Video-Text-to-Text
Transformers
Safetensors
qwen3_5
image-text-to-text
robotics
reward-model
vlm
gr00t
system-2
Instructions to use nvidia/Flora-Rewarder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use nvidia/Flora-Rewarder with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("nvidia/Flora-Rewarder") model = AutoModelForMultimodalLM.from_pretrained("nvidia/Flora-Rewarder", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Document third-party inference dependencies
#2
by OmarLaymounNvidia - opened
- batch_utils/README.md +2 -0
- batch_utils/THIRD_PARTY_NOTICES.md +16 -0
batch_utils/README.md
CHANGED
|
@@ -14,6 +14,8 @@ Scores: terminal `1` = complete failure, `5` = complete success; dense `1` = fai
|
|
| 14 |
|
| 15 |
## Setup
|
| 16 |
|
|
|
|
|
|
|
| 17 |
Validated with Python 3.12 and NVIDIA H100 80 GB GPUs: one GPU for terminal and dense rewards,
|
| 18 |
two for rubric rewards with the default settings (`--tensor-parallel-size 2`).
|
| 19 |
|
|
|
|
| 14 |
|
| 15 |
## Setup
|
| 16 |
|
| 17 |
+
This project will download and install additional third-party open source software projects. Review the license terms of these open source projects before use. See [third-party notices](THIRD_PARTY_NOTICES.md).
|
| 18 |
+
|
| 19 |
Validated with Python 3.12 and NVIDIA H100 80 GB GPUs: one GPU for terminal and dense rewards,
|
| 20 |
two for rubric rewards with the default settings (`--tensor-parallel-size 2`).
|
| 21 |
|
batch_utils/THIRD_PARTY_NOTICES.md
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Third-party notices
|
| 2 |
+
|
| 3 |
+
The inference scripts use the packages below, installed separately by the setup commands. These packages are not bundled in this repository. The requirements match [requirements.txt](requirements.txt).
|
| 4 |
+
|
| 5 |
+
The links identify upstream project licenses. Installed distributions and their dependencies retain their own licenses and notices. For version ranges, consult the license files supplied with the installed version.
|
| 6 |
+
|
| 7 |
+
| Requirement | Upstream license |
|
| 8 |
+
| --- | --- |
|
| 9 |
+
| `vllm==0.24.0` | [Apache-2.0](https://github.com/vllm-project/vllm/blob/v0.24.0/LICENSE) |
|
| 10 |
+
| `transformers==5.8.1` | [Apache-2.0](https://github.com/huggingface/transformers/blob/v5.8.1/LICENSE) |
|
| 11 |
+
| `qwen-vl-utils==0.0.14` | [Apache-2.0](https://github.com/QwenLM/Qwen3-VL/blob/main/LICENSE) |
|
| 12 |
+
| `decord==0.6.0` | [Apache-2.0](https://github.com/dmlc/decord/blob/v0.6.0/LICENSE) |
|
| 13 |
+
| `av>=15` | [BSD-3-Clause](https://github.com/PyAV-Org/PyAV/blob/main/LICENSE.txt) |
|
| 14 |
+
| `numpy<3` | [BSD-3-Clause](https://github.com/numpy/numpy/blob/main/LICENSE.txt) |
|
| 15 |
+
| `Pillow>=11,<13` | [PIL Software License (MIT-CMU)](https://github.com/python-pillow/Pillow/blob/main/LICENSE) |
|
| 16 |
+
| `huggingface_hub>=1.0` | [Apache-2.0](https://github.com/huggingface/huggingface_hub/blob/main/LICENSE) |
|