Mia
Collection
7 items
•
Updated
updated to V3 with some refinement
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 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. | 68.00 |
| AI2 Reasoning Challenge (25-Shot) | 64.42 |
| HellaSwag (10-Shot) | 84.22 |
| MMLU (5-Shot) | 62.64 |
| TruthfulQA (0-shot) | 53.95 |
| Winogrande (5-shot) | 81.53 |
| GSM8k (5-shot) | 61.26 |
- Downloads last month
- 3,697
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-v3-refined
Collection including indischepartij/OpenMia-Indo-Mistral-7b-v3-refined
Evaluation results
- normalized accuracy on AI2 Reasoning Challenge (25-Shot)test set Open LLM Leaderboard64.420
- normalized accuracy on HellaSwag (10-Shot)validation set Open LLM Leaderboard84.220
- accuracy on MMLU (5-Shot)test set Open LLM Leaderboard62.640
- mc2 on TruthfulQA (0-shot)validation set Open LLM Leaderboard53.950
- accuracy on Winogrande (5-shot)validation set Open LLM Leaderboard81.530
- accuracy on GSM8k (5-shot)test set Open LLM Leaderboard61.260