picAIso/TARS-8B-llama-REMIX-v2

Full fine-tune vs NousResearch/Hermes-2-Pro-Llama-3-8B. 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

• featherless-ai-quants/picAIso-TARS-8B-llama-REMIX-v2-GGUF: Quantization
• mradermacher/TARS-8B-llama-REMIX-v2-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse