bgg1996/Melinoe-GLM-30B-A3B-Thinking

Full fine-tune vs zai-org/GLM-4.7-Flash. Fine-tune: 100% of the weights changed, across 47 of 47 layers.

Tensors changed: Embeddings 1/1, Norms 189/189, MLP 2504/2504, Attention 235/235, lm_head 1/1

3 derivatives checked

• mradermacher/Melinoe-GLM-30B-A3B-Thinking-i1-GGUF: Quantization
• mradermacher/Melinoe-GLM-30B-A3B-Thinking-GGUF: Quantization
• bgg1996/Melinoe-GLM-30B-A3B-Thinking-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse