Spaces:

richardlin823
/

modules_play

Running

356 kB

Ctrl+K

3 contributors

richard.lin

fix: unidrive vla quantization, oom failure during calib. add dynamic loading of calibration data, add max_pixel to limit mass loading.

945cba1 2 days ago

PLANS
add: unidrive_vla_nusc_base_evaluation 14 days ago
__pycache__
add: model infer, model eval, within HuggingFace APIs, hello 27 days ago
.gitattributes

1.52 kB
Duplicate from gradio/gradio-lite-template 28 days ago
CLAUDE.md

1.97 kB
add: model infer, model eval, within HuggingFace APIs, hello 27 days ago
README.md

13.9 kB
fix: GPT-score can't work in China. 10 days ago
demo.py

228 Bytes
add: model infer, model eval, within HuggingFace APIs, hello 27 days ago
hgnetv2_b2_eval_quantized.py

12.4 kB
update: log output. 17 days ago
hgnetv2_b2_evaluate.py

18 kB
update: log output. 17 days ago
hgnetv2_b2_qad.py

33.9 kB
fix: finetune output folder. 14 days ago
hgnetv2_b2_qat.py

25.7 kB
fix: finetune output folder. 14 days ago
hgnetv2_b2_quantize_all.py

6.88 kB
feat: finished with hgnetv2 PTQ scripts. 22 days ago
prepare_env.sh

8.96 kB
update: add UniDriveVLA deps into prepare_env.sh 6 days ago
regnet_x_800mf_eval_quantized.py

12.4 kB
update: log output. 17 days ago
regnet_x_800mf_evaluate.py

17.9 kB
update: log output. 17 days ago
regnet_x_800mf_quantize_all.py

6.91 kB
feat: finished with regnet_x_800mf PTQ scripts. 22 days ago
remote_eval.py

21.2 kB
feat: finished with regnet_x_800mf PTQ scripts. 22 days ago
remote_sync.sh

22.7 kB
feat: sync for offline environment. 3 days ago
requirements.txt

7.58 kB
feat: finished with regnet_x_800mf PTQ scripts. 22 days ago
run.sh

740 Bytes
feat: run.sh 3 days ago
unidrive_vla_nusc_base_evaluation.py

45.6 kB
feat: unstrict evaluation 3 days ago
unidrive_vla_nusc_base_quantize_all.py

42.3 kB
fix: unidrive vla quantization, oom failure during calib. add dynamic loading of calibration data, add max_pixel to limit mass loading. 2 days ago
vit_large_patch16_224_eval_quantized.py

16 kB
update: log output. 17 days ago
vit_large_patch16_224_evaluate.py

18.1 kB
update: log output. 17 days ago
vit_large_patch16_224_quantize_all.py

18 kB
fix: exclude QKV, attention, MatMuls, LayerNorm, MatMuls layers for int8 quant. 20 days ago