Text Generation
Transformers
PyTorch
TensorFlow
JAX
LiteRT
Rust
Core ML
Safetensors
English
gpt2
exbert
Eval Results (legacy)
text-generation-inference
Instructions to use distilbert/distilgpt2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use distilbert/distilgpt2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="distilbert/distilgpt2")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("distilbert/distilgpt2") model = AutoModelForCausalLM.from_pretrained("distilbert/distilgpt2", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use distilbert/distilgpt2 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "distilbert/distilgpt2" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "distilbert/distilgpt2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/distilbert/distilgpt2
- SGLang
How to use distilbert/distilgpt2 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 "distilbert/distilgpt2" \ --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": "distilbert/distilgpt2", "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 "distilbert/distilgpt2" \ --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": "distilbert/distilgpt2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use distilbert/distilgpt2 with Docker Model Runner:
docker model run hf.co/distilbert/distilgpt2
Update README.md
Browse filesThe DistilGPT2 model is truly impressive in its efficiency and performance. We would love to contribute by updating the README to include detailed information about the base model, GPT-2. This addition will help address the current gap in the model card and provide users with a more comprehensive understanding of the model's origins.
README.md
CHANGED
|
@@ -2,26 +2,25 @@
|
|
| 2 |
language: en
|
| 3 |
tags:
|
| 4 |
- exbert
|
| 5 |
-
|
| 6 |
license: apache-2.0
|
| 7 |
datasets:
|
| 8 |
- openwebtext
|
| 9 |
-
|
| 10 |
model-index:
|
| 11 |
- name: distilgpt2
|
| 12 |
results:
|
| 13 |
-
- task:
|
| 14 |
type: text-generation
|
| 15 |
name: Text Generation
|
| 16 |
dataset:
|
| 17 |
type: wikitext
|
| 18 |
name: WikiText-103
|
| 19 |
metrics:
|
| 20 |
-
|
| 21 |
-
|
| 22 |
-
|
| 23 |
-
|
| 24 |
co2_eq_emissions: 149200
|
|
|
|
|
|
|
| 25 |
---
|
| 26 |
|
| 27 |
# DistilGPT2
|
|
@@ -179,4 +178,4 @@ The creators of DistilGPT2 [report](https://github.com/huggingface/transformers/
|
|
| 179 |
|
| 180 |
<a href="https://huggingface.co/exbert/?model=distilgpt2">
|
| 181 |
<img width="300px" src="https://cdn-media.huggingface.co/exbert/button.png">
|
| 182 |
-
</a>
|
|
|
|
| 2 |
language: en
|
| 3 |
tags:
|
| 4 |
- exbert
|
|
|
|
| 5 |
license: apache-2.0
|
| 6 |
datasets:
|
| 7 |
- openwebtext
|
|
|
|
| 8 |
model-index:
|
| 9 |
- name: distilgpt2
|
| 10 |
results:
|
| 11 |
+
- task:
|
| 12 |
type: text-generation
|
| 13 |
name: Text Generation
|
| 14 |
dataset:
|
| 15 |
type: wikitext
|
| 16 |
name: WikiText-103
|
| 17 |
metrics:
|
| 18 |
+
- type: perplexity
|
| 19 |
+
name: Perplexity
|
| 20 |
+
value: 21.1
|
|
|
|
| 21 |
co2_eq_emissions: 149200
|
| 22 |
+
base_model:
|
| 23 |
+
- openai-community/gpt2
|
| 24 |
---
|
| 25 |
|
| 26 |
# DistilGPT2
|
|
|
|
| 178 |
|
| 179 |
<a href="https://huggingface.co/exbert/?model=distilgpt2">
|
| 180 |
<img width="300px" src="https://cdn-media.huggingface.co/exbert/button.png">
|
| 181 |
+
</a>
|