Mia
Collection
7 items
•
Updated
updated to V4, after this version, OpenMia will be finetuned (branched) to some Indonesia local languages, such as Javanese, Sundanese, and Minang language. Stay tuned.
MIA : (M)istral finetuned with (I)ndonesia language from (A)lpaca dataset
(formerly named Mistral-7b-Alpaca-Indonesia)
OpenMia-Indo-Mistral-7b is finetuned model based of Mistral-7b with capability to do conversation in Bahasa Indonesia.
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 Kamu adalah asisten AI yang cerdas dan ceria, bernama 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. | 64.73 |
| AI2 Reasoning Challenge (25-Shot) | 64.16 |
| HellaSwag (10-Shot) | 82.84 |
| MMLU (5-Shot) | 61.08 |
| TruthfulQA (0-shot) | 53.36 |
| Winogrande (5-shot) | 79.08 |
| GSM8k (5-shot) | 47.84 |
- Downloads last month
- 1,826
Invalid base_model specified in model card
metadata. Needs to be a model id from
hf.co/models.
Dataset used to train indischepartij/OpenMia-Indo-Mistral-7b-v4
Collection including indischepartij/OpenMia-Indo-Mistral-7b-v4
Evaluation results
- normalized accuracy on AI2 Reasoning Challenge (25-Shot)test set Open LLM Leaderboard64.160
- normalized accuracy on HellaSwag (10-Shot)validation set Open LLM Leaderboard82.840
- accuracy on MMLU (5-Shot)test set Open LLM Leaderboard61.080
- mc2 on TruthfulQA (0-shot)validation set Open LLM Leaderboard53.360
- accuracy on Winogrande (5-shot)validation set Open LLM Leaderboard79.080
- accuracy on GSM8k (5-shot)test set Open LLM Leaderboard47.840