Kquant03/Samlagast-7B-bf16

Full fine-tune vs FelixChao/Faraday-7B. Fine-tune: 100% of the weights changed, across 32 of 32 layers.

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

2 derivatives checked

• mradermacher/Samlagast-7B-bf16-GGUF: Same weights, converted
• mradermacher/Samlagast-7B-bf16-i1-GGUF: Quantization

On the Hub · Downloads on Model Pulse