schonsense/70B_Triage

Full fine-tune vs HPAI-BSC/Llama3.1-Aloe-Beta-70B. Fine-tune: 100% of the weights changed, across 80 of 80 layers.

Tensors changed: Embeddings 1/1, Norms 161/161, MLP 240/240, Attention 320/320, lm_head 1/1

3 derivatives checked

• mradermacher/70B_Triage-i1-GGUF: Quantization
• mradermacher/70B_Triage-GGUF: Quantization
• schonsense/70B_Incisive_Vernacular: Full fine-tune

On the Hub · Downloads on Model Pulse