mradermacher/Co-rewarding-I-Llama-3.2-3B-Instruct-MATH-GGUF

Same weights, converted vs TMLR-Group-HF/Co-rewarding-I-Llama-3.2-3B-Instruct-MATH. Same weights stored in another dtype (BF16 → F16/F32), plus 1 new tensors.

Tensors changed: lm_head 0/1, Embeddings 0/1, MLP 0/84, Norms 0/57, Attention 0/112

On the Hub · Downloads on Model Pulse