thu-coai/IF-CRITIC-14B
Full fine-tune vs Qwen/Qwen2.5-14B-Instruct. Fine-tune: 100% of the weights changed, across 48 of 48 layers.
Tensors changed: Embeddings 1/1, Norms 97/97, MLP 144/144, Attention 336/336, lm_head 1/1
2 derivatives checked
- mradermacher/IF-CRITIC-14B-i1-GGUF: Quantization
- mradermacher/IF-CRITIC-14B-GGUF: Quantization