Azure99/Blossom-V6.1-GLM-32B

Full fine-tune vs zai-org/GLM-4-32B-Base-0414. Fine-tune: 97% of the weights changed, across 61 of 61 layers.

Tensors changed: Embeddings 0/1, Norms 0/245, MLP 122/122, Attention 244/244, lm_head 1/1

2 derivatives checked

• mradermacher/Blossom-V6.1-GLM-32B-i1-GGUF: Quantization
• mradermacher/Blossom-V6.1-GLM-32B-GGUF: Quantization

On the Hub · Downloads on Model Pulse