https://huggingface.co/NousResearch/Hermes-3-Llama-3.1-405B
#227
by
leafspark
- opened
NousResearch/Hermes-3-Llama-3.1-405B
Another huge model by NousResearch, interestingly it's a full parameter fine tune on the base.
They also released a 8B and 70B finetune:
https://huggingface.co/NousResearch/Hermes-3-Llama-3.1-70B
https://huggingface.co/NousResearch/Hermes-3-Llama-3.1-8B
What a high-quality model. This is a full parameter finetune of Llama-3.1 405B on par with Llama-3.1 405B Instruct. It uses the ChatML template, supports function calling and has a system prompt to generate structured JSON output.
Queued, but for the 405B, patience is required.
mradermacher
changed discussion status to
closed