mradermacher/UnifiedReward-qwen-7b-i1-GGUF
Full fine-tune (fewer layers) vs CodeGoat24/UnifiedReward-qwen-7b. mradermacher/UnifiedReward-qwen-7b-i1-GGUF matches part of CodeGoat24/UnifiedReward-qwen-7b (339 of its 729 tensors; the rest of CodeGoat24/UnifiedReward-qwen-7b has no counterpart). On the shared part: mradermacher/UnifiedReward-qwen-7b-i1-GGUF is a GGUF (Q6_K) of different weights. Fine-tune: 100% of the weights changed, across 28 of 28 layers.
Tensors changed: Embeddings 1/1, Norms 53/57, MLP 84/84, Attention 196/196, lm_head 1/1