Instructions to use cortecs/Llama-3-SauerkrautLM-70b-Instruct-GPTQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use cortecs/Llama-3-SauerkrautLM-70b-Instruct-GPTQ with Transformers:

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

pipe = pipeline("text-generation", model="cortecs/Llama-3-SauerkrautLM-70b-Instruct-GPTQ")
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("cortecs/Llama-3-SauerkrautLM-70b-Instruct-GPTQ")
model = AutoModelForCausalLM.from_pretrained("cortecs/Llama-3-SauerkrautLM-70b-Instruct-GPTQ", 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 cortecs/Llama-3-SauerkrautLM-70b-Instruct-GPTQ with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "cortecs/Llama-3-SauerkrautLM-70b-Instruct-GPTQ"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "cortecs/Llama-3-SauerkrautLM-70b-Instruct-GPTQ",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/cortecs/Llama-3-SauerkrautLM-70b-Instruct-GPTQ

SGLang

How to use cortecs/Llama-3-SauerkrautLM-70b-Instruct-GPTQ 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 "cortecs/Llama-3-SauerkrautLM-70b-Instruct-GPTQ" \
    --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": "cortecs/Llama-3-SauerkrautLM-70b-Instruct-GPTQ",
		"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 "cortecs/Llama-3-SauerkrautLM-70b-Instruct-GPTQ" \
        --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": "cortecs/Llama-3-SauerkrautLM-70b-Instruct-GPTQ",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use cortecs/Llama-3-SauerkrautLM-70b-Instruct-GPTQ with Docker Model Runner:
```
docker model run hf.co/cortecs/Llama-3-SauerkrautLM-70b-Instruct-GPTQ
```

Rename gptq_model-4bit-128g.safetensors to model.safetensors

by edgelesssys - opened Aug 13, 2024

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

-0

edgelesssys

Aug 13, 2024

Tools such as https://github.com/lm-sys/FastChat expect the model weights in certain naming schemes.
Not saying this is necessarily a good idea, but most models on HF seem to follow this scheme.
Do you think you can change it to make this model work out of the box with these tools?

Rename gptq_model-4bit-128g.safetensors to model.safetensorsa8e4130f

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

Tap or paste here to upload images

Ready to merge

This branch is ready to get merged automatically.

· Sign up or log in to comment