Instructions to use dingzhaohan/gpt2-wikitext2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use dingzhaohan/gpt2-wikitext2 with Transformers:

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

pipe = pipeline("text-generation", model="dingzhaohan/gpt2-wikitext2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("dingzhaohan/gpt2-wikitext2")
model = AutoModelForCausalLM.from_pretrained("dingzhaohan/gpt2-wikitext2")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use dingzhaohan/gpt2-wikitext2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "dingzhaohan/gpt2-wikitext2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "dingzhaohan/gpt2-wikitext2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/dingzhaohan/gpt2-wikitext2

SGLang

How to use dingzhaohan/gpt2-wikitext2 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 "dingzhaohan/gpt2-wikitext2" \
    --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": "dingzhaohan/gpt2-wikitext2",
		"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 "dingzhaohan/gpt2-wikitext2" \
        --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": "dingzhaohan/gpt2-wikitext2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use dingzhaohan/gpt2-wikitext2 with Docker Model Runner:
```
docker model run hf.co/dingzhaohan/gpt2-wikitext2
```

dingzhaohan commited on Apr 13, 2023

Commit

a7a7e33

1 Parent(s): 7bb242b

End of training

Browse files

Files changed (4) hide show

generation_config.json +6 -0
pytorch_model.bin +1 -1
runs/Apr13_09-43-18_bohrium-157-1012591/events.out.tfevents.1681350206.bohrium-157-1012591.2686.0 +2 -2
runs/Apr13_09-43-18_bohrium-157-1012591/events.out.tfevents.1681351039.bohrium-157-1012591.2686.2 +3 -0

generation_config.json ADDED Viewed

	@@ -0,0 +1,6 @@

+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.27.4"
+}

pytorch_model.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94e77a19de7d29aa4c3ee80c3c158cb098e15fbc407e03f536f05b731ae47e5c
 size 510398013

 version https://git-lfs.github.com/spec/v1
+oid sha256:261285feb3497ed37f545418d1d67570d0bcefe3ac9150d34add75155cce92d6
 size 510398013

runs/Apr13_09-43-18_bohrium-157-1012591/events.out.tfevents.1681350206.bohrium-157-1012591.2686.0 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e552377dff6906f738e5aaf59beb70e5c256046ee7ecdc4015765682d75fbc0f
-size 6262

 version https://git-lfs.github.com/spec/v1
+oid sha256:8f42345d52c7be0dfc501a0f26ea1e428e4641dbcb17ce6a653dd269ca5d2e41
+size 7358

runs/Apr13_09-43-18_bohrium-157-1012591/events.out.tfevents.1681351039.bohrium-157-1012591.2686.2 ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:9f31ba945fa68f637e47148b2cde22a555c800bae34759bfc4d208a5311bd1ab
+size 311