/57, MLP 84/84, Attention 112/196, lm_head 0/1

2 derivatives checked

• mradermacher/EsDrac-v1-7B-i1-GGUF: Quantization
• mradermacher/EsDrac-v1-7B-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse