AIencoder/Axon26-Coder

Full fine-tune vs Nondzu/Mistral-7B-Instruct-v0.2-code-ft. Fine-tune: 100% of the weights changed, across 32 of 32 layers.

Tensors changed: Norms 65/65, MLP 96/96, Attention 128/128

1 derivatives checked

• mradermacher/Axon26-Coder-i1-GGUF: Quantization

On the Hub · Downloads on Model Pulse