Instructions to use geralt/MechDistilGPT2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use geralt/MechDistilGPT2 with Transformers:

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

pipe = pipeline("text-generation", model="geralt/MechDistilGPT2")

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

tokenizer = AutoTokenizer.from_pretrained("geralt/MechDistilGPT2")
model = AutoModelForCausalLM.from_pretrained("geralt/MechDistilGPT2", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use geralt/MechDistilGPT2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "geralt/MechDistilGPT2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "geralt/MechDistilGPT2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/geralt/MechDistilGPT2

SGLang

How to use geralt/MechDistilGPT2 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 "geralt/MechDistilGPT2" \
    --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": "geralt/MechDistilGPT2",
		"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 "geralt/MechDistilGPT2" \
        --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": "geralt/MechDistilGPT2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use geralt/MechDistilGPT2 with Docker Model Runner:
```
docker model run hf.co/geralt/MechDistilGPT2
```

witcher commited on Jul 29, 2021

Commit

ae0fc7b

1 Parent(s): 55aa619

Update README.md

Browse files

Files changed (1) hide show

README.md +9 -9

README.md CHANGED Viewed

@@ -4,14 +4,14 @@ This model is fine-tuned on 200k text scraped from Mechanical/Automotive pdf boo
 Base model is DistilGPT2(https://huggingface.co/gpt2) (the smallest version of GPT2)
 ## Fine-Tuning
-Default Training Args
-Epochs = 3
-Perplexity = 48
-Training set = 200k sentences
-Validation set = 40k sentences
 ## Framework versions
-Transformers 4.7.0.dev0
-Pytorch 1.8.1+cu111
-Datasets 1.6.2
-Tokenizers 0.10.2

 Base model is DistilGPT2(https://huggingface.co/gpt2) (the smallest version of GPT2)
 ## Fine-Tuning
+* Default Training Args
+* Epochs = 3
+* Perplexity = 48
+* Training set = 200k sentences
+* Validation set = 40k sentences
 ## Framework versions
+* Transformers 4.7.0.dev0
+* Pytorch 1.8.1+cu111
+* Datasets 1.6.2
+* Tokenizers 0.10.2