Instructions to use infly/OpenCoder-8B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use infly/OpenCoder-8B-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="infly/OpenCoder-8B-Instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("infly/OpenCoder-8B-Instruct")
model = AutoModelForCausalLM.from_pretrained("infly/OpenCoder-8B-Instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use infly/OpenCoder-8B-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "infly/OpenCoder-8B-Instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "infly/OpenCoder-8B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/infly/OpenCoder-8B-Instruct

SGLang

How to use infly/OpenCoder-8B-Instruct 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 "infly/OpenCoder-8B-Instruct" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "infly/OpenCoder-8B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "infly/OpenCoder-8B-Instruct" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "infly/OpenCoder-8B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use infly/OpenCoder-8B-Instruct with Docker Model Runner:
```
docker model run hf.co/infly/OpenCoder-8B-Instruct
```

FIM task

by danielus - opened Nov 9, 2024

Discussion

danielus

Nov 9, 2024

•

edited Nov 9, 2024

Hi! I read the paper and found nothing about fill in the middle, but < fim_prefix > suffix and middle tokens are present.
is it possible to use this model for autocomplete code?

Simingh

inftech.ai org Nov 10, 2024

Hi! Unfortunately OpenCoder doesn't support the FIM task. Our model added this token due to certain historical considerations.

djuna

Nov 10, 2024

I found this dataset
https://huggingface.co/datasets/Etherll/code-fim-v2
Can we finetuned with this?

crazycth

inftech.ai org Nov 10, 2024

@djuna It's recommend to learn FIM through pretrain stage instead of alignment stage :-)

djuna

Nov 10, 2024

I see...

Simingh changed discussion status to closed Nov 14, 2024

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