Hugging Face's logo

a-normal-username
/
Mixtral-8x22B-OpenHermes-2.5

English
Mixtral
instruct
finetune
chatml
gpt4
synthetic data
distillation
Model card Files Community
1
Edit model card

OpenHermes 2.5 - Mixtral 8x22B

Mixtral 8x22B full SFTed on OpenHermes 2.5 dataset (https://huggingface.co/datasets/teknium/OpenHermes-2.5).

Evaluations are still being ran. Download the model from branches 4th-epoch and 3rd-epoch.

Prompt format is ChatML. Refer to https://huggingface.co/teknium/OpenHermes-2.5-Mistral-7B for examples.

Research supported by Google's TPU Research Cloud.

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference API
Unable to determine this model's library. Check the docs .

Model tree for a-normal-username/Mixtral-8x22B-OpenHermes-2.5

Base model

mistralai/Mixtral-8x22B-v0.1
Finetuned
(5)
this model

Dataset used to train a-normal-username/Mixtral-8x22B-OpenHermes-2.5