Instructions to use TheYuriLover/airoboros-13b-gpt4-TRITON with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TheYuriLover/airoboros-13b-gpt4-TRITON with Transformers:

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

pipe = pipeline("text-generation", model="TheYuriLover/airoboros-13b-gpt4-TRITON")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TheYuriLover/airoboros-13b-gpt4-TRITON")
model = AutoModelForCausalLM.from_pretrained("TheYuriLover/airoboros-13b-gpt4-TRITON")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use TheYuriLover/airoboros-13b-gpt4-TRITON with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TheYuriLover/airoboros-13b-gpt4-TRITON"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TheYuriLover/airoboros-13b-gpt4-TRITON",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/TheYuriLover/airoboros-13b-gpt4-TRITON

SGLang

How to use TheYuriLover/airoboros-13b-gpt4-TRITON 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 "TheYuriLover/airoboros-13b-gpt4-TRITON" \
    --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": "TheYuriLover/airoboros-13b-gpt4-TRITON",
		"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 "TheYuriLover/airoboros-13b-gpt4-TRITON" \
        --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": "TheYuriLover/airoboros-13b-gpt4-TRITON",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use TheYuriLover/airoboros-13b-gpt4-TRITON with Docker Model Runner:
```
docker model run hf.co/TheYuriLover/airoboros-13b-gpt4-TRITON
```

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

This is the gptq 4bit quantization of this model: https://huggingface.co/jondurbin/airoboros-13b-gpt4

This quantization was made by using this repository: https://github.com/qwopqwop200/GPTQ-for-LLaMa/tree/triton

And I used the triton branch with all the gptq implementations available (true_sequential + act_order + groupsize 128)

CUDA_VISIBLE_DEVICES=0 python llama.py ./airoboros-13b-gpt4-TRITON c4 --wbits 4 --true-sequential --act-order --groupsize 128 --save_safetensors airoboros-13b-gpt4-128g-ts-ao.safetensors

Airoboros 13b gpt4 TRITON (g128 - ts - ao)
PPL: 5.480927467346191
max memory(MiB): 8590.25

Airoboros 13b gpt4 CUDA (g128 - ts)
PPL: 5.535770893096924
max memory(MiB): 8750.4697265625

Downloads last month: 3