jesbu1
/

robometer-4b-fft-libero

preference_comparisons

text-generation-inference

Model card Files Files and versions

jesbu1/robometer-4b-fft-libero

This Robometer model is full-finetuned on the libero_all dataset containing: LIBERO-90, 10, Object, Goal, Spatial, and generated failures from each of these datasets. This is likely to outperform the default Robometer model because the standard one is not trained on LIBERO-90.

Model Details

Base Model: Qwen/Qwen3-VL-4B-Instruct
Model Type: qwen2_5_vl

Training Run

Wandb Run: rbm
Wandb ID: wj739wca
Project: robometer
Notes: training Robometer

Citation

If you use this model, please cite:

Downloads last month: 74

Safetensors

Model size

4B params

Tensor type

BF16

·

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for jesbu1/robometer-4b-fft-libero

Base model

Qwen/Qwen3-VL-4B-Instruct

Finetuned

(268)

this model