Instructions to use OpenVINO/starcoder2-7b-int8-ov with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use OpenVINO/starcoder2-7b-int8-ov with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="OpenVINO/starcoder2-7b-int8-ov")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("OpenVINO/starcoder2-7b-int8-ov") model = AutoModelForCausalLM.from_pretrained("OpenVINO/starcoder2-7b-int8-ov") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use OpenVINO/starcoder2-7b-int8-ov with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "OpenVINO/starcoder2-7b-int8-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/starcoder2-7b-int8-ov", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/OpenVINO/starcoder2-7b-int8-ov
- SGLang
How to use OpenVINO/starcoder2-7b-int8-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/starcoder2-7b-int8-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/starcoder2-7b-int8-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/starcoder2-7b-int8-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/starcoder2-7b-int8-ov", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use OpenVINO/starcoder2-7b-int8-ov with Docker Model Runner:
docker model run hf.co/OpenVINO/starcoder2-7b-int8-ov
Update README.md
Browse files
README.md
CHANGED
|
@@ -28,7 +28,8 @@ The provided OpenVINO™ IR model is compatible with:
|
|
| 28 |
* OpenVINO version 2024.1.0 and higher
|
| 29 |
* Optimum Intel 1.16.0 and higher
|
| 30 |
|
| 31 |
-
## Running Model Inference
|
|
|
|
| 32 |
|
| 33 |
1. Install packages required for using [Optimum Intel](https://huggingface.co/docs/optimum/intel/index) integration with the OpenVINO backend:
|
| 34 |
|
|
@@ -55,6 +56,37 @@ print(text)
|
|
| 55 |
|
| 56 |
For more examples and possible optimizations, refer to the [OpenVINO Large Language Model Inference Guide](https://docs.openvino.ai/2024/learn-openvino/llm_inference_guide.html).
|
| 57 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 58 |
## Legal information
|
| 59 |
|
| 60 |
The original model is distributed under [bigcode-openrail-m](https://www.bigcode-project.org/docs/pages/bigcode-openrail/) license. More details can be found in [bigcode/starcoder2-7b](https://huggingface.co/bigcode/starcoder2-7b).
|
|
|
|
| 28 |
* OpenVINO version 2024.1.0 and higher
|
| 29 |
* Optimum Intel 1.16.0 and higher
|
| 30 |
|
| 31 |
+
## Running Model Inference with [Optimum Intel](https://huggingface.co/docs/optimum/intel/index)
|
| 32 |
+
|
| 33 |
|
| 34 |
1. Install packages required for using [Optimum Intel](https://huggingface.co/docs/optimum/intel/index) integration with the OpenVINO backend:
|
| 35 |
|
|
|
|
| 56 |
|
| 57 |
For more examples and possible optimizations, refer to the [OpenVINO Large Language Model Inference Guide](https://docs.openvino.ai/2024/learn-openvino/llm_inference_guide.html).
|
| 58 |
|
| 59 |
+
## Running Model Inference with [OpenVINO GenAI](https://github.com/openvinotoolkit/openvino.genai)
|
| 60 |
+
|
| 61 |
+
1. Install packages required for using OpenVINO GenAI.
|
| 62 |
+
```
|
| 63 |
+
pip install openvino-genai huggingface_hub
|
| 64 |
+
```
|
| 65 |
+
|
| 66 |
+
2. Download model from HuggingFace Hub
|
| 67 |
+
|
| 68 |
+
```
|
| 69 |
+
import huggingface_hub as hf_hub
|
| 70 |
+
|
| 71 |
+
model_id = "OpenVINO/starcoder2-7b-int8-ov"
|
| 72 |
+
model_path = "starcoder2-7b-int8-ov"
|
| 73 |
+
|
| 74 |
+
hf_hub.snapshot_download(model_id, local_dir=model_path)
|
| 75 |
+
|
| 76 |
+
```
|
| 77 |
+
|
| 78 |
+
3. Run model inference:
|
| 79 |
+
|
| 80 |
+
```
|
| 81 |
+
import openvino_genai as ov_genai
|
| 82 |
+
|
| 83 |
+
device = "CPU"
|
| 84 |
+
pipe = ov_genai.LLMPipeline(model_path, device)
|
| 85 |
+
print(pipe.generate("def print_hello_world():"))
|
| 86 |
+
```
|
| 87 |
+
|
| 88 |
+
More GenAI usage examples can be found in OpenVINO GenAI library [docs](https://github.com/openvinotoolkit/openvino.genai/blob/master/src/README.md) and [samples](https://github.com/openvinotoolkit/openvino.genai?tab=readme-ov-file#openvino-genai-samples)
|
| 89 |
+
|
| 90 |
## Legal information
|
| 91 |
|
| 92 |
The original model is distributed under [bigcode-openrail-m](https://www.bigcode-project.org/docs/pages/bigcode-openrail/) license. More details can be found in [bigcode/starcoder2-7b](https://huggingface.co/bigcode/starcoder2-7b).
|