kromeurus/L3.1-Tivir-v0.1-10B

Full fine-tune vs ArliAI/Llama-3.1-8B-ArliAI-RPMax-v1.3. Fine-tune: 100% of the weights changed, across 32 of 32 layers.

Tensors changed: Norms 43/65, MLP 96/96, Attention 128/128

2 derivatives checked

• mradermacher/L3.1-Tivir-v0.1-10B-i1-GGUF: Quantization
• mradermacher/L3.1-Tivir-v0.1-10B-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse