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, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- 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
Update config.json
Browse filesupdate mm_vision_tower.
- config.json +1 -1
config.json
CHANGED
|
@@ -20,7 +20,7 @@
|
|
| 20 |
"mm_use_im_start_end": false,
|
| 21 |
"mm_vision_select_feature": "patch",
|
| 22 |
"mm_vision_select_layer": -2,
|
| 23 |
-
"mm_vision_tower": "
|
| 24 |
"model_type": "transcorem",
|
| 25 |
"num_attention_heads": 40,
|
| 26 |
"num_hidden_layers": 40,
|
|
|
|
| 20 |
"mm_use_im_start_end": false,
|
| 21 |
"mm_vision_select_feature": "patch",
|
| 22 |
"mm_vision_select_layer": -2,
|
| 23 |
+
"mm_vision_tower": "PCIResearch/clip-vit-large-patch14-336",
|
| 24 |
"model_type": "transcorem",
|
| 25 |
"num_attention_heads": 40,
|
| 26 |
"num_hidden_layers": 40,
|