Instructions to use rajpurkar/distilgpt2-squad with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use rajpurkar/distilgpt2-squad with Transformers:

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

pipe = pipeline("text-generation", model="rajpurkar/distilgpt2-squad")

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

tokenizer = AutoTokenizer.from_pretrained("rajpurkar/distilgpt2-squad")
model = AutoModelForCausalLM.from_pretrained("rajpurkar/distilgpt2-squad", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use rajpurkar/distilgpt2-squad with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "rajpurkar/distilgpt2-squad"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "rajpurkar/distilgpt2-squad",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/rajpurkar/distilgpt2-squad

SGLang

How to use rajpurkar/distilgpt2-squad 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 "rajpurkar/distilgpt2-squad" \
    --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": "rajpurkar/distilgpt2-squad",
		"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 "rajpurkar/distilgpt2-squad" \
        --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": "rajpurkar/distilgpt2-squad",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use rajpurkar/distilgpt2-squad with Docker Model Runner:
```
docker model run hf.co/rajpurkar/distilgpt2-squad
```

rajpurkar commited on Sep 20, 2022

Commit

916b25d

1 Parent(s): 5f16e15

add model

Browse files

Files changed (7) hide show

.gitignore +1 -0
merges.txt +0 -0
pytorch_model.bin +1 -1
special_tokens_map.json +5 -0
tokenizer.json +0 -0
tokenizer_config.json +10 -0
vocab.json +0 -0

.gitignore ADDED Viewed

	@@ -0,0 +1 @@


1	+ checkpoint-*/

merges.txt ADDED Viewed

The diff for this file is too large to render. See raw diff

pytorch_model.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:580c02e11f5032b47ddff2d36ea8045b1c1f41cb317668c18d2e9bb12749ec0a
 size 333968953

 version https://git-lfs.github.com/spec/v1
+oid sha256:484c96c9aa1150fc208627d1ad53f23fdb82a7c04bc1e2095f2753c6f5405fa4
 size 333968953

special_tokens_map.json ADDED Viewed

	@@ -0,0 +1,5 @@

+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer.json ADDED Viewed

The diff for this file is too large to render. See raw diff

tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,10 @@

+{
+  "add_prefix_space": false,
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1024,
+  "name_or_path": "distilgpt2",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

vocab.json ADDED Viewed

The diff for this file is too large to render. See raw diff