Instructions to use DevsDoCode/LLama-3-8b-Uncensored-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DevsDoCode/LLama-3-8b-Uncensored-4bit with Transformers:

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

pipe = pipeline("text-generation", model="DevsDoCode/LLama-3-8b-Uncensored-4bit")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("DevsDoCode/LLama-3-8b-Uncensored-4bit")
model = AutoModelForCausalLM.from_pretrained("DevsDoCode/LLama-3-8b-Uncensored-4bit", 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 DevsDoCode/LLama-3-8b-Uncensored-4bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "DevsDoCode/LLama-3-8b-Uncensored-4bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DevsDoCode/LLama-3-8b-Uncensored-4bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/DevsDoCode/LLama-3-8b-Uncensored-4bit

SGLang

How to use DevsDoCode/LLama-3-8b-Uncensored-4bit 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 "DevsDoCode/LLama-3-8b-Uncensored-4bit" \
    --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": "DevsDoCode/LLama-3-8b-Uncensored-4bit",
		"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 "DevsDoCode/LLama-3-8b-Uncensored-4bit" \
        --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": "DevsDoCode/LLama-3-8b-Uncensored-4bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Desktop
Docker Model Runner
How to use DevsDoCode/LLama-3-8b-Uncensored-4bit with Docker Model Runner:
```
docker model run hf.co/DevsDoCode/LLama-3-8b-Uncensored-4bit
```

config.json

by john-no-code - opened May 7, 2024

Discussion

john-no-code

May 7, 2024

Hi there,

I was just testing a model via the URL https://huggingface.co/DevsDoCode/LLama-3-8b-Uncensored-4bit by typing a random message into the text box labeled "Input a message to start chatting with DevsDoCode/LLama-3-8b-Uncensored-4bit."

After sending the message, an error occurred indicating that the file "config.json" for the model "unsloth/llama-3-8b-bnb-4bit" could not be found. The path where Gradio is searching for the file is: https://huggingface.co/unsloth/llama-3-8b-bnb-4bit/resolve/nonono/config.json

Could you please verify if the file "config.json" is available at this location? It seems to be essential for loading the model correctly.

Thank you for your assistance!

Best regards,
John

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment