Instructions to use PCIResearch/TransCore-M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use PCIResearch/TransCore-M with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="PCIResearch/TransCore-M", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("PCIResearch/TransCore-M", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use PCIResearch/TransCore-M with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "PCIResearch/TransCore-M" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "PCIResearch/TransCore-M", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/PCIResearch/TransCore-M
- SGLang
How to use PCIResearch/TransCore-M 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 "PCIResearch/TransCore-M" \ --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": "PCIResearch/TransCore-M", "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 "PCIResearch/TransCore-M" \ --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": "PCIResearch/TransCore-M", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use PCIResearch/TransCore-M with Docker Model Runner:
docker model run hf.co/PCIResearch/TransCore-M
Commit ·
4d33240
1
Parent(s): 933b2c4
Update README.md
Browse files
README.md
CHANGED
|
@@ -3,7 +3,7 @@ language:
|
|
| 3 |
- en
|
| 4 |
---
|
| 5 |
|
| 6 |
-
#
|
| 7 |
|
| 8 |
Details and codes will be released soon. Stay tuned!
|
| 9 |
|
|
@@ -16,7 +16,7 @@ Details and codes will be released soon. Stay tuned!
|
|
| 16 |
PCI TransCore-M is a multimodal model, it's composed of a visual encoder and a language model. It enables content comprehension, recognition and multi-round conversations about pictures.
|
| 17 |
|
| 18 |
- **Visual Encoder:** CLIP ViT-L/14
|
| 19 |
-
- **Pre-trained LLM:**
|
| 20 |
|
| 21 |
# Install
|
| 22 |
Our install environment:NVIDIA A800-SXM4-80GB,CUDA Version: 11.7
|
|
|
|
| 3 |
- en
|
| 4 |
---
|
| 5 |
|
| 6 |
+
# PCI_TransCore-M
|
| 7 |
|
| 8 |
Details and codes will be released soon. Stay tuned!
|
| 9 |
|
|
|
|
| 16 |
PCI TransCore-M is a multimodal model, it's composed of a visual encoder and a language model. It enables content comprehension, recognition and multi-round conversations about pictures.
|
| 17 |
|
| 18 |
- **Visual Encoder:** CLIP ViT-L/14
|
| 19 |
+
- **Pre-trained LLM:** PCITransGPT-13B
|
| 20 |
|
| 21 |
# Install
|
| 22 |
Our install environment:NVIDIA A800-SXM4-80GB,CUDA Version: 11.7
|