Instructions to use Sermental/Sermental-Instruct-7.3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Sermental/Sermental-Instruct-7.3B with Transformers:

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

pipe = pipeline("text-generation", model="Sermental/Sermental-Instruct-7.3B")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("Sermental/Sermental-Instruct-7.3B", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Sermental/Sermental-Instruct-7.3B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Sermental/Sermental-Instruct-7.3B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Sermental/Sermental-Instruct-7.3B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Sermental/Sermental-Instruct-7.3B

SGLang

How to use Sermental/Sermental-Instruct-7.3B 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 "Sermental/Sermental-Instruct-7.3B" \
    --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": "Sermental/Sermental-Instruct-7.3B",
		"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 "Sermental/Sermental-Instruct-7.3B" \
        --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": "Sermental/Sermental-Instruct-7.3B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Sermental/Sermental-Instruct-7.3B with Docker Model Runner:
```
docker model run hf.co/Sermental/Sermental-Instruct-7.3B
```

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Model Card for Sermental-Instruct-7.3B

Download

from huggingface_hub import snapshot_download
from pathlib import Path

sermental_models_path = Path.home().joinpath('sermental_models', '7.3B')
sermental_models_path.mkdir(parents=True, exist_ok=True)

snapshot_download(repo_id="Sermental-Instruct-7.3B", allow_patterns=["params.json", "consolidated.safetensors", "tokenizer.model.v3"], local_dir=sermental_models_path)

Generate with `transformers`

If you want to use Hugging Face transformers to generate text, you can do something like this.

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "Sermental-Instruct-7.3B"
tokenizer = AutoTokenizer.from_pretrained(model_id)

model = AutoModelForCausalLM.from_pretrained(model_id)
inputs = tokenizer("Hola, mi nombre es", return_tensors="pt")

outputs = model.generate(**inputs, max_new_tokens=20)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Limitations

El modelo Sermental Instruct 7.3B es una demostración rápida de que el modelo base se puede ajustar fácilmente para lograr un rendimiento convincente. No tiene ningún mecanismo de moderación. Esperamos interactuar con la comunidad en formas de Haga que el modelo respete finamente las barreras de protección, lo que permite la implementación en entornos que requieren salidas moderadas.

Downloads last month: -

You need to agree to share your contact information to access this model

Model Card for Sermental-Instruct-7.3B

Download

Generate with transformers

Limitations

Generate with `transformers`