Instructions to use Coobiw/ChartMoE_Reproduced with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Coobiw/ChartMoE_Reproduced with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="Coobiw/ChartMoE_Reproduced", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Coobiw/ChartMoE_Reproduced", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use Coobiw/ChartMoE_Reproduced with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Coobiw/ChartMoE_Reproduced" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Coobiw/ChartMoE_Reproduced", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Coobiw/ChartMoE_Reproduced
- SGLang
How to use Coobiw/ChartMoE_Reproduced 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 "Coobiw/ChartMoE_Reproduced" \ --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": "Coobiw/ChartMoE_Reproduced", "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 "Coobiw/ChartMoE_Reproduced" \ --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": "Coobiw/ChartMoE_Reproduced", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Coobiw/ChartMoE_Reproduced with Docker Model Runner:
docker model run hf.co/Coobiw/ChartMoE_Reproduced
Upload 6 files
Browse files- ChartQA_PoT/augmented.json +0 -0
- ChartQA_PoT/human.json +0 -0
- ChartQA_PoT/table.txt +7 -0
- ChartQA_wo-PoT/augmented.json +0 -0
- ChartQA_wo-PoT/human.json +0 -0
- ChartQA_wo-PoT/table.txt +7 -0
ChartQA_PoT/augmented.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
ChartQA_PoT/human.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
ChartQA_PoT/table.txt
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
+-----------+--------+-------+--------+
|
| 2 |
+
| @AP | 0.05 | 0.1 | 0.2 |
|
| 3 |
+
+-----------+--------+-------+--------+
|
| 4 |
+
| Human | 0.7976 | 0.816 | 0.832 |
|
| 5 |
+
| Augmented | 0.912 | 0.924 | 0.9384 |
|
| 6 |
+
| Averaged | 0.8548 | 0.87 | 0.8852 |
|
| 7 |
+
+-----------+--------+-------+--------+
|
ChartQA_wo-PoT/augmented.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
ChartQA_wo-PoT/human.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
ChartQA_wo-PoT/table.txt
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
+-----------+--------------------+--------+--------+
|
| 2 |
+
| @AP | 0.05 | 0.1 | 0.2 |
|
| 3 |
+
+-----------+--------------------+--------+--------+
|
| 4 |
+
| Human | 0.7184 | 0.7544 | 0.784 |
|
| 5 |
+
| Augmented | 0.9136 | 0.9256 | 0.9392 |
|
| 6 |
+
| Averaged | 0.8160000000000001 | 0.84 | 0.8616 |
|
| 7 |
+
+-----------+--------------------+--------+--------+
|