CodeGoat24/UnifiedReward-Think-qwen3vl-32b

Full fine-tune vs CodeGoat24/UnifiedReward-2.0-qwen3vl-32b. Fine-tune: 96% of the weights changed, across 64 of 64 layers.

Tensors changed: Embeddings 1/4, Norms 241/373, MLP 192/316, Attention 256/364, lm_head 1/1

3 derivatives checked

• mradermacher/UnifiedReward-Think-qwen3vl-32b-i1-GGUF: Quantization (fewer layers)
• mradermacher/UnifiedReward-Think-qwen3vl-32b-GGUF: Quantization (fewer layers)
• CodeGoat24/UnifiedReward-Flex-qwen3vl-32b: Full fine-tune

On the Hub · Downloads on Model Pulse