allura-forge/q3-30b-rc1

Full fine-tune vs Gryphe/Pantheon-Proto-RP-1.8-30B-A3B. Fine-tune: 100% of the weights changed, across 48 of 48 layers.

Tensors changed: MLP 2613/2613, Embeddings 1/1, Norms 193/193, Attention 192/192, lm_head 1/1

3 derivatives checked

• mradermacher/q3-30b-rc1-GGUF: Quantization
• mradermacher/q3-30b-rc1-i1-GGUF: Quantization
• allura-org/Q3-30b-A3b-Pentiment: LoRA-style

On the Hub · Downloads on Model Pulse