jsk0214/Seagull-llama-3-8B-orpo-v0.4

Full fine-tune vs kuotient/Meta-Llama-3-8B. Fine-tune: 93% of the weights changed, across 32 of 32 layers.

Tensors changed: Embeddings 0/1, Norms 0/65, MLP 96/96, Attention 128/128, lm_head 1/1

2 derivatives checked

• featherless-ai-quants/jsk0214-Seagull-llama-3-8B-orpo-v0.4-GGUF: Quantization
• mradermacher/Seagull-llama-3-8B-orpo-v0.4-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse