MaziyarPanahi/Calme-7B-Instruct-v0.1.1

Full fine-tune vs MaziyarPanahi/Calme-7B-Instruct-v0.1. Fine-tune: 100% of the weights changed, across 32 of 32 layers.

Tensors changed: Embeddings 1/1, Norms 13/65, MLP 96/96, Attention 128/128, lm_head 1/1

3 derivatives checked

• MaziyarPanahi/Calme-7B-Instruct-v0.1.1-GGUF: Quantization
• mradermacher/Calme-7B-Instruct-v0.1.1-i1-GGUF: Quantization
• mradermacher/Calme-7B-Instruct-v0.1.1-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse