Instructions to use flax-community/swe-gpt-wiki with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use flax-community/swe-gpt-wiki with Transformers:

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

pipe = pipeline("text-generation", model="flax-community/swe-gpt-wiki")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("flax-community/swe-gpt-wiki")
model = AutoModelForCausalLM.from_pretrained("flax-community/swe-gpt-wiki")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use flax-community/swe-gpt-wiki with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/flax-community/swe-gpt-wiki

SGLang

How to use flax-community/swe-gpt-wiki 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 "flax-community/swe-gpt-wiki" \
    --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": "flax-community/swe-gpt-wiki",
		"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 "flax-community/swe-gpt-wiki" \
        --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": "flax-community/swe-gpt-wiki",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use flax-community/swe-gpt-wiki with Docker Model Runner:
```
docker model run hf.co/flax-community/swe-gpt-wiki
```

birgermoell commited on Jul 13, 2021

Commit

ea54aa8

1 Parent(s): 1c47fec

Updated generation script2

Browse files

Files changed (1) hide show

evaluate.py +1 -1

evaluate.py CHANGED Viewed

@@ -6,5 +6,5 @@ model = GPT2LMHeadModel.from_pretrained("flax-community/swe-gpt-wiki")
 generator = pipeline('text-generation', model=model, tokenizer=tokenizer)
 set_seed(42)
-result = generator("Sveriges huvudstad är", max_length=30, num_return_sequences=5)
 print(result)

 generator = pipeline('text-generation', model=model, tokenizer=tokenizer)
 set_seed(42)
+result = generator("En dag för länge sedan så fanns det", max_length=150, num_return_sequences=5)
 print(result)