Instructions to use philschmid/instruct-igel-001 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use philschmid/instruct-igel-001 with Transformers:

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

pipe = pipeline("text-generation", model="philschmid/instruct-igel-001")

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

tokenizer = AutoTokenizer.from_pretrained("philschmid/instruct-igel-001")
model = AutoModelForCausalLM.from_pretrained("philschmid/instruct-igel-001", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use philschmid/instruct-igel-001 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "philschmid/instruct-igel-001"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "philschmid/instruct-igel-001",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/philschmid/instruct-igel-001

SGLang

How to use philschmid/instruct-igel-001 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 "philschmid/instruct-igel-001" \
    --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": "philschmid/instruct-igel-001",
		"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 "philschmid/instruct-igel-001" \
        --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": "philschmid/instruct-igel-001",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use philschmid/instruct-igel-001 with Docker Model Runner:
```
docker model run hf.co/philschmid/instruct-igel-001
```

philschmid commited on Apr 3, 2023

Commit

2b468fd

1 Parent(s): 74ce4a1

Update README.md

Browse files

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -12,7 +12,7 @@ widget:
 ---
 <div style="text-align:center;width:250px;height:250px;">
-    <img src="https://huggingface.co/philschmid/instruct-igel-001/resolve/main/assets/igel_removedbg.png" alt="IGEL logo"">
 </div>
@@ -23,7 +23,7 @@ IGEL is a LLM model family developed for German. The first version of IGEL is bu
 ### You can try out the model at [igel-playground]().
-The IGEL family includes instruction `instruct-igel-001` and `chat-igel-001` _coming soon_.
 ## Model Description

 ---
 <div style="text-align:center;width:250px;height:250px;">
+    <img src="https://huggingface.co/philschmid/instruct-igel-001/resolve/main/igel.jpeg" alt="IGEL logo"">
 </div>
 ### You can try out the model at [igel-playground]().
+The IGEL family includes `instruct-igel-001` and `chat-igel-001` _coming soon_.
 ## Model Description