lik07/Stheno-TheSpice-v1

Full fine-tune vs Sao10K/L3-8B-Stheno-v3.2. Fine-tune: 100% of the weights changed, across 32 of 32 layers.

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

2 derivatives checked

• mradermacher/Stheno-TheSpice-v1-i1-GGUF: Quantization
• mradermacher/Stheno-TheSpice-v1-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse