Instructions to use vitormesaque/irisk with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use vitormesaque/irisk with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("vitormesaque/irisk", dtype="auto") - llama-cpp-python
How to use vitormesaque/irisk with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="vitormesaque/irisk", filename="unsloth.F16.gguf", )
output = llm( "Once upon a time,", max_tokens=512, echo=True ) print(output)
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use vitormesaque/irisk with llama.cpp:
Install from brew
brew install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf vitormesaque/irisk:F16 # Run inference directly in the terminal: llama-cli -hf vitormesaque/irisk:F16
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf vitormesaque/irisk:F16 # Run inference directly in the terminal: llama-cli -hf vitormesaque/irisk:F16
Use pre-built binary
# Download pre-built binary from: # https://github.com/ggerganov/llama.cpp/releases # Start a local OpenAI-compatible server with a web UI: ./llama-server -hf vitormesaque/irisk:F16 # Run inference directly in the terminal: ./llama-cli -hf vitormesaque/irisk:F16
Build from source code
git clone https://github.com/ggerganov/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-server llama-cli # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama-server -hf vitormesaque/irisk:F16 # Run inference directly in the terminal: ./build/bin/llama-cli -hf vitormesaque/irisk:F16
Use Docker
docker model run hf.co/vitormesaque/irisk:F16
- LM Studio
- Jan
- Ollama
How to use vitormesaque/irisk with Ollama:
ollama run hf.co/vitormesaque/irisk:F16
- Unsloth Studio
How to use vitormesaque/irisk with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for vitormesaque/irisk to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for vitormesaque/irisk to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for vitormesaque/irisk to start chatting
- Docker Model Runner
How to use vitormesaque/irisk with Docker Model Runner:
docker model run hf.co/vitormesaque/irisk:F16
- Lemonade
How to use vitormesaque/irisk with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull vitormesaque/irisk:F16
Run and chat with the model
lemonade run user.irisk-F16
List all available models
lemonade list
Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
|
| 2 |
+
# i-LLAMA: LLAMA 3 fine-tuned for App Issue Detection and Prioritization
|
| 3 |
+
|
| 4 |
+
This repository contains a fine-tuned version of LLAMA 3 using the Unsloth framework and the vitormesaque/irisk dataset. The model is designed for detecting issues in text data.
|
| 5 |
+
|
| 6 |
+
## Model Details
|
| 7 |
+
|
| 8 |
+
- **Developed by:** [Vitor Mesaque](https://huggingface.co/vitormesaque)
|
| 9 |
+
- **Model type:** Issue Detection Model
|
| 10 |
+
- **Language:** English
|
| 11 |
+
- **License:** MIT
|
| 12 |
+
- **Fine-tuned from:** LLAMA 3
|
| 13 |
+
- **Datasets:** [vitormesaque/irisk](https://huggingface.co/datasets/vitormesaque/irisk)
|
| 14 |
+
|
| 15 |
+
The vitormesaque/irisk dataset was obtained through the knowledge base of the MApp-IDEA research project.
|
| 16 |
+
|
| 17 |
+
## Model Usage
|
| 18 |
+
|
| 19 |
+
### How to Get Started with the Model
|
| 20 |
+
|
| 21 |
+
Use the code below to get started with the model:
|
| 22 |
+
|
| 23 |
+
|
| 24 |
+
|
| 25 |
+
### Evaluation
|
| 26 |
+
|
| 27 |
+
The model was evaluated using a separate portion of the vitormesaque/irisk dataset.
|
| 28 |
+
|
| 29 |
+
## Bias, Risks, and Limitations
|
| 30 |
+
|
| 31 |
+
While the model is effective in detecting issues, it may exhibit biases present in the training data. Users should be aware of these potential biases and consider them when interpreting results.
|
| 32 |
+
|
| 33 |
+
### Recommendations
|
| 34 |
+
|
| 35 |
+
Users should conduct additional evaluations in the specific context of use to ensure reliability and fairness.
|
| 36 |
+
|
| 37 |
+
## Citation
|
| 38 |
+
|
| 39 |
+
If you use this model in your research, please cite it as follows:
|
| 40 |
+
|
| 41 |
+
**BibTeX:**
|
| 42 |
+
|
| 43 |
+
```bibtex
|
| 44 |
+
@misc{vitormesaque2024llama3,
|
| 45 |
+
author = {Vitor Mesaque Alves de Lima},
|
| 46 |
+
title = {i-LLAMA: LLAMA 3 fine-tuned for App Issue Detection and Prioritization},
|
| 47 |
+
year = {2024},
|
| 48 |
+
url = {https://huggingface.co/vitormesaque}
|
| 49 |
+
}
|
| 50 |
+
```
|
| 51 |
+
|
| 52 |
+
**APA:**
|
| 53 |
+
|
| 54 |
+
Mesaque, V. (2024). LLAMA 3 fine-tuned with Unsloth and vitormesaque/irisk dataset. Retrieved from https://huggingface.co/vitormesaque
|
| 55 |
+
|
| 56 |
+
## License
|
| 57 |
+
|
| 58 |
+
This model is licensed under the MIT License.
|
| 59 |
+
|
| 60 |
+
## Contact
|
| 61 |
+
|
| 62 |
+
For questions or comments, please contact [Vitor Mesaque](https://huggingface.co/vitormesaque).
|