Modelpublic

cnbeining/OpenHermes-2.5-Mistral-7B-Sentence-Segmentation

sourceHugging Faceapache-2.0updated 3y agoView on Hugging Face

0likes

Model Card

OpenHermes-2.5-Mistral-7B-Sentence-Segmentation

See files for original notebook used for finetuning

Model description

OpenHermes-2.5-Mistral-7B-Sentence-Segmentation is a DPO finetuned OpenHermes model for sentence segmentation capability.

This model is based on teknium/OpenHermes-2.5-Mistral-7B, a state-of-the-art chat-aligned 7B model.

Example Outputs

The model has been finetuned with (ChatML)[https://github.com/MicrosoftDocs/azure-docs/blob/main/articles/ai-services/openai/includes/chat-markup-language.md#messages] template:

<|im_start|>system
Segment:<|im_end|>
<|im_start|>user

"input": "sentence": "segment":

—"word": "Shere,"
—"word": "in"
—"word": "your"
—"word": "report"
—"word": "on"
—"word": "female"
—"word": "sexuality,"
—"word": "men"
—"word": "were"
—"word": "staggered"
—"word": "to"
—"word": "learn"
—"word": "that"
—"word": "clitoral"
—"word": "stimulation"
—"word": "was"
—"word": "much"
—"word": "more"
—"word": "important"
—"word": "than"
—"word": "penetration."

<|im_end|>

<|im_start|>assistant

with output in the format of

"output": "sentence": "segment":

—"word": "Shere,"
—"word": "in"
—"word": "your"
—"word": "report"
—"word": "on"
—"word": "female"
—"word": "sexuality," "segment":
—"word": "men"
—"word": "were"
—"word": "staggered"
—"word": "to"
—"word": "learn"
—"word": "that" "segment":
—"word": "clitoral"
—"word": "stimulation"
—"word": "was"
—"word": "much"
—"word": "more"
—"word": "important"
—"word": "than"
—"word": "penetration."

Misc

This mistral model was trained 2x faster with Unsloth and Huggingface's TRL library.