MiniMaxAI/SynLogic-7B

Full fine-tune vs Qwen/Qwen2.5-7B. Fine-tune: 100% of the weights changed, across 28 of 28 layers.

Tensors changed: Embeddings 1/1, Norms 51/57, MLP 84/84, Attention 196/196, lm_head 1/1

3 derivatives checked

• mradermacher/SynLogic-7B-GGUF: Same weights, converted
• mradermacher/SynLogic-7B-i1-GGUF: Quantization
• tensorblock/MiniMaxAI_SynLogic-7B-GGUF: Quantization

1 other repos hold byte-for-byte identical weight files.

On the Hub · Downloads on Model Pulse