OpenBuddy/openbuddy-yi1.5-34b-v21.3-32k

Full fine-tune vs 01-ai/Yi-1.5-34B-32K. Fine-tune: 100% of the weights changed, across 60 of 60 layers.

Tensors changed: Norms 111/121, MLP 180/180, Attention 240/240

2 derivatives checked

• mradermacher/openbuddy-yi1.5-34b-v21.3-32k-i1-GGUF: Quantization
• mradermacher/openbuddy-yi1.5-34b-v21.3-32k-GGUF: Quantization

On the Hub · Downloads on Model Pulse