Instructions to use failspy/Meta-Llama-3-8B-Instruct-abliterated-v3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use failspy/Meta-Llama-3-8B-Instruct-abliterated-v3 with Transformers:

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

pipe = pipeline("text-generation", model="failspy/Meta-Llama-3-8B-Instruct-abliterated-v3")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("failspy/Meta-Llama-3-8B-Instruct-abliterated-v3")
model = AutoModelForCausalLM.from_pretrained("failspy/Meta-Llama-3-8B-Instruct-abliterated-v3", 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 failspy/Meta-Llama-3-8B-Instruct-abliterated-v3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "failspy/Meta-Llama-3-8B-Instruct-abliterated-v3"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "failspy/Meta-Llama-3-8B-Instruct-abliterated-v3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/failspy/Meta-Llama-3-8B-Instruct-abliterated-v3

SGLang

How to use failspy/Meta-Llama-3-8B-Instruct-abliterated-v3 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 "failspy/Meta-Llama-3-8B-Instruct-abliterated-v3" \
    --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": "failspy/Meta-Llama-3-8B-Instruct-abliterated-v3",
		"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 "failspy/Meta-Llama-3-8B-Instruct-abliterated-v3" \
        --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": "failspy/Meta-Llama-3-8B-Instruct-abliterated-v3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use failspy/Meta-Llama-3-8B-Instruct-abliterated-v3 with Docker Model Runner:
```
docker model run hf.co/failspy/Meta-Llama-3-8B-Instruct-abliterated-v3
```

Possibly missing files

by ayyylol - opened May 21, 2024

Discussion

ayyylol

May 21, 2024

Hi @failspy ,

Let me start off by thanking you so much for this.
I really enjoyed the first 2 versions too and I appreciate all your work.

I was also wondering if it's possible that this repo is missing some files? I believe the tokenizer maybe and some other files.
Thank you!

failspy

Owner May 21, 2024

Ah, yeah, appears to be. For what its worth, the tokenizer model is the same as Llama-3-8B-Instruct, so if you have those files locally available, you can copy paste them and they should just work. But thanks for pointing this out, will add them to the repo ASAP

ayyylol

May 21, 2024

Thank you very much!

failspy

Owner May 22, 2024

Published.

failspy changed discussion status to closed May 22, 2024

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