Instructions to use vaclavkosar/openchat_3.5-ct2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use vaclavkosar/openchat_3.5-ct2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="vaclavkosar/openchat_3.5-ct2")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("vaclavkosar/openchat_3.5-ct2", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use vaclavkosar/openchat_3.5-ct2 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "vaclavkosar/openchat_3.5-ct2" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "vaclavkosar/openchat_3.5-ct2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/vaclavkosar/openchat_3.5-ct2
- SGLang
How to use vaclavkosar/openchat_3.5-ct2 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 "vaclavkosar/openchat_3.5-ct2" \ --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": "vaclavkosar/openchat_3.5-ct2", "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 "vaclavkosar/openchat_3.5-ct2" \ --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": "vaclavkosar/openchat_3.5-ct2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use vaclavkosar/openchat_3.5-ct2 with Docker Model Runner:
docker model run hf.co/vaclavkosar/openchat_3.5-ct2
Commit ·
65b9849
1
Parent(s): 8f27f72
Update README.md
Browse files
README.md
CHANGED
|
@@ -21,7 +21,7 @@ pipeline_tag: text-generation
|
|
| 21 |
|
| 22 |
For efficient inference and low VRAM 7GB to up to 9GB with a short context window.
|
| 23 |
|
| 24 |
-
[
|
| 25 |
|
| 26 |
|
| 27 |
Original model description:
|
|
|
|
| 21 |
|
| 22 |
For efficient inference and low VRAM 7GB to up to 9GB with a short context window.
|
| 23 |
|
| 24 |
+
[Contact me or follow me, Vaclav Kosar, for more software and machine learning here.](https://vaclavkosar.com/)
|
| 25 |
|
| 26 |
|
| 27 |
Original model description:
|