Instructions to use ColorfulAI/LSTP-Chat with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ColorfulAI/LSTP-Chat with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="ColorfulAI/LSTP-Chat")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("ColorfulAI/LSTP-Chat", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use ColorfulAI/LSTP-Chat with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "ColorfulAI/LSTP-Chat" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "ColorfulAI/LSTP-Chat", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/ColorfulAI/LSTP-Chat
- SGLang
How to use ColorfulAI/LSTP-Chat 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 "ColorfulAI/LSTP-Chat" \ --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": "ColorfulAI/LSTP-Chat", "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 "ColorfulAI/LSTP-Chat" \ --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": "ColorfulAI/LSTP-Chat", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use ColorfulAI/LSTP-Chat with Docker Model Runner:
docker model run hf.co/ColorfulAI/LSTP-Chat
Commit ·
78b0ff7
1
Parent(s): 9656e7d
init
Browse files- LSTP-7B.ckpt +3 -0
- README.md +7 -0
LSTP-7B.ckpt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f2f2ba540721eb1de1bdb41d461e2ff05effd29d6f3988a87a51141b31008334
|
| 3 |
+
size 32182891823
|
README.md
CHANGED
|
@@ -1,3 +1,10 @@
|
|
| 1 |
---
|
| 2 |
license: mit
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
license: mit
|
| 3 |
---
|
| 4 |
+
# LSTP-Chat: Language-guided Spatial-Temporal Prompt Learning for Video Chat
|
| 5 |
+
|
| 6 |
+
Available Checkpoints:
|
| 7 |
+
|
| 8 |
+
- LSTP-Chat-7b
|
| 9 |
+
|
| 10 |
+
For more details, please refer to our [official code repository](https://github.com/patrick-tssn/LSTP-Chat)
|