Instructions to use Joseph717171/BigOrca-2-XB with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Joseph717171/BigOrca-2-XB with Transformers:

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

pipe = pipeline("text-generation", model="Joseph717171/BigOrca-2-XB")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Joseph717171/BigOrca-2-XB")
model = AutoModelForCausalLM.from_pretrained("Joseph717171/BigOrca-2-XB")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Joseph717171/BigOrca-2-XB with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Joseph717171/BigOrca-2-XB"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Joseph717171/BigOrca-2-XB",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Joseph717171/BigOrca-2-XB

SGLang

How to use Joseph717171/BigOrca-2-XB 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 "Joseph717171/BigOrca-2-XB" \
    --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": "Joseph717171/BigOrca-2-XB",
		"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 "Joseph717171/BigOrca-2-XB" \
        --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": "Joseph717171/BigOrca-2-XB",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Joseph717171/BigOrca-2-XB with Docker Model Runner:
```
docker model run hf.co/Joseph717171/BigOrca-2-XB
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Inspired by AbucusAI's BigYi-15b...

BigOrca-2-XB

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the passthrough merge method.

Models Merged

The following models were included in the merge:

/Users/jsarnecki/opt/microsoft-Orca-2-13b

Quantizations

GGUFS (Thanks to mradermacher)

mradermacher/BigOrca-2-XB-GGUF

Configuration

The following YAML configuration was used to produce this model:

dtype: float16
merge_method: passthrough
slices:
- sources:
  - layer_range: [0, 10]
    model: /Users/jsarnecki/opt/microsoft-Orca-2-13b
- sources:
  - layer_range: [5, 15]
    model: /Users/jsarnecki/opt/microsoft-Orca-2-13b
- sources:
  - layer_range: [10, 20]
    model: /Users/jsarnecki/opt/microsoft-Orca-2-13b
- sources:
  - layer_range: [15, 25]
    model: /Users/jsarnecki/opt/microsoft-Orca-2-13b
- sources:
  - layer_range: [20, 30]
    model: /Users/jsarnecki/opt/microsoft-Orca-2-13b
- sources:
  - layer_range: [25, 35]
    model: /Users/jsarnecki/opt/microsoft-Orca-2-13b
- sources:
  - layer_range: [30, 40]
    model: /Users/jsarnecki/opt/microsoft-Orca-2-13b

Downloads last month: 109

Safetensors

Model size

23B params

Tensor type

F16

Model tree for Joseph717171/BigOrca-2-XB

Quantizations

1 model