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)

# pip install -U transformers accelerate
# 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=256)
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
```

DevsDoCode commited on Apr 19, 2024

Commit

2c3bb56

verified ·

1 Parent(s): 3e25282

Update README.md

Browse files

Files changed (1) hide show

README.md +13 -15

README.md CHANGED Viewed

@@ -10,6 +10,9 @@ tags:
 - llama-3
 ---
 # Finetune Meta Llama-3 8b to create an Uncensored Model with Devs Do Code!
 Unleash the power of uncensored text generation with our model! We've fine-tuned the Meta Llama-3 8b model to create an uncensored variant that pushes the boundaries of text generation.
@@ -33,21 +36,16 @@ model = GPT2LMHeadModel.from_pretrained(model_name)
 ```
 ## Social Media Handles
-- **Telegram:** [Insert Telegram Handle]
-- **YouTube:** [Insert YouTube Channel]
-- **Instagram:** [Insert Instagram Handle]
-- **LinkedIn:** [Insert LinkedIn Profile]
-- **Discord:** [Insert Discord Server Invite]
-- **Twitter:** [Insert Twitter Handle]
-## Contributors
-- Devs Do Code
-- Sreejan
-- OEvortex
-## Notebooks
-- **Finetuning Process:** [Google Colab Notebook](Insert Google Colab Link)
-- **Accessing the Model:** [Google Colab Notebook](Insert Google Colab Link)
-```
-Replace `[Insert ...]` with appropriate links and handles. Let me know if you need further modifications!

 - llama-3
 ---
+## Contributors
+![Contributors](https://raw.githubusercontent.com/unslothai/unsloth/main/images/contributors.png) **Devs Do Code**, **Sreejan**, **OEvortex**
 # Finetune Meta Llama-3 8b to create an Uncensored Model with Devs Do Code!
 Unleash the power of uncensored text generation with our model! We've fine-tuned the Meta Llama-3 8b model to create an uncensored variant that pushes the boundaries of text generation.
 ```
 ## Social Media Handles
+- **Telegram:** [Insert Telegram Handle](https://t.me/your_telegram_handle)
+- **YouTube:** [Insert YouTube Channel](https://www.youtube.com/your_channel)
+- **Instagram:** [Insert Instagram Handle](https://www.instagram.com/your_instagram_handle)
+- **LinkedIn:** [Insert LinkedIn Profile](https://www.linkedin.com/in/your_profile)
+- **Discord:** [Insert Discord Server Invite](https://discord.gg/your_server_invite)
+- **Twitter:** [Insert Twitter Handle](https://twitter.com/your_twitter_handle)
+## Notebooks
+- **Finetuning Process:** [▶️ Start on Colab](https://colab.research.google.com/drive/135ced7oHytdxu3N2DNe1Z0kqjyYIkDXp?usp=sharing)
+- **Accessing the Model:** [▶️ Start on Colab](https://colab.research.google.com/drive/135ced7oHytdxu3N2DNe1Z0kqjyYIkDXp?usp=sharing)