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

Libraries

How to use christopherastone/distilgpt2-proofs with Transformers:

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

pipe = pipeline("text-generation", model="christopherastone/distilgpt2-proofs")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use christopherastone/distilgpt2-proofs with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/christopherastone/distilgpt2-proofs

SGLang

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

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

christopherastone commited on Jul 2, 2021

Commit

4e7b9f1

1 Parent(s): aa584d4

Update README.md

Browse files

Added widget-text metadata

Files changed (1) hide show

README.md +7 -6

README.md CHANGED Viewed

@@ -1,12 +1,13 @@
 [DistilGPT2](https://huggingface.co/distilgpt2)  English language model fine-tuned on mathematical proofs extracted from [arXiv.org](https://arxiv.org) LaTeX sources from 1992 to 2020.
  Proofs have been cleaned up a bit. In particular, they use
  * `CITE` for any citation
  * `REF` for any reference
  * `MATH` for any LaTeX mathematical formula
- * `CASE:` for any `\\item` or labeled subcase.
- For text generation, I recommend prompts such as:
- * `Let MATH be given.`
- * `By the inductive hypothesis,`
- * `If MATH is a nonempty`

+---
+widget:
+- text: "Let MATH be given."
+- text: "If MATH is a nonempty"
+- text: "By the inductive hypothesis,"
+---
 [DistilGPT2](https://huggingface.co/distilgpt2)  English language model fine-tuned on mathematical proofs extracted from [arXiv.org](https://arxiv.org) LaTeX sources from 1992 to 2020.
  Proofs have been cleaned up a bit. In particular, they use
  * `CITE` for any citation
  * `REF` for any reference
  * `MATH` for any LaTeX mathematical formula
+ * `CASE:` for any `\item` or labeled subcase.