theprint/ThinkMix-Gemma3-4B-GRPO-GGUF

Same weights, converted (fewer layers) vs theprint/ThinkMix-Gemma3-4B-GRPO. theprint/ThinkMix-Gemma3-4B-GRPO-GGUF matches part of theprint/ThinkMix-Gemma3-4B-GRPO (444 of its 883 tensors; the rest of theprint/ThinkMix-Gemma3-4B-GRPO has no counterpart). On the shared part: Same weights stored in another dtype (BF16 → BF16/F32).

Tensors changed: Embeddings 0/1, Norms 0/205, MLP 0/102, Attention 0/136

On the Hub · Downloads on Model Pulse