Note: This requires Ollama 0.0.19 or later.

OpenHermes-13b is a new fine-tuning of the Hermes dataset.

From the Hugging Face card:

OpenHermes was trained on 242,000 entries of primarily GPT-4 generated data, from open datasets across the AI landscape, including:

• GPTeacher - General Instruct, Roleplay v1, Roleplay v2, and Code Instruct Datasets, by Teknium
• WizardLM (v1, evol_instruct 70k), by WizardLM Team/nlpxucan
• Airoboros GPT-4 (v1.0), by JonDurbin
• Camel-AI’s domain expert datasets, by the Camel-AI Team
• CodeAlpaca, by Sahil2801
• GPT4-LLM and Unnatural Instructions, by Microsoft

Filtering included removal of OpenAI refusals, disclaimers, and “As an AI” type examples and more

The base dataset mix the model was trained on is identical to Nous-Hermes’, minus the Nous-Instruct and PDACTL datasets which were private datasets.

Modelfile:

# Base model for OpenHermes-13B
FROM ./gguf-OpenHermes-13B-q3_K_M.bin

TEMPLATE """
{{- if and .First .System }}
### Instruction:
{{ .System }}
{{- end }}

### Input:
{{ .Prompt }}

### Response: """

SYSTEM """
Below is an instruction that describes a task. Write a response that appropriately completes the request"""