birgermoell/llama-3-open-hermes-disco

Full fine-tune vs Muhammad2003/Llama3-8B-OpenHermes-DPO. Fine-tune: 93% of the weights changed, across 32 of 32 layers.

Tensors changed: Embeddings 1/1, Norms 5/65, MLP 96/96, Attention 128/128, lm_head 0/1

3 derivatives checked

• featherless-ai-quants/birgermoell-llama-3-open-hermes-disco-GGUF: Quantization
• mradermacher/llama-3-open-hermes-disco-i1-GGUF: Quantization
• mradermacher/llama-3-open-hermes-disco-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse