metadata
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
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
Detailed results can be found here
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 |