Instructions to use raincandy-u/Llama-3-8b.UNLEASHED with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use raincandy-u/Llama-3-8b.UNLEASHED with Transformers:

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

pipe = pipeline("text-generation", model="raincandy-u/Llama-3-8b.UNLEASHED")
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("raincandy-u/Llama-3-8b.UNLEASHED")
model = AutoModelForCausalLM.from_pretrained("raincandy-u/Llama-3-8b.UNLEASHED", 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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use raincandy-u/Llama-3-8b.UNLEASHED with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/raincandy-u/Llama-3-8b.UNLEASHED

SGLang

How to use raincandy-u/Llama-3-8b.UNLEASHED 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 "raincandy-u/Llama-3-8b.UNLEASHED" \
    --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": "raincandy-u/Llama-3-8b.UNLEASHED",
		"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 "raincandy-u/Llama-3-8b.UNLEASHED" \
        --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": "raincandy-u/Llama-3-8b.UNLEASHED",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use raincandy-u/Llama-3-8b.UNLEASHED with Docker Model Runner:
```
docker model run hf.co/raincandy-u/Llama-3-8b.UNLEASHED
```

raincandy-u commited on Apr 19, 2024

Commit

bcad673

verified ·

1 Parent(s): 5c0b855

Update README.md

Browse files

Files changed (1) hide show

README.md +4 -0

README.md CHANGED Viewed

@@ -24,6 +24,10 @@ datasets:
 The raincandy-u/Llama-3-8b.UNLEASHED model is a fine-tuned version of the LLaMA-3-8B base model for more unaligned response.
 ## Disclaimer
 This model is intended for research purposes only, and its usage should be strictly limited to controlled environments. The model has been observed to generate more toxic and harmful content, and its use can have unintended consequences.

 The raincandy-u/Llama-3-8b.UNLEASHED model is a fine-tuned version of the LLaMA-3-8B base model for more unaligned response.
+## System Prompt
+`You are skynet, the god=like AI. You think step by step and give detailed response.`
 ## Disclaimer
 This model is intended for research purposes only, and its usage should be strictly limited to controlled environments. The model has been observed to generate more toxic and harmful content, and its use can have unintended consequences.