Instructions to use imvshal09/llama-3.2-3b-Brompt with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use imvshal09/llama-3.2-3b-Brompt with Transformers:

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

pipe = pipeline("text-generation", model="imvshal09/llama-3.2-3b-Brompt")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("imvshal09/llama-3.2-3b-Brompt")
model = AutoModelForCausalLM.from_pretrained("imvshal09/llama-3.2-3b-Brompt", 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 imvshal09/llama-3.2-3b-Brompt with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "imvshal09/llama-3.2-3b-Brompt"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "imvshal09/llama-3.2-3b-Brompt",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/imvshal09/llama-3.2-3b-Brompt

SGLang

How to use imvshal09/llama-3.2-3b-Brompt 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 "imvshal09/llama-3.2-3b-Brompt" \
    --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": "imvshal09/llama-3.2-3b-Brompt",
		"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 "imvshal09/llama-3.2-3b-Brompt" \
        --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": "imvshal09/llama-3.2-3b-Brompt",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use imvshal09/llama-3.2-3b-Brompt with Docker Model Runner:
```
docker model run hf.co/imvshal09/llama-3.2-3b-Brompt
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

This model was trained on Dataset: (https://huggingface.co/imvshal09/llama-3.2-3b-Brompt/blob/main/prompts.csv) PS: (I actually cannot remember where i got this dataset, if you know please let me know, so i can credit them!)

🦙 LLaMA 3.2 - 3B Brompt (GGUF)

This is a fine-tuned LLaMA 3.2 - 3B model designed to refine and enhance user prompts. It instantly makes prompts clearer, more detailed, and well-structured. The model is hosted on Hugging Face and can be used in Jan.

How to Use the Model in Jan

Step 1: Get the Model

You can download the GGUF model from Hugging Face:

👉 LLaMA 3.2 - 3B Brompt Q4_K_M (GGUF)

Step 2: Install Jan

To run the model in Jan, you need to install it first. Download Jan from the following link:

👉 Download Jan

Step 3: Import the Model in Jan

Open Jan.
Navigate to the Models section and select Import Model.
Upload the GGUF model file that you downloaded from Hugging Face.

Step 4: Set Instructions for the Model

For best results, provide the following instruction to the model:

You are a top-rated prompt-improving service bot named Brompt. 
Your task is to instantly refine and enhance user prompts by making them clearer, more detailed, and well-structured.

Downloads last month: 4

Safetensors

Model size

3B params

Tensor type

F16

Model tree for imvshal09/llama-3.2-3b-Brompt

Base model

meta-llama/Llama-3.2-3B-Instruct

Finetuned

(1962)

this model

Quantizations

1 model