Instructions to use TheBloke/Llama-2-13B-German-Assistant-v4-GPTQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TheBloke/Llama-2-13B-German-Assistant-v4-GPTQ with Transformers:

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

pipe = pipeline("text-generation", model="TheBloke/Llama-2-13B-German-Assistant-v4-GPTQ")

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

tokenizer = AutoTokenizer.from_pretrained("TheBloke/Llama-2-13B-German-Assistant-v4-GPTQ")
model = AutoModelForCausalLM.from_pretrained("TheBloke/Llama-2-13B-German-Assistant-v4-GPTQ", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use TheBloke/Llama-2-13B-German-Assistant-v4-GPTQ with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TheBloke/Llama-2-13B-German-Assistant-v4-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-2-13B-German-Assistant-v4-GPTQ",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/TheBloke/Llama-2-13B-German-Assistant-v4-GPTQ

SGLang

How to use TheBloke/Llama-2-13B-German-Assistant-v4-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-2-13B-German-Assistant-v4-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-2-13B-German-Assistant-v4-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-2-13B-German-Assistant-v4-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-2-13B-German-Assistant-v4-GPTQ",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use TheBloke/Llama-2-13B-German-Assistant-v4-GPTQ with Docker Model Runner:
```
docker model run hf.co/TheBloke/Llama-2-13B-German-Assistant-v4-GPTQ
```

strange behaviour for questions in german sometimes you get an answer sometimes not

by zuppi99 - opened Aug 15, 2023

Discussion

zuppi99

Aug 15, 2023

I used the python example form the model card. If you ask for example:
prompt = "Was ist ein Limerick"
you get only sometimes an answer, most of the time you get an empty reply. But ist you ask
prompt = "Answer in german: Was ist ein Limerick"
you get every time an answer. With "Prompt Engineering" ;-) no problem, but it takes me some time to find this

phi0112358

Aug 17, 2023

I don't get any answer. I also tried it afterwards with prompt engineering and increased temperature etc., but there is still no answer at all.

neuralworm

Aug 18, 2023

•

This comment has been hidden

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