Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.
|
|
9 months ago | |
|---|---|---|
| .. | ||
| llama_factory_recorder | 10 months ago | |
| tests | 10 months ago | |
| README.md | 11 months ago | |
| pyproject.toml | 9 months ago | |
Experimental node for recording for training llama based model.
git clone https://github.com/hiyouga/LLaMA-Factory --depth 1 $HOME
Example:
- id: dora-qwenvl-recorder
build: pip install -e ../../node-hub/llama-factory-recorder
path: llama-factory-recorder
inputs:
image_right: reachy/image_right
ground_truth: key-interpolation/text
outputs:
- text
env:
DEFAULT_QUESTION: Respond to people. # Prompt to use
LLAMA_FACTORY_ROOT_PATH: $HOME/LLaMA-Factory # path to llama factory
llama-factory/examples/train_lora/qwen2vl_lora_sft.yaml so that the dataset is the one you want to use,- dataset: mllm_demo,identity # video: mllm_video_demo
+ dataset: dora_demo_1,identity`
- model_name_or_path: Qwen/Qwen2-VL-7B-Instruct
+ model_name_or_path: Qwen/Qwen2.5-VL-3B-Instruct
llamafactory-cli train examples/train_lora/qwen2vl_lora_sft.yaml
DORA (Dataflow-Oriented Robotic Architecture) is middleware designed to streamline and simplify the creation of AI-based robotic applications. It offers low latency, composable, and distributed datafl
Rust Python TOML Markdown C other