aippolit/RENT-Qwen-7B

Partial fine-tune vs Qwen/Qwen2.5-7B-Instruct. Partial change: 86% of the weights changed (attention, mlp, norms), in 28 of 28 layers.

Tensors changed: Embeddings 0/1, Norms 49/57, MLP 84/84, Attention 196/196, lm_head 0/1

2 derivatives checked

• mradermacher/RENT-Qwen-7B-i1-GGUF: Quantization
• mradermacher/RENT-Qwen-7B-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse