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

Libraries

How to use openai-community/gpt2-medium with Transformers:

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

pipe = pipeline("text-generation", model="openai-community/gpt2-medium")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("openai-community/gpt2-medium")
model = AutoModelForCausalLM.from_pretrained("openai-community/gpt2-medium")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use openai-community/gpt2-medium with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/openai-community/gpt2-medium

SGLang

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

Docker Model Runner
How to use openai-community/gpt2-medium with Docker Model Runner:
```
docker model run hf.co/openai-community/gpt2-medium
```

Add Core ML conversion

#11

by Harissam - opened Aug 23, 2023

base: refs/heads/main

←

from: refs/pr/11

Discussion Files changed

+27085

-0

Files changed (3) hide show

coreml/text-generation/float32_model.mlpackage/Data/com.apple.CoreML/model.mlmodel +0 -0
coreml/text-generation/float32_model.mlpackage/Data/com.apple.CoreML/weights/weight.bin +3 -0
coreml/text-generation/float32_model.mlpackage/Manifest.json +18 -0

coreml/text-generation/float32_model.mlpackage/Data/com.apple.CoreML/model.mlmodel ADDED Viewed

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

coreml/text-generation/float32_model.mlpackage/Data/com.apple.CoreML/weights/weight.bin ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:8c4de82799a4c0c7801af172e85adf3580fa104f9ed399bc50cc7de754c2ea45
+size 1416891140

coreml/text-generation/float32_model.mlpackage/Manifest.json ADDED Viewed

	@@ -0,0 +1,18 @@

+{
+    "fileFormatVersion": "1.0.0",
+    "itemInfoEntries": {
+        "5A483B09-08D6-458C-B9B0-2867E47672EB": {
+            "author": "com.apple.CoreML",
+            "description": "CoreML Model Weights",
+            "name": "weights",
+            "path": "com.apple.CoreML/weights"
+        },
+        "FCB106B2-2F91-49B4-BF63-B253B98E2BEB": {
+            "author": "com.apple.CoreML",
+            "description": "CoreML Model Specification",
+            "name": "model.mlmodel",
+            "path": "com.apple.CoreML/model.mlmodel"
+        }
+    },
+    "rootModelIdentifier": "FCB106B2-2F91-49B4-BF63-B253B98E2BEB"
+}