metadata
base_model: teknium/OpenHermes-2-Mistral-7B
inference: false
language:
- en
license: apache-2.0
model-index:
- name: OpenHermes-2-Mistral-7B
results: []
model_creator: Teknium
model_name: OpenHermes 2 Mistral 7B
model_type: mistral
prompt_template: |
<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
quantized_by: lr1729
tags:
- mistral
- instruct
- finetune
- chatml
- gpt4
- synthetic data
- distillation
GGUF quants of https://huggingface.co/teknium/OpenHermes-2.5-Mistral-7B with importance matrix calculations run on 20k_random_data.txt for improved perplexity.