Instructions to use OpenVINO/pythia-12b-fp16-ov with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OpenVINO/pythia-12b-fp16-ov with Transformers:

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

pipe = pipeline("text-generation", model="OpenVINO/pythia-12b-fp16-ov", trust_remote_code=True)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("OpenVINO/pythia-12b-fp16-ov", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("OpenVINO/pythia-12b-fp16-ov", trust_remote_code=True)

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use OpenVINO/pythia-12b-fp16-ov with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OpenVINO/pythia-12b-fp16-ov"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OpenVINO/pythia-12b-fp16-ov",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/OpenVINO/pythia-12b-fp16-ov

SGLang

How to use OpenVINO/pythia-12b-fp16-ov 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 "OpenVINO/pythia-12b-fp16-ov" \
    --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": "OpenVINO/pythia-12b-fp16-ov",
		"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 "OpenVINO/pythia-12b-fp16-ov" \
        --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": "OpenVINO/pythia-12b-fp16-ov",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use OpenVINO/pythia-12b-fp16-ov with Docker Model Runner:
```
docker model run hf.co/OpenVINO/pythia-12b-fp16-ov
```

pythia-12b-fp16-ov

Model creator: Eleutherai
Original model: pythia-12b

Description

Compatibility

The provided OpenVINO™ IR model is compatible with:

OpenVINO version 2024.2.0 and higher
Optimum Intel 1.19.0 and higher

Running Model Inference

Install packages required for using Optimum Intel integration with the OpenVINO backend:

pip install optimum[openvino]

Running Model Inference with Optimum Intel

Install packages required for using Optimum Intel integration with the OpenVINO backend:

pip install optimum[openvino]

Run model inference:

from transformers import AutoTokenizer
from optimum.intel.openvino import OVModelForCausalLM

model_id = "OpenVINO/pythia-12b-fp16-ov"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = OVModelForCausalLM.from_pretrained(model_id)

inputs = tokenizer("What is OpenVINO?", return_tensors="pt")

outputs = model.generate(**inputs, max_length=200)
text = tokenizer.batch_decode(outputs)[0]
print(text)

For more examples and possible optimizations, refer to the OpenVINO Large Language Model Inference Guide.

Running Model Inference with OpenVINO GenAI

Install packages required for using OpenVINO GenAI.

pip install openvino-genai huggingface_hub

Download model from HuggingFace Hub

import huggingface_hub as hf_hub

model_id = "OpenVINO/pythia-12b-fp16-ov"
model_path = "pythia-12b-fp16-ov"

hf_hub.snapshot_download(model_id, local_dir=model_path)

Run model inference:

import openvino_genai as ov_genai

device = "CPU"
pipe = ov_genai.LLMPipeline(model_path, device)
print(pipe.generate("What is OpenVINO?", max_length=200))

More GenAI usage examples can be found in OpenVINO GenAI library docs and samples

Limitations

Check the original model card for limitations.

Legal information

The original model is distributed under apache-2.0 license. More details can be found in original model card.

Disclaimer

Intel is committed to respecting human rights and avoiding causing or contributing to adverse impacts on human rights. See Intel’s Global Human Rights Principles. Intel’s products and software are intended only to be used in applications that do not cause or contribute to adverse impacts on human rights.

Downloads last month: 47

Model tree for OpenVINO/pythia-12b-fp16-ov

Base model

EleutherAI/pythia-12b

Finetuned

(2)

this model

Collection including OpenVINO/pythia-12b-fp16-ov

LLM

Collection

Collection of OpenVINO optimized LLMs • 146 items • Updated 3 days ago • 79