openGPT-X/Teuken-7B-instruct-v0.6

Full fine-tune vs openGPT-X/Teuken-7B-base-v0.6. Fine-tune: 100% of the weights changed, across 32 of 32 layers.

Tensors changed: Norms 50/65, MLP 96/96, Attention 128/128

2 derivatives checked

• mradermacher/Teuken-7B-instruct-v0.6-i1-GGUF: Quantization
• mradermacher/Teuken-7B-instruct-v0.6-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse