Instructions to use allenai/open-instruct-code-alpaca-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use allenai/open-instruct-code-alpaca-7b with Transformers:

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

pipe = pipeline("text-generation", model="allenai/open-instruct-code-alpaca-7b")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("allenai/open-instruct-code-alpaca-7b")
model = AutoModelForCausalLM.from_pretrained("allenai/open-instruct-code-alpaca-7b")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use allenai/open-instruct-code-alpaca-7b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "allenai/open-instruct-code-alpaca-7b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "allenai/open-instruct-code-alpaca-7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/allenai/open-instruct-code-alpaca-7b

SGLang

How to use allenai/open-instruct-code-alpaca-7b 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 "allenai/open-instruct-code-alpaca-7b" \
    --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": "allenai/open-instruct-code-alpaca-7b",
		"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 "allenai/open-instruct-code-alpaca-7b" \
        --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": "allenai/open-instruct-code-alpaca-7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use allenai/open-instruct-code-alpaca-7b with Docker Model Runner:
```
docker model run hf.co/allenai/open-instruct-code-alpaca-7b
```

hamishivi commited on Jun 9, 2023

Commit

88c78a4

1 Parent(s): 295e592

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -46,7 +46,7 @@ Here is the performance of this model across benchmarks explored in our paper [H
 | MMLU 0-shot | MMLU 5-shot | GSM Direct | GSM CoT | BBH Direct | BBH CoT | TydiQA Gold-Passage | TydiQA Closed-book | Codex-Eval Pass@1 | Codex-Eval Pass@10 | AlpacaFarm vs Davinci-003 | Average |
 |:-----------:|:-----------:|:----------:|:-------:|:----------:|:-------:|:-------------------:|:------------------:|:-----------------:|:------------------:|:-------------------------:|---------|
-| 42.6 | 44.3 | 5.0 | 12.0 | 35.5 | 36.6 | 41.3 | 10.9 | 20.1 | 34.5 | 19.4 | 26.8 |
 If you use this model, please cite our work, the llama paper, and the original dataset:

 | MMLU 0-shot | MMLU 5-shot | GSM Direct | GSM CoT | BBH Direct | BBH CoT | TydiQA Gold-Passage | TydiQA Closed-book | Codex-Eval Pass@1 | Codex-Eval Pass@10 | AlpacaFarm vs Davinci-003 | Average |
 |:-----------:|:-----------:|:----------:|:-------:|:----------:|:-------:|:-------------------:|:------------------:|:-----------------:|:------------------:|:-------------------------:|---------|
+| 34.7 | 34.5 | 6.5 | 7.5 | 29.6 | 30.5 | 36.7 | 10.5 | 16.5 | 29.2 | 17.5 | 22.6 |
 If you use this model, please cite our work, the llama paper, and the original dataset: