Mistral-7B-Discord-0.1
This model is a finetune of Mistral-7B-0.1 on ~40 Million tokens worth of mostly not formatted, anonymized discord messages for 4 Epochs.
This is a base model.
Model Details
- Finetuned from model : mistralai/Mistral-7B-v0.1
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
Metric | Value |
---|---|
Avg. | 59.55 |
AI2 Reasoning Challenge (25-Shot) | 60.58 |
HellaSwag (10-Shot) | 82.49 |
MMLU (5-Shot) | 62.82 |
TruthfulQA (0-shot) | 42.73 |
Winogrande (5-shot) | 77.74 |
GSM8k (5-shot) | 30.93 |
- Downloads last month
- 76
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.
Spaces using BlouseJury/Mistral-7B-Discord-0.2 2
Evaluation results
- normalized accuracy on AI2 Reasoning Challenge (25-Shot)test set Open LLM Leaderboard60.580
- normalized accuracy on HellaSwag (10-Shot)validation set Open LLM Leaderboard82.490
- accuracy on MMLU (5-Shot)test set Open LLM Leaderboard62.820
- mc2 on TruthfulQA (0-shot)validation set Open LLM Leaderboard42.730
- accuracy on Winogrande (5-shot)validation set Open LLM Leaderboard77.740
- accuracy on GSM8k (5-shot)test set Open LLM Leaderboard30.930