fusedyi / README.md
leaderboard-pr-bot's picture
Adding Evaluation Results
2e725db verified
|
raw
history blame
1.03 kB
---
language:
- en
license: apache-2.0
tags:
- Mixtral
- instruct
- finetune
- chatml
- DPO
- RLHF
- gpt4
- synthetic data
- distillation
model-index:
- name: fusedYi
results: []
---
# Model Card for FusedYi
<!-- Provide a quick summary of what the model is/does. -->
This is fused Yi-6B.
I took a Yi, merged it with another Yi, and got a new Yi out of the Yis.
Yi-ceptionized.
## Model Details
1.9 x Yi-6B
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_pharaouk__fusedyi)
| Metric |Value|
|---------------------------------|----:|
|Avg. |53.18|
|AI2 Reasoning Challenge (25-Shot)|55.03|
|HellaSwag (10-Shot) |76.60|
|MMLU (5-Shot) |63.43|
|TruthfulQA (0-shot) |49.29|
|Winogrande (5-shot) |72.69|
|GSM8k (5-shot) | 2.05|