|
|
--- |
|
|
license: mit |
|
|
|
|
|
ScoLAM_01: |
|
|
description: "ScoLAM 01 has been trained over 100,000 high-quality French language samples with a focus on data bias, grammar, and overall language/writing capacities of the model." |
|
|
training_environment: |
|
|
hardware: "Nvidia GPU" |
|
|
platform: "Vertex AI" |
|
|
base_model: "Llama2-70B-Chat-HF" |
|
|
dataset: "private dataset" |
|
|
added_value: |
|
|
- "French Language" |
|
|
- "English Language" |
|
|
- "Writing" |
|
|
- "Content Creation" |
|
|
- "Data Bias Reduction" |
|
|
- "Cybersecurity prediction" |
|
|
|
|
|
|
|
|
contact: |
|
|
email: "team@theschooly.tech" |
|
|
--- |
|
|
|
|
|
# ScoLaM_01 |
|
|
|
|
|
This model card provides a detailed overview of the ScoLaM_01 model, trained for enhanced language processing and content creation in French, with a particular focus on reducing data bias. |
|
|
|
|
|
## Model Details |
|
|
|
|
|
### Model Description |
|
|
|
|
|
ScoLaM_01 is a state-of-the-art language model designed for various applications in French language processing, including writing enhancement and content creation. The model has been trained with a specific emphasis on addressing data bias, improving grammatical accuracy, and enhancing the overall language and writing capabilities. |
|
|
|
|
|
- **Developed by:** The Schooly Tech Team |
|
|
- **Model type:** Language Processing |
|
|
- **Language(s) (NLP):** French ,English |
|
|
- **License:** MIT |
|
|
- **Finetuned from model:** Llama2-70B-Chat-HF |
|
|
|
|
|
## Uses |
|
|
|
|
|
### Direct Use |
|
|
|
|
|
ScoLaM_01 is designed for direct application in language processing tasks, such as content creation, text analysis, and educational purposes in the French language. |
|
|
|
|
|
### Out-of-Scope Use |
|
|
|
|
|
The model is not intended for use in languages other than French, or for tasks that require understanding of cultural nuances or context-specific jargon. |
|
|
|
|
|
## Bias, Risks, and Limitations |
|
|
|
|
|
The model has been trained to reduce data bias; however, users should be aware of the inherent limitations and potential biases in any language model. |
|
|
|
|
|
### Recommendations |
|
|
|
|
|
Users should critically evaluate the model's outputs, especially in sensitive or nuanced contexts. Regular updates and feedback will be essential for continuous improvement. |
|
|
|
|
|
## Training Details |
|
|
|
|
|
### Training Data |
|
|
|
|
|
The model was trained on over 100,000 high-quality French language samples from a private dataset. |
|
|
|
|
|
### Training Procedure |
|
|
|
|
|
#### Training Hyperparameters |
|
|
|
|
|
- **Training regime:** Details on the specific training regime will be added upon further validation and testing. |
|
|
|
|
|
## Environmental Impact |
|
|
|
|
|
- **Hardware Type:** Nvidia GPU |
|
|
- **Cloud Provider:** Vertex AI |
|
|
- **Compute Region:** [Region Information Needed] |
|
|
- **Carbon Emitted:** Estimations will be made using the Machine Learning Impact calculator. |
|
|
|
|
|
## Technical Specifications |
|
|
|
|
|
### Compute Infrastructure |
|
|
|
|
|
- **Hardware:** Nvidia GPU |
|
|
- **Software:** Vertex AI , AI Azure Studio , AWS Sage , Langchain |
|
|
|
|
|
For more information, please feel free to reach out to us at team@theschooly.tech. |
|
|
|
