Instructions to use jondurbin/airocoder-34b-2.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jondurbin/airocoder-34b-2.1 with Transformers:

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

pipe = pipeline("text-generation", model="jondurbin/airocoder-34b-2.1")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("jondurbin/airocoder-34b-2.1")
model = AutoModelForCausalLM.from_pretrained("jondurbin/airocoder-34b-2.1")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use jondurbin/airocoder-34b-2.1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "jondurbin/airocoder-34b-2.1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jondurbin/airocoder-34b-2.1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/jondurbin/airocoder-34b-2.1

SGLang

How to use jondurbin/airocoder-34b-2.1 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 "jondurbin/airocoder-34b-2.1" \
    --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": "jondurbin/airocoder-34b-2.1",
		"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 "jondurbin/airocoder-34b-2.1" \
        --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": "jondurbin/airocoder-34b-2.1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use jondurbin/airocoder-34b-2.1 with Docker Model Runner:
```
docker model run hf.co/jondurbin/airocoder-34b-2.1
```

Which?

by ehartford - opened Sep 4, 2023

Discussion

ehartford

Sep 4, 2023

-instruct, -python, or base?

jondurbin

Owner Sep 4, 2023

Base coder, since the dataset has many languages.

This model is not that great though, at least on humaneval. Humaneval does code completion of basic functions requiring (virtually) no dependencies, and this dataset has many examples eith external libraries, and very few pure python completion examples.

ehartford

Sep 4, 2023

Requesting 13b 😜

jondurbin

Owner Sep 4, 2023

Working on the airoboros dataset 2.2 with some more coding examples; I can add a 13b for that one.

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