Instructions to use rewicks/monolingual_de_8k-shared_ep2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use rewicks/monolingual_de_8k-shared_ep2 with Transformers:

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

pipe = pipeline("text-generation", model="rewicks/monolingual_de_8k-shared_ep2")

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

tokenizer = AutoTokenizer.from_pretrained("rewicks/monolingual_de_8k-shared_ep2")
model = AutoModelForCausalLM.from_pretrained("rewicks/monolingual_de_8k-shared_ep2", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use rewicks/monolingual_de_8k-shared_ep2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "rewicks/monolingual_de_8k-shared_ep2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "rewicks/monolingual_de_8k-shared_ep2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/rewicks/monolingual_de_8k-shared_ep2

SGLang

How to use rewicks/monolingual_de_8k-shared_ep2 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 "rewicks/monolingual_de_8k-shared_ep2" \
    --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": "rewicks/monolingual_de_8k-shared_ep2",
		"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 "rewicks/monolingual_de_8k-shared_ep2" \
        --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": "rewicks/monolingual_de_8k-shared_ep2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use rewicks/monolingual_de_8k-shared_ep2 with Docker Model Runner:
```
docker model run hf.co/rewicks/monolingual_de_8k-shared_ep2
```

rewicks commited on Nov 6, 2024

Commit

00b4c2d

verified ·

1 Parent(s): fd54986

Upload model.safetensors with huggingface_hub

Browse files

Files changed (1) hide show

model.safetensors +2 -2

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dff7341d9275ea6d21702966fec0314a400f71c07397ddb5e282aca8cd52d0af
-size 1242943848

 version https://git-lfs.github.com/spec/v1
+oid sha256:887c3a555edbbff4fee698d68e957592986735f57af7b2b6023caec46d83690d
+size 1242975928