Instructions to use michaelfeil/codegen2-1B-gptj with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use michaelfeil/codegen2-1B-gptj with Transformers:

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

pipe = pipeline("text-generation", model="michaelfeil/codegen2-1B-gptj")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("michaelfeil/codegen2-1B-gptj")
model = AutoModelForCausalLM.from_pretrained("michaelfeil/codegen2-1B-gptj")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use michaelfeil/codegen2-1B-gptj with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "michaelfeil/codegen2-1B-gptj"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "michaelfeil/codegen2-1B-gptj",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/michaelfeil/codegen2-1B-gptj

SGLang

How to use michaelfeil/codegen2-1B-gptj 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 "michaelfeil/codegen2-1B-gptj" \
    --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": "michaelfeil/codegen2-1B-gptj",
		"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 "michaelfeil/codegen2-1B-gptj" \
        --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": "michaelfeil/codegen2-1B-gptj",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use michaelfeil/codegen2-1B-gptj with Docker Model Runner:
```
docker model run hf.co/michaelfeil/codegen2-1B-gptj
```

michaelfeil commited on May 22, 2023

Commit

2f4fc5d

1 Parent(s): 9c0a143

Upload Salesforce/codegen2-1B ctranslate fp16 weights

Browse files

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -9,7 +9,7 @@ license: apache-2.0
 ---
 # Conversion for FauxPilot, Codegen-2 as GPT-J
 It feels like GPT-J, acts like any other GPT-J, but its Codegen-2 weights under the hood.
-```
 Converted on 2023-05-22 using
 ```
 python /home/michael/fauxpilot/converter/codegen_gptj_convert.py --code_model Salesforce/codegen2-1B /home/michael/tmp-codegen2-1B-gptj

 ---
 # Conversion for FauxPilot, Codegen-2 as GPT-J
 It feels like GPT-J, acts like any other GPT-J, but its Codegen-2 weights under the hood.
 Converted on 2023-05-22 using
 ```
 python /home/michael/fauxpilot/converter/codegen_gptj_convert.py --code_model Salesforce/codegen2-1B /home/michael/tmp-codegen2-1B-gptj