Instructions to use bil-y/Pharia-1-LLM-7B-control with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bil-y/Pharia-1-LLM-7B-control with Transformers:

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

pipe = pipeline("text-generation", model="bil-y/Pharia-1-LLM-7B-control", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("bil-y/Pharia-1-LLM-7B-control", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use bil-y/Pharia-1-LLM-7B-control with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "bil-y/Pharia-1-LLM-7B-control"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "bil-y/Pharia-1-LLM-7B-control",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/bil-y/Pharia-1-LLM-7B-control

SGLang

How to use bil-y/Pharia-1-LLM-7B-control 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 "bil-y/Pharia-1-LLM-7B-control" \
    --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": "bil-y/Pharia-1-LLM-7B-control",
		"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 "bil-y/Pharia-1-LLM-7B-control" \
        --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": "bil-y/Pharia-1-LLM-7B-control",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use bil-y/Pharia-1-LLM-7B-control with Docker Model Runner:
```
docker model run hf.co/bil-y/Pharia-1-LLM-7B-control
```

This is the safetensors-conversion of Pharia-1-LLM-7B-control. We provide a joint model card for Pharia-1-LLM-7B-control and Pharia-1-LLM-control-aligned. Find this model card here.

Usage

import torch

from transformers import AutoModelForCausalLM, PreTrainedTokenizerFast


INPUT = """<|begin_of_text|><|start_header_id|>system<|end_header_id|>

You are a helpful assistant. You give engaging, well-structured answers to user inquiries.<|eot_id|><|start_header_id|>user<|end_header_id|>

When was Rome founded?<|eot_id|><|start_header_id|>assistant<|end_header_id|>


"""

MODEL_ID = "Aleph-Alpha/Pharia-1-LLM-7B-control-hf"

tokenizer = PreTrainedTokenizerFast.from_pretrained(MODEL_ID)
model = AutoModelForCausalLM.from_pretrained(MODEL_ID, trust_remote_code=True, torch_dtype=torch.bfloat16)

device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
model = model.to(device)

inputs = tokenizer(INPUT, return_token_type_ids=False, return_tensors="pt").to(device)
outputs = model.generate(**inputs, max_new_tokens=50)
generated_text = tokenizer.decode(outputs[0])
print(generated_text)

Downloads last month: 1

Safetensors

Model size

7B params

Tensor type

BF16