Instructions to use WilliamStar/eli5_clm-model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use WilliamStar/eli5_clm-model with Transformers:

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

pipe = pipeline("text-generation", model="WilliamStar/eli5_clm-model")

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

tokenizer = AutoTokenizer.from_pretrained("WilliamStar/eli5_clm-model")
model = AutoModelForCausalLM.from_pretrained("WilliamStar/eli5_clm-model", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use WilliamStar/eli5_clm-model with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "WilliamStar/eli5_clm-model"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "WilliamStar/eli5_clm-model",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/WilliamStar/eli5_clm-model

SGLang

How to use WilliamStar/eli5_clm-model 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 "WilliamStar/eli5_clm-model" \
    --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": "WilliamStar/eli5_clm-model",
		"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 "WilliamStar/eli5_clm-model" \
        --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": "WilliamStar/eli5_clm-model",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use WilliamStar/eli5_clm-model with Docker Model Runner:
```
docker model run hf.co/WilliamStar/eli5_clm-model
```

Anda Liang commited on Apr 27, 2024

Commit

aff475c

1 Parent(s): 698b80a

Training in progress, step 2000

Browse files

Files changed (2) hide show

pytorch_model.bin +1 -1
runs/Apr27_06-23-48_28a0b54bcdf0/events.out.tfevents.1714199034.28a0b54bcdf0.459.1 +2 -2

pytorch_model.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:714fd88f677b758af5310a210a31608b6997a939f12fdb64893ca42667825efa
 size 1472971290

 version https://git-lfs.github.com/spec/v1
+oid sha256:1ce562758504fdaeb8bca348a57a4f2d7eb2489c083a046158fea4c21c9f6312
 size 1472971290

runs/Apr27_06-23-48_28a0b54bcdf0/events.out.tfevents.1714199034.28a0b54bcdf0.459.1 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21d07a7920bd3cda5b885bd936ce1f3c3e69a8a069420da7e4c1d119b6766b74
-size 7217

 version https://git-lfs.github.com/spec/v1
+oid sha256:8ca22f6ecf69a662c47e5fc1aa5586c6b0bb4a803d817a88f056c9e1a92fed8d
+size 7374