mradermacher/Llama-1B-GRPO_Final-GGUF
Same weights, converted vs NickyNicky/Llama-1B-GRPO_Final. Same weights stored in another dtype (BF16 → F16/F32), plus 1 new tensors.
Tensors changed: Embeddings 0/1, Norms 0/33, MLP 0/48, Attention 0/64
Same weights, converted vs NickyNicky/Llama-1B-GRPO_Final. Same weights stored in another dtype (BF16 → F16/F32), plus 1 new tensors.
Tensors changed: Embeddings 0/1, Norms 0/33, MLP 0/48, Attention 0/64