Instructions to use siliconcorerina/rina-coder-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use siliconcorerina/rina-coder-base with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="siliconcorerina/rina-coder-base")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("siliconcorerina/rina-coder-base", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use siliconcorerina/rina-coder-base with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "siliconcorerina/rina-coder-base" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "siliconcorerina/rina-coder-base", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/siliconcorerina/rina-coder-base
- SGLang
How to use siliconcorerina/rina-coder-base with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "siliconcorerina/rina-coder-base" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "siliconcorerina/rina-coder-base", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "siliconcorerina/rina-coder-base" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "siliconcorerina/rina-coder-base", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use siliconcorerina/rina-coder-base with Docker Model Runner:
docker model run hf.co/siliconcorerina/rina-coder-base
Initial model card for RINA Coder Base
Browse files
README.md
ADDED
|
@@ -0,0 +1,105 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
language:
|
| 4 |
+
- en
|
| 5 |
+
- fr
|
| 6 |
+
- code
|
| 7 |
+
library_name: transformers
|
| 8 |
+
pipeline_tag: text-generation
|
| 9 |
+
tags:
|
| 10 |
+
- code
|
| 11 |
+
- code-generation
|
| 12 |
+
- rina-ai
|
| 13 |
+
- llm
|
| 14 |
+
---
|
| 15 |
+
|
| 16 |
+
# RINA Coder — Base
|
| 17 |
+
|
| 18 |
+
> Modele de langage RINA AI dedie a la generation, la completion et l explication de code.
|
| 19 |
+
> Site : [plateforme-rina.com](https://plateforme-rina.com) · Code : [github.com/siliconcorerina/RINA-AI](https://github.com/siliconcorerina/RINA-AI)
|
| 20 |
+
|
| 21 |
+
**Statut : placeholder.** Les poids ne sont pas encore publies. Ce depot reserve l identifiant `siliconcorerina/rina-coder-base` et decrit le modele cible. La premiere version sera annoncee via les [issues du depot GitHub](https://github.com/siliconcorerina/RINA-AI/issues/4).
|
| 22 |
+
|
| 23 |
+
## Description
|
| 24 |
+
|
| 25 |
+
RINA Coder est la famille de modeles de generation de code maintenue par l equipe RINA AI. Cette variante `base` est destinee a la completion et a la generation libre. Une variante `instruct` suivra pour les usages conversationnels.
|
| 26 |
+
|
| 27 |
+
## Usage prevu
|
| 28 |
+
|
| 29 |
+
```python
|
| 30 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer
|
| 31 |
+
|
| 32 |
+
model_id = "siliconcorerina/rina-coder-base"
|
| 33 |
+
tokenizer = AutoTokenizer.from_pretrained(model_id)
|
| 34 |
+
model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto")
|
| 35 |
+
|
| 36 |
+
prompt = "def fibonacci(n):"
|
| 37 |
+
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
|
| 38 |
+
outputs = model.generate(**inputs, max_new_tokens=128, temperature=0.2)
|
| 39 |
+
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
|
| 40 |
+
```
|
| 41 |
+
|
| 42 |
+
Voir aussi le script de demo : [demo/inference_example.py](https://github.com/siliconcorerina/RINA-AI/blob/main/demo/inference_example.py).
|
| 43 |
+
|
| 44 |
+
## Cas d usage
|
| 45 |
+
|
| 46 |
+
- Completion de code dans des editeurs et IDE
|
| 47 |
+
- Generation de fonctions a partir de docstrings
|
| 48 |
+
- Explication de snippets de code
|
| 49 |
+
- Refactoring assiste
|
| 50 |
+
- Tests unitaires generes a partir du code source
|
| 51 |
+
|
| 52 |
+
## Hors perimetre
|
| 53 |
+
|
| 54 |
+
- Conseil juridique, medical ou financier
|
| 55 |
+
- Decisions impactant des personnes (recrutement, credit, etc.)
|
| 56 |
+
- Usage en production sans verification humaine du code genere
|
| 57 |
+
|
| 58 |
+
## Donnees d entrainement
|
| 59 |
+
|
| 60 |
+
A documenter lors de la publication du premier checkpoint. Les sources prevues incluent :
|
| 61 |
+
|
| 62 |
+
- Code open source sous licences permissives
|
| 63 |
+
- Documentation technique publique
|
| 64 |
+
- Corpus de problemes de programmation (HumanEval-like)
|
| 65 |
+
|
| 66 |
+
## Evaluation
|
| 67 |
+
|
| 68 |
+
Les benchmarks cibles sont :
|
| 69 |
+
|
| 70 |
+
| Benchmark | Statut |
|
| 71 |
+
|-----------|--------|
|
| 72 |
+
| HumanEval (pass@1) | a venir |
|
| 73 |
+
| MBPP (pass@1) | a venir |
|
| 74 |
+
| MultiPL-E (Rust, Go, Kotlin) | a venir |
|
| 75 |
+
| RINA-Bench (interne) | a venir |
|
| 76 |
+
|
| 77 |
+
Suivi : [issues evaluation](https://github.com/siliconcorerina/RINA-AI/labels/evaluation).
|
| 78 |
+
|
| 79 |
+
## Limitations
|
| 80 |
+
|
| 81 |
+
- Le code genere peut contenir des bugs, des failles de securite, ou ne pas compiler. Toujours relire et tester.
|
| 82 |
+
- Le modele peut halluciner des API ou des bibliotheques inexistantes.
|
| 83 |
+
- Les performances varient fortement selon le langage et le domaine.
|
| 84 |
+
- Le contexte est limite ; les fichiers tres longs ne sont pas couverts dans une seule passe.
|
| 85 |
+
|
| 86 |
+
## Licence
|
| 87 |
+
|
| 88 |
+
MIT. Voir [LICENSE](https://github.com/siliconcorerina/RINA-AI/blob/main/LICENSE).
|
| 89 |
+
|
| 90 |
+
## Contact
|
| 91 |
+
|
| 92 |
+
- Site : [plateforme-rina.com](https://plateforme-rina.com)
|
| 93 |
+
- Email : [hello@plateforme-rina.com](mailto:hello@plateforme-rina.com)
|
| 94 |
+
- GitHub : [github.com/siliconcorerina](https://github.com/siliconcorerina)
|
| 95 |
+
|
| 96 |
+
## Citation
|
| 97 |
+
|
| 98 |
+
```bibtex
|
| 99 |
+
@misc{rinacoder2026,
|
| 100 |
+
title = {RINA Coder: a code language model by RINA AI},
|
| 101 |
+
author = {RINA AI Team},
|
| 102 |
+
year = {2026},
|
| 103 |
+
url = {https://huggingface.co/siliconcorerina/rina-coder-base}
|
| 104 |
+
}
|
| 105 |
+
```
|