Instructions to use IDEA-FinAI/chartmoe with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use IDEA-FinAI/chartmoe with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="IDEA-FinAI/chartmoe", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("IDEA-FinAI/chartmoe", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use IDEA-FinAI/chartmoe with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "IDEA-FinAI/chartmoe" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "IDEA-FinAI/chartmoe", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/IDEA-FinAI/chartmoe
- SGLang
How to use IDEA-FinAI/chartmoe 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 "IDEA-FinAI/chartmoe" \ --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": "IDEA-FinAI/chartmoe", "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 "IDEA-FinAI/chartmoe" \ --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": "IDEA-FinAI/chartmoe", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use IDEA-FinAI/chartmoe with Docker Model Runner:
docker model run hf.co/IDEA-FinAI/chartmoe
add flash-attn support
Browse files
configuration_chartmoe.py
CHANGED
|
@@ -53,6 +53,7 @@ class ChartMoEConfig(PretrainedConfig):
|
|
| 53 |
rope_scaling=None,
|
| 54 |
num_experts=4,
|
| 55 |
num_selected=2,
|
|
|
|
| 56 |
**kwargs,
|
| 57 |
):
|
| 58 |
self.num_experts = num_experts
|
|
@@ -77,6 +78,10 @@ class ChartMoEConfig(PretrainedConfig):
|
|
| 77 |
self.rope_theta = rope_theta
|
| 78 |
self.rope_scaling = rope_scaling
|
| 79 |
self._rope_scaling_validation()
|
|
|
|
|
|
|
|
|
|
|
|
|
| 80 |
super().__init__(
|
| 81 |
pad_token_id=pad_token_id,
|
| 82 |
bos_token_id=bos_token_id,
|
|
|
|
| 53 |
rope_scaling=None,
|
| 54 |
num_experts=4,
|
| 55 |
num_selected=2,
|
| 56 |
+
attn_implementation=None,
|
| 57 |
**kwargs,
|
| 58 |
):
|
| 59 |
self.num_experts = num_experts
|
|
|
|
| 78 |
self.rope_theta = rope_theta
|
| 79 |
self.rope_scaling = rope_scaling
|
| 80 |
self._rope_scaling_validation()
|
| 81 |
+
|
| 82 |
+
self.attn_implementation = attn_implementation
|
| 83 |
+
if self.attn_implementation is None:
|
| 84 |
+
self.attn_implementation = "eager"
|
| 85 |
super().__init__(
|
| 86 |
pad_token_id=pad_token_id,
|
| 87 |
bos_token_id=bos_token_id,
|