CodeGoat24/UnifiedReward-Think-qwen-7b
Partial fine-tune vs CodeGoat24/UnifiedReward-qwen-7b. Partial change: 85% of the weights changed (attention, lm_head, mlp, norms), in 28 of 32 layers.
Tensors changed: Embeddings 0/2, Norms 53/122, MLP 84/280, Attention 196/324, lm_head 1/1
2 derivatives checked
- mradermacher/UnifiedReward-Think-qwen-7b-i1-GGUF: Quantization (fewer layers)
- mradermacher/UnifiedReward-Think-qwen-7b-GGUF: Same weights, converted (fewer layers)