Instructions to use jondurbin/airoboros-34b-3.2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jondurbin/airoboros-34b-3.2 with Transformers:

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

pipe = pipeline("text-generation", model="jondurbin/airoboros-34b-3.2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("jondurbin/airoboros-34b-3.2")
model = AutoModelForCausalLM.from_pretrained("jondurbin/airoboros-34b-3.2")
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]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use jondurbin/airoboros-34b-3.2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "jondurbin/airoboros-34b-3.2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jondurbin/airoboros-34b-3.2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/jondurbin/airoboros-34b-3.2

SGLang

How to use jondurbin/airoboros-34b-3.2 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/airoboros-34b-3.2" \
    --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": "jondurbin/airoboros-34b-3.2",
		"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 "jondurbin/airoboros-34b-3.2" \
        --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": "jondurbin/airoboros-34b-3.2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use jondurbin/airoboros-34b-3.2 with Docker Model Runner:
```
docker model run hf.co/jondurbin/airoboros-34b-3.2
```

Retain with the latest Yi-34B-200K?

by Hoioi - opened Mar 7, 2024

Discussion

Hoioi

Mar 7, 2024

Could you please retain this model with the latest released version of 01-ai/Yi-34B-200K? They claim that the new release can support long input better. Is there any chance?
And when could we expect bagel 34b v.5? When will the training finish?
Thank you so much for your great models.

Hoioi changed discussion status to closed Mar 7, 2024

jondurbin

Owner Mar 7, 2024

I can give it a go when I have some additional funds and time to do another fine-tune.

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