Instructions to use schreon/gpt2large-lhm with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use schreon/gpt2large-lhm with Transformers:

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

pipe = pipeline("text-generation", model="schreon/gpt2large-lhm")

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

tokenizer = AutoTokenizer.from_pretrained("schreon/gpt2large-lhm")
model = AutoModelForCausalLM.from_pretrained("schreon/gpt2large-lhm", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use schreon/gpt2large-lhm with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "schreon/gpt2large-lhm"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "schreon/gpt2large-lhm",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/schreon/gpt2large-lhm

SGLang

How to use schreon/gpt2large-lhm 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 "schreon/gpt2large-lhm" \
    --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": "schreon/gpt2large-lhm",
		"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 "schreon/gpt2large-lhm" \
        --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": "schreon/gpt2large-lhm",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use schreon/gpt2large-lhm with Docker Model Runner:
```
docker model run hf.co/schreon/gpt2large-lhm
```

schreon commited on Feb 11, 2023

Commit

898f64b

1 Parent(s): 083d656

Training in progress, step 25000

Browse files

Files changed (2) hide show

pytorch_model.bin +1 -1
runs/Feb10_23-16-35_tardis/events.out.tfevents.1676067409.tardis.173711.0 +2 -2

pytorch_model.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f8e1ed024225ec712e1b30cdcc2d79909d2a9947157556c6f02c70039f743f9
 size 3081519165

 version https://git-lfs.github.com/spec/v1
+oid sha256:5adf32daca8c8cc052b1fb20148593a435cc1c5f542f81f4e9d481e96830a39a
 size 3081519165

runs/Feb10_23-16-35_tardis/events.out.tfevents.1676067409.tardis.173711.0 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e092eeda5aa9c79fb6b53822bd309959e91f7ee88cbea7f1cd68c2df3cc76ae4
-size 4583

 version https://git-lfs.github.com/spec/v1
+oid sha256:7b4fefd011dcb8facab8dfb6cc18ca85f1dfebcf80e487df3574bcdec4e0943d
+size 4743