Jebadiah/Aria-rp-coder-7b

Full fine-tune vs Jebadiah/Aria-ruby-v3. Fine-tune: 100% of the weights changed, across 32 of 32 layers.

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

2 derivatives checked

• mradermacher/Aria-rp-coder-7b-i1-GGUF: Quantization
• mradermacher/Aria-rp-coder-7b-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse