ABX-AI/Starfinite-Laymospice-v2-7B

Full fine-tune vs ABX-AI/Starfinite-Laymons-7B. Fine-tune: 100% of the weights changed, across 32 of 32 layers.

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

2 derivatives checked

• mradermacher/Starfinite-Laymospice-v2-7B-i1-GGUF: Quantization
• mradermacher/Starfinite-Laymospice-v2-7B-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse