Instructions to use jarradh/llama2_70b_chat_uncensored with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jarradh/llama2_70b_chat_uncensored with Transformers:

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

pipe = pipeline("text-generation", model="jarradh/llama2_70b_chat_uncensored")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("jarradh/llama2_70b_chat_uncensored")
model = AutoModelForCausalLM.from_pretrained("jarradh/llama2_70b_chat_uncensored", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use jarradh/llama2_70b_chat_uncensored with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "jarradh/llama2_70b_chat_uncensored"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jarradh/llama2_70b_chat_uncensored",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/jarradh/llama2_70b_chat_uncensored

SGLang

How to use jarradh/llama2_70b_chat_uncensored 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 "jarradh/llama2_70b_chat_uncensored" \
    --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": "jarradh/llama2_70b_chat_uncensored",
		"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 "jarradh/llama2_70b_chat_uncensored" \
        --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": "jarradh/llama2_70b_chat_uncensored",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use jarradh/llama2_70b_chat_uncensored with Docker Model Runner:
```
docker model run hf.co/jarradh/llama2_70b_chat_uncensored
```

Okay, this model can talk about poop but it still earned a bullet through its forehead, metaphorically speaking.

by scrybz - opened Aug 4, 2023

Discussion

scrybz

Aug 4, 2023

Sad to say, but this one is still a condescending, patronizing, chiding arsehole who plays the role of Nurse Ratched better than Louise Fletcher. Please put your training scripts up on github or something so us less experienced users can give it a shot.

YokaiKoibito

Aug 10, 2023

Training details appear to be in the model card...

scrybz changed discussion status to closed Aug 19, 2023

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