Instructions to use vmajor/Orca2-13B-selfmerge-39B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use vmajor/Orca2-13B-selfmerge-39B with Transformers:

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

pipe = pipeline("text-generation", model="vmajor/Orca2-13B-selfmerge-39B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("vmajor/Orca2-13B-selfmerge-39B")
model = AutoModelForCausalLM.from_pretrained("vmajor/Orca2-13B-selfmerge-39B")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use vmajor/Orca2-13B-selfmerge-39B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "vmajor/Orca2-13B-selfmerge-39B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "vmajor/Orca2-13B-selfmerge-39B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/vmajor/Orca2-13B-selfmerge-39B

SGLang

How to use vmajor/Orca2-13B-selfmerge-39B 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 "vmajor/Orca2-13B-selfmerge-39B" \
    --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": "vmajor/Orca2-13B-selfmerge-39B",
		"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 "vmajor/Orca2-13B-selfmerge-39B" \
        --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": "vmajor/Orca2-13B-selfmerge-39B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use vmajor/Orca2-13B-selfmerge-39B with Docker Model Runner:
```
docker model run hf.co/vmajor/Orca2-13B-selfmerge-39B
```

This model is a result of merging three Orca2-13B models with itself using 'mergekit-legacy'. Merge parameters were passthrough for one and --weight 0.5 --density 0.5 for the second merge.

This merged model showed marginal improvement in perplexity scores:

The perplexity for Orca-2-13b is: 7.595028877258301 The perplexity for orca2-26B-self-merge is: 7.550178050994873 The perplexity for orca2-39B-self-merge is: NC

The following table summarizes the model performance across a range of benchmarks:

Model	Average	ARC	HellaSwag	MMLU	TruthfulQA	Winogrande	GSM8K
microsoft/Orca-2-13b	58.64	60.67	79.81	60.37	56.41	76.64	17.97
vmajor/Orca2-13B-selfmerge-26B	62.24	60.84	79.84	60.32	56.38	76.87	39.2
vmajor/Orca2-13B-selfmerge-39B	62.24	60.84	79.84	60.32	56.38	76.87	39.2

Interestingly the GSM8K performance more than doubled with the first self merge. Second self merge resulting in the 39B model did not produce any further gains.

license: ms-pl

Downloads last month: 244

Safetensors

Model size

13B params

Tensor type

BF16