Instructions to use Pys237/pys-expert-amon-v1-final with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Pys237/pys-expert-amon-v1-final with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="Pys237/pys-expert-amon-v1-final")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Pys237/pys-expert-amon-v1-final")
model = AutoModelForCausalLM.from_pretrained("Pys237/pys-expert-amon-v1-final")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Pys237/pys-expert-amon-v1-final with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Pys237/pys-expert-amon-v1-final"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Pys237/pys-expert-amon-v1-final",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Pys237/pys-expert-amon-v1-final

SGLang

How to use Pys237/pys-expert-amon-v1-final 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 "Pys237/pys-expert-amon-v1-final" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Pys237/pys-expert-amon-v1-final",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "Pys237/pys-expert-amon-v1-final" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Pys237/pys-expert-amon-v1-final",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Pys237/pys-expert-amon-v1-final with Docker Model Runner:
```
docker model run hf.co/Pys237/pys-expert-amon-v1-final
```

PYS-Expert Amon V1 Final

Ce modèle est une version optimisée basée sur Qwen/Qwen2.5-0.5B-Instruct. Il est configuré pour servir de moteur de correction textuelle, de restructuration de documents et d'assistance linguistique pour l'écosystème PYS-DOC.

🧠 Utilisation dans PYS-DOC

Ce modèle est conçu pour être appelé via l'Inference API de Hugging Face pour nettoyer le texte brut extrait des manuscrits des étudiants de l'Université de Dschang.

Paramètres d'API recommandés

Max New Tokens: 512
Temperature: 0.3 (pour des corrections strictes sans invention)
Do Sample: false

Model Details

Developed by: Pys237
Model type: Causal Language Model
Language(s) (NLP): Français (fr)
Finetuned from model: Qwen/Qwen2.5-0.5B-Instruct

Bias, Risks, and Limitations

Ce modèle étant ultra-léger (0.5B), il est extrêmement rapide mais peut présenter des limites sur des consignes de rédaction trop complexes. Il doit être utilisé principalement pour de la correction orthographique, le remplacement d'abréviations étudiantes et la mise au propre de paragraphes.

Downloads last month: 35

Safetensors

Model size

0.5B params

Tensor type

F16

Model tree for Pys237/pys-expert-amon-v1-final

Base model

Qwen/Qwen2.5-0.5B

Finetuned

Qwen/Qwen2.5-0.5B-Instruct

Finetuned

(793)

this model