Instructions to use KnutJaegersberg/orca-mini-70b-2bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use KnutJaegersberg/orca-mini-70b-2bit with Transformers:

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

pipe = pipeline("text-generation", model="KnutJaegersberg/orca-mini-70b-2bit")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("KnutJaegersberg/orca-mini-70b-2bit")
model = AutoModelForCausalLM.from_pretrained("KnutJaegersberg/orca-mini-70b-2bit")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use KnutJaegersberg/orca-mini-70b-2bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "KnutJaegersberg/orca-mini-70b-2bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "KnutJaegersberg/orca-mini-70b-2bit",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/KnutJaegersberg/orca-mini-70b-2bit

SGLang

How to use KnutJaegersberg/orca-mini-70b-2bit 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 "KnutJaegersberg/orca-mini-70b-2bit" \
    --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": "KnutJaegersberg/orca-mini-70b-2bit",
		"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 "KnutJaegersberg/orca-mini-70b-2bit" \
        --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": "KnutJaegersberg/orca-mini-70b-2bit",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use KnutJaegersberg/orca-mini-70b-2bit with Docker Model Runner:
```
docker model run hf.co/KnutJaegersberg/orca-mini-70b-2bit
```

This is a 2-bit quantization of @pankajmathur orca_mini_v3_70b using quip# (https://cornell-relaxml.github.io/quip-sharp/) with hessian context lenght 4k.

Inference with the model is a bit slow, but this should be the best 70b model you can use without offloading on a 3090.

Prompt Format:

### System:
You are an AI assistant that follows instruction extremely well. Help as much as you can.

### User:
Tell me about Orcas.

### Assistant:

I have included the quip library I have used in this repo. I am able to use this model in the widely known textgen-webui. For installation I suggest to follow these steps:

Download the quip folder from this repo and place it inside the repositories folder of the textgen-webui folder.
install the requirements of quip#
compile and install the quiptools cuda lib:

pip install fast-hadamard-transform glog==0.3.1 primefac==2.0.12
cd repositories/quip-sharp/quiptools
python setup.py install --force

reinstall the requirements of textgen-webui
load the model with the quip# integration of textgen-webui

You can use the library of this repo also for scripts. Within the quip# folder, after installing the library, use this command:

python interactive_gen.py --hf_path path_to_the_2bitmodel --max_length 500 text

Downloads last month: 8

Safetensors

Model size

3B params

Tensor type

I64

F16