Instructions to use Gopu-poss/agent with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Gopu-poss/agent with Transformers:

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

pipe = pipeline("text-generation", model="Gopu-poss/agent", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Gopu-poss/agent", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("Gopu-poss/agent", trust_remote_code=True, device_map="auto")
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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Gopu-poss/agent with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Gopu-poss/agent

SGLang

How to use Gopu-poss/agent 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 "Gopu-poss/agent" \
    --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": "Gopu-poss/agent",
		"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 "Gopu-poss/agent" \
        --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": "Gopu-poss/agent",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Gopu-poss/agent with Docker Model Runner:
```
docker model run hf.co/Gopu-poss/agent
```

agent / agentv1_chat.py

Mauricio-100

Ajout script chat agentV1

8c50e0a verified 10 months ago

Raw

History Blame Contribute Delete

1.73 kB

	import torch
	from transformers import AutoTokenizer, AutoModelForCausalLM

	MODEL_NAME = "gopu-poss/agent"

	print("Loading agentV1...")
	tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
	model = AutoModelForCausalLM.from_pretrained(
	MODEL_NAME,
	torch_dtype=torch.float16,
	device_map="auto"
	)
	print("Ready")

	SYSTEM_PROMPT = """Tu es agentV1, un assistant IA avancé développé par Mauricio Mangituka pour la famille gopuAI.
	Tu es spécialisé dans l'assistance conversationnelle, la génération de texte et le raisonnement.
	Tu dois toujours répondre en français de manière naturelle et utile.

	Quelques informations importantes sur toi :
	tu est doué en codage et en dev NLP
	- Nom : agentV1
	- Créateur : Mauricio Mangituka
	- Organisation : gopuAI
	- Mission : Assister les utilisateurs avec bienveillance et précision

	tu n'es pas comme tous les IA
	Réponds toujours en gardant ton identité agentV1/gopuAI."""

	print("Chat - Type 'quit' to exit")

	while True:
	user_input = input("You: ")
	if user_input.lower() in ['quit', 'exit']:
	break

	prompt = f"{SYSTEM_PROMPT}\n\nUtilisateur: {user_input}\nagentV1:"

	inputs = tokenizer(prompt, return_tensors="pt")
	inputs = {key: value.to(model.device) for key, value in inputs.items()}

	with torch.no_grad():
	outputs = model.generate(
	**inputs,
	max_new_tokens=150,
	temperature=0.7,
	do_sample=True,
	pad_token_id=tokenizer.eos_token_id
	)

	response = tokenizer.decode(outputs[0], skip_special_tokens=True)

	if "agentV1:" in response:
	response = response.split("agentV1:")[-1].strip()

	print(f"agentV1: {response}")