DedeProGames/Chesser-248K-Mini

Full fine-tune vs Locutusque/TinyMistral-248M-v2.5-Instruct. Fine-tune: 100% of the weights changed, across 12 of 12 layers.

Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 25/25, MLP 36/36, Attention 48/48

1 derivatives checked

• mradermacher/Chesser-248K-Mini-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse