Mistral trained with the airoboros dataset!

image/png

Actual dataset is airoboros 2.2, but it seems to have been replaced on hf with 2.2.1.

Prompt Format:

USER: <prompt>
ASSISTANT:

TruthfulQA:

hf-causal-experimental (pretrained=/home/teknium/dakota/lm-evaluation-harness/airoboros2.2-mistral/,dtype=float16), limit: None, provide_description: False, num_fewshot: 0, batch_size: 8
|    Task     |Version|Metric|Value |   |Stderr|
|-------------|------:|------|-----:|---|-----:|
|truthfulqa_mc|      1|mc1   |0.3562|±  |0.0168|
|             |       |mc2   |0.5217|±  |0.0156|

Wandb training charts: https://wandb.ai/teknium1/airoboros-mistral-7b/runs/airoboros-mistral-1?workspace=user-teknium1

More info to come

Downloads last month
15
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Dataset used to train LoneStriker/airoboros-mistral2.2-7b-8.0bpw-h6-exl2