Instructions to use gameofdimension/cs324-length-control with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use gameofdimension/cs324-length-control with Transformers:

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

pipe = pipeline("text-generation", model="gameofdimension/cs324-length-control")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("gameofdimension/cs324-length-control")
model = AutoModelForCausalLM.from_pretrained("gameofdimension/cs324-length-control")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use gameofdimension/cs324-length-control with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "gameofdimension/cs324-length-control"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "gameofdimension/cs324-length-control",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/gameofdimension/cs324-length-control

SGLang

How to use gameofdimension/cs324-length-control 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 "gameofdimension/cs324-length-control" \
    --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": "gameofdimension/cs324-length-control",
		"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 "gameofdimension/cs324-length-control" \
        --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": "gameofdimension/cs324-length-control",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use gameofdimension/cs324-length-control with Docker Model Runner:
```
docker model run hf.co/gameofdimension/cs324-length-control
```

gameofdimension commited on Jun 26, 2023

Commit

76accc1

1 Parent(s): 8654d62

Training in progress, step 10000

Browse files

Files changed (2) hide show

pytorch_model.bin +1 -1
runs/Jun26_09-19-33_83a2afccd378/events.out.tfevents.1687771175.83a2afccd378.3562.1 +2 -2

pytorch_model.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9c4f4d631a099a1679ec693676b14262f68b093e7e86fe7f054d23243953138
 size 497807197

 version https://git-lfs.github.com/spec/v1
+oid sha256:03071b4abace230cbfdb2e469cc4ead16ad2aae16d621dc3c9e12cb2c438d95b
 size 497807197

runs/Jun26_09-19-33_83a2afccd378/events.out.tfevents.1687771175.83a2afccd378.3562.1 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf84d7e51effb8db1b0f4d7941105f8e127c4dd6f61cf93966e2d52b1d08d3b9
-size 4692

 version https://git-lfs.github.com/spec/v1
+oid sha256:de615aeaefb23a82f31f7b8cd7fef9b58db12d673c220729a5ef2d7aa8500c97
+size 5120