|
--- |
|
library_name: peft |
|
base_model: vilm/vinallama-7b-chat |
|
language: |
|
- vi |
|
- en |
|
datasets: |
|
- alespalla/chatbot_instruction_prompts |
|
--- |
|
|
|
# Model Card for VinaLLaMA |
|
|
|
<!-- Provide a quick summary of what the model is/does. --> |
|
|
|
Reference: |
|
|
|
- https://www.dropbox.com/scl/fi/sy4d78jk4mp8g87y2xwrs/description.pdf |
|
- https://huggingface.co/docs/peft/quicktour |
|
|
|
## Model Details |
|
|
|
### Model Description |
|
|
|
<!-- Provide a longer summary of what this model is. --> |
|
|
|
- **Developed by:** Teddythinh |
|
- **Shared by:** AI VIET NAM |
|
- **Model type:** PEFT |
|
- **Language(s) (NLP):** Vietnamese |
|
- **License:** |
|
- **Finetuned from model:** vilm/vinallama-7b-chat |
|
|
|
### Model Sources [optional] |
|
|
|
<!-- Provide the basic links for the model. --> |
|
|
|
- **Repository:** https://huggingface.co/teddythinh/vinallama-test |
|
|
|
#### Summary |
|
|
|
## Environmental Impact |
|
|
|
Experiments were conducted using the Google Cloud Platform in region asia-east1, which has a carbon efficiency of 0.56 kgCO2eq/kWh. A cumulative of 5 hours of computation was performed on hardware of type T4 (TDP of 70W). |
|
|
|
Total emissions are estimated to be 0.2 kgCO2eq of which 100 percent were directly offset by the cloud provider. |
|
|
|
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.7.2.dev0 |
