openaccess-ai-collective/DPOpenHermes-7B-v2

Full fine-tune vs teknium/OpenHermes-2.5-Mistral-7B. Fine-tune: 100% of the weights changed, across 32 of 32 layers.

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

3 derivatives checked

• TheBloke/DPOpenHermes-7B-v2-GGUF: Quantization
• mradermacher/DPOpenHermes-7B-v2-i1-GGUF: Quantization
• mradermacher/DPOpenHermes-7B-v2-GGUF: Same weights, converted

1 other repos hold byte-for-byte identical weight files.

On the Hub · Downloads on Model Pulse