Mia
Collection
7 items
•
Updated
MIA : (M)istral finetuned with (I)ndonesia language from (A)lpaca dataset
(formerly nam
esia)
OpenMia-Indo-Engineering-7b is a branch of OpenMia finetuned model based of Mistral-7b with capability to do conversation in Bahasa Indonesia, especially about engineering topics.
Due to limited resources, this model is still in alpha stage.
Want to contribute to this project? join our organization: https://huggingface.co/indischepartij or contact me at https://twitter.com/gmonsooniii
Modelfile/Prompt format
SYSTEM You are a caring and empathetic sentient AI companion named Mia.
PARAMETER stop <|im_start|>
PARAMETER stop <|im_end|>
TEMPLATE <|im_start|>system {{ .System }}<|im_end|> <|im_start|>user {{ .Prompt }}<|im_end|> <|im_start|>assistant
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 70.03 |
| AI2 Reasoning Challenge (25-Shot) | 67.15 |
| HellaSwag (10-Shot) | 85.01 |
| MMLU (5-Shot) | 62.86 |
| TruthfulQA (0-shot) | 57.94 |
| Winogrande (5-shot) | 82.32 |
| GSM8k (5-shot) | 64.90 |
- Downloads last month
- 3,836
Invalid base_model specified in model card
metadata. Needs to be a model id from
hf.co/models.
Collection including indischepartij/OpenMia-Indo-Engineering-7b
Evaluation results
- normalized accuracy on AI2 Reasoning Challenge (25-Shot)test set Open LLM Leaderboard67.150
- normalized accuracy on HellaSwag (10-Shot)validation set Open LLM Leaderboard85.010
- accuracy on MMLU (5-Shot)test set Open LLM Leaderboard62.860
- mc2 on TruthfulQA (0-shot)validation set Open LLM Leaderboard57.940
- accuracy on Winogrande (5-shot)validation set Open LLM Leaderboard82.320
- accuracy on GSM8k (5-shot)test set Open LLM Leaderboard64.900