Instructions to use kiri-ai/gpt2-large-quantized with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kiri-ai/gpt2-large-quantized with Transformers:

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

pipe = pipeline("text-generation", model="kiri-ai/gpt2-large-quantized")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("kiri-ai/gpt2-large-quantized")
model = AutoModelForCausalLM.from_pretrained("kiri-ai/gpt2-large-quantized")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use kiri-ai/gpt2-large-quantized with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/kiri-ai/gpt2-large-quantized

SGLang

How to use kiri-ai/gpt2-large-quantized 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 "kiri-ai/gpt2-large-quantized" \
    --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": "kiri-ai/gpt2-large-quantized",
		"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 "kiri-ai/gpt2-large-quantized" \
        --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": "kiri-ai/gpt2-large-quantized",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use kiri-ai/gpt2-large-quantized with Docker Model Runner:
```
docker model run hf.co/kiri-ai/gpt2-large-quantized
```

What transformers version should I use to load this model?

by apivovarov - opened Feb 16, 2023

Discussion

apivovarov

Feb 16, 2023

Error:

>>> model = torch.load("pytorch_model_quantized.bin")
Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
  File "/usr/local/lib/python3.8/dist-packages/torch/serialization.py", line 789, in load
    return _load(opened_zipfile, map_location, pickle_module, **pickle_load_args)
  File "/usr/local/lib/python3.8/dist-packages/torch/serialization.py", line 1131, in _load
    result = unpickler.load()
  File "/usr/local/lib/python3.8/dist-packages/torch/serialization.py", line 1124, in find_class
    return super().find_class(mod_name, name)
AttributeError: Can't get attribute 'Block' on <module 'transformers.models.gpt2.modeling_gpt2' from '/usr/local/lib/python3.8/dist-packages/transformers/models/gpt2/modeling_gpt2.py'>

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment