mradermacher/UnifiedReward-Flex-qwen3vl-8b-GGUF
Full fine-tune (fewer layers) vs CodeGoat24/UnifiedReward-Flex-qwen3vl-8b. mradermacher/UnifiedReward-Flex-qwen3vl-8b-GGUF matches part of CodeGoat24/UnifiedReward-Flex-qwen3vl-8b (399 of its 750 tensors; the rest of CodeGoat24/UnifiedReward-Flex-qwen3vl-8b has no counterpart). On the shared part: mradermacher/UnifiedReward-Flex-qwen3vl-8b-GGUF is a GGUF (F16) of different weights. Fine-tune: 92% of the weights changed, across 36 of 36 layers.
Tensors changed: lm_head 1/1, Embeddings 0/1, Norms 125/145, MLP 108/108, Attention 144/144