Instructions to use TheBloke/Llama-2-70B-Chat-GPTQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TheBloke/Llama-2-70B-Chat-GPTQ with Transformers:

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

pipe = pipeline("text-generation", model="TheBloke/Llama-2-70B-Chat-GPTQ")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TheBloke/Llama-2-70B-Chat-GPTQ")
model = AutoModelForCausalLM.from_pretrained("TheBloke/Llama-2-70B-Chat-GPTQ", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use TheBloke/Llama-2-70B-Chat-GPTQ with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TheBloke/Llama-2-70B-Chat-GPTQ"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TheBloke/Llama-2-70B-Chat-GPTQ",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/TheBloke/Llama-2-70B-Chat-GPTQ

SGLang

How to use TheBloke/Llama-2-70B-Chat-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 "TheBloke/Llama-2-70B-Chat-GPTQ" \
    --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": "TheBloke/Llama-2-70B-Chat-GPTQ",
		"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 "TheBloke/Llama-2-70B-Chat-GPTQ" \
        --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": "TheBloke/Llama-2-70B-Chat-GPTQ",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use TheBloke/Llama-2-70B-Chat-GPTQ with Docker Model Runner:
```
docker model run hf.co/TheBloke/Llama-2-70B-Chat-GPTQ
```

Inference time with TGI

#15

by jacktenyx - opened Jul 23, 2023

Discussion

jacktenyx

Jul 23, 2023

Thanks for posting this model, I was able to run inference with TGI on a single 40 GB A100 with the following command:

docker run \
    -p 8080:80 \
    -e GPTQ_BITS=4 \
    -e GPTQ_GROUPSIZE=1 \
    --gpus all \
    --shm-size 5g \
    -v $volume:/data ghcr.io/huggingface/text-generation-inference:latest \
    --model-id TheBloke/Llama-2-70B-chat-GPTQ \
    --max-input-length 4096 \
    --max-total-tokens 8192 \
    --quantize gptq \
    --sharded false

This was able to generate a response at 225ms/token. However, when running the unquantized model sharded across 4 A100s I was able to get around 45ms/token. Am I missing a config or environment variable that would improve the inference time or is this expected behavior with this quantization?

phucdoitoan

Sep 19, 2023

I get the same number of latency (>100ms/ toekn) with half the length for input and total_tokens. It even slower than using quantization with bitsandbytes-nf4 (~51 ms/token).
This is weird as it is said that gptq is faster for inference than bitsandbytes.
...

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