mradermacher/CriticLeanGPT-Qwen2.5-7B-Instruct-SFT-RL-GGUF

Same weights, converted vs m-a-p/CriticLeanGPT-Qwen2.5-7B-Instruct-SFT-RL. Same weights stored in another dtype (BF16 → F16/F32).

Tensors changed: lm_head 0/1, MLP 0/84, Attention 0/196, Norms 0/57, Embeddings 0/1

On the Hub · Downloads on Model Pulse