CodeGoat24/UnifiedReward-Flex-qwen3vl-8b

Partial fine-tune vs CodeGoat24/UnifiedReward-Think-qwen3vl-8b. Partial change: 86% of the weights changed (attention, lm_head, mlp, norms), in 36 of 36 layers.

Tensors changed: Embeddings 0/4, Norms 123/261, MLP 108/232, Attention 144/252, lm_head 1/1

2 derivatives checked

• mradermacher/UnifiedReward-Flex-qwen3vl-8b-i1-GGUF: Full fine-tune (fewer layers)
• mradermacher/UnifiedReward-Flex-qwen3vl-8b-GGUF: Full fine-tune (fewer layers)

On the Hub · Downloads on Model Pulse