mpasila/Llama-3-Umbral-Mind-SimPO-8B

Full fine-tune vs Casual-Autopsy/L3-Umbral-Mind-RP-v1.0-8B. Fine-tune: 100% of the weights changed, across 32 of 32 layers.

Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 61/65, MLP 96/96, Attention 128/128

2 derivatives checked

• mradermacher/Llama-3-Umbral-Mind-SimPO-8B-i1-GGUF: Quantization
• mradermacher/Llama-3-Umbral-Mind-SimPO-8B-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse