Instructions to use fittar/ViPE-M-CTX7 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use fittar/ViPE-M-CTX7 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="fittar/ViPE-M-CTX7")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("fittar/ViPE-M-CTX7") model = AutoModelForCausalLM.from_pretrained("fittar/ViPE-M-CTX7") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use fittar/ViPE-M-CTX7 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "fittar/ViPE-M-CTX7" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "fittar/ViPE-M-CTX7", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/fittar/ViPE-M-CTX7
- SGLang
How to use fittar/ViPE-M-CTX7 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 "fittar/ViPE-M-CTX7" \ --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": "fittar/ViPE-M-CTX7", "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 "fittar/ViPE-M-CTX7" \ --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": "fittar/ViPE-M-CTX7", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use fittar/ViPE-M-CTX7 with Docker Model Runner:
docker model run hf.co/fittar/ViPE-M-CTX7
Update README.md
Browse files
README.md
CHANGED
|
@@ -37,11 +37,13 @@ in generating depictable and semantically meaningful prompts.
|
|
| 37 |
ViPE provides a robust backbone for many practical applications such as music video generation and creative writing.
|
| 38 |
- #### Music Video Genrations
|
| 39 |
- **Repository:** [Github](https://github.com/Hazel1994/ViPE-Videos)
|
| 40 |
-
- **
|
| 41 |
- #### Creative Writing
|
| 42 |
- **Demo:** [Hugging Face Playground](https://huggingface.co/spaces/fittar/ViPE)
|
| 43 |
- #### Summagery: Document Summarization through Images
|
| 44 |
- **Demo:** [Hugging Face Playground](https://huggingface.co/spaces/fittar/summagary)
|
|
|
|
|
|
|
| 45 |
|
| 46 |
|
| 47 |
### Direct Use
|
|
|
|
| 37 |
ViPE provides a robust backbone for many practical applications such as music video generation and creative writing.
|
| 38 |
- #### Music Video Genrations
|
| 39 |
- **Repository:** [Github](https://github.com/Hazel1994/ViPE-Videos)
|
| 40 |
+
- **Example Videos:** [ViPE Videos](https://www.youtube.com/playlist?list=PLvLHdI48ZdfaDMxPZIGHXrvsRkdADcMUh)
|
| 41 |
- #### Creative Writing
|
| 42 |
- **Demo:** [Hugging Face Playground](https://huggingface.co/spaces/fittar/ViPE)
|
| 43 |
- #### Summagery: Document Summarization through Images
|
| 44 |
- **Demo:** [Hugging Face Playground](https://huggingface.co/spaces/fittar/summagary)
|
| 45 |
+
- **Repository:** [Github](https://github.com/Hazel1994/summagary)
|
| 46 |
+
- **Examples:** [Summagery Videos](https://www.youtube.com/watch?v=mFMkE2waYGQ)
|
| 47 |
|
| 48 |
|
| 49 |
### Direct Use
|