Instructions to use readerbench/RoGPT2-medium with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use readerbench/RoGPT2-medium with Transformers:

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

pipe = pipeline("text-generation", model="readerbench/RoGPT2-medium")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("readerbench/RoGPT2-medium")
model = AutoModelForCausalLM.from_pretrained("readerbench/RoGPT2-medium")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use readerbench/RoGPT2-medium with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "readerbench/RoGPT2-medium"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "readerbench/RoGPT2-medium",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/readerbench/RoGPT2-medium

SGLang

How to use readerbench/RoGPT2-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 "readerbench/RoGPT2-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": "readerbench/RoGPT2-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 "readerbench/RoGPT2-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": "readerbench/RoGPT2-medium",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use readerbench/RoGPT2-medium with Docker Model Runner:
```
docker model run hf.co/readerbench/RoGPT2-medium
```

ReaderBench commited on Jul 22, 2021

Commit

f0587eb

1 Parent(s): fb77fbb

update readme

Browse files

Files changed (1) hide show

README.md +3 -3

README.md CHANGED Viewed

@@ -52,7 +52,7 @@ print(tokenizer.decode(text[0]))
 ### Training Statistics
-| Version | Number of parameters | Number of epoch | Duration of an epoch | Block size | Batch size | PPL |
 |:-------:|:--------------------:|:---------------:|:--------------------:|:----------:|:----------:|:---:|
 | Base   | 124M | 15 | 7h      | 1024 | 72 | 22.96    |
 | Medium | 354M | 10 | 22h     | 1024 | 24 | 17.64    |
@@ -125,8 +125,8 @@ print(tokenizer.decode(text[0]))
 |RoBERT-small  | -             | 30.84 | 45.17    |
 |RoBERT-base   | -             | 53.52 | 70.04    |
 |RoBERT-large  | -             | 55.46 |  69.64   |
-|mBERT         | -             | 72.7  | 59.9     |
-|XLM-R Large   | -             |**83.6**|**69.7**|
 |RoGPT2-base   |  Greedy       | 23.69 | 35.97    |
 |RoGPT2-base   | Beam-search-4 | 24.11 | 35.27    |
 |RoGPT2-medium | Greedy        | 29.66 | 44.74    |

 ### Training Statistics
+| Version | Number of parameters | Number of epoch | Duration of an epoch | Context size | Batch size | PPL |
 |:-------:|:--------------------:|:---------------:|:--------------------:|:----------:|:----------:|:---:|
 | Base   | 124M | 15 | 7h      | 1024 | 72 | 22.96    |
 | Medium | 354M | 10 | 22h     | 1024 | 24 | 17.64    |
 |RoBERT-small  | -             | 30.84 | 45.17    |
 |RoBERT-base   | -             | 53.52 | 70.04    |
 |RoBERT-large  | -             | 55.46 |  69.64   |
+|mBERT         | -             | 59.9  |  72.7  |
+|XLM-R Large   | -             |**69.7** |**83.6** |
 |RoGPT2-base   |  Greedy       | 23.69 | 35.97    |
 |RoGPT2-base   | Beam-search-4 | 24.11 | 35.27    |
 |RoGPT2-medium | Greedy        | 29.66 | 44.74    |