-
Thanks for the brilliant work! I am reading this legendary paper and get this question that I want to discuss here.
The paper starts at introducing a new method to distill knowledge from a trained …
-
Hi,
I was looking at the zero cost, zero time, zero shot notebook for financial sentiment analysis (i.e., [this one](https://github.com/huggingface/setfit/blob/main/notebooks/zero_cost_zero_time_ze…
-
My teacher is Bert large and my student is TinyBert (pretrained - from Huggingface)
Now I facing incompatible num_attention_heads 12 for Tiny and 16 for Bert large.
Do you have some best practic…
-
@intfloat
Hi,
I'm implementing a E5 fine tune task similar to [1066](https://github.com/microsoft/unilm/issues/1066).
I am trying to run a simple E5-large fine-tuning with BM25 hard negatives…
-
hi, I trained DistilPose-S model without distillation. To achieve this, I simply set these four losses to None:
loss_keypoint=dict(type='SmoothL1Loss', use_target_weight=True),
loss_vis_toke…
-
After training en-hu we noticed a somewhat larger quality gap in 4 BLEU points between the teacher and student models.
It’s 24.8 for the quantized and fine-tuned student vs 30.2 BLEU for the teache…
-
### Description
Our contributions can be summarized as:• We propose to optimize NeRF as 3D self-prior, whereadaptive viewpoint sampling and boundary integrity metric are suggested to alleviate incons…
dmarx updated
7 months ago
-
Hi, this is a great work!
May I ask which method performs better in text-to-3d generation, SDS-bridge or NFSD? It seems that the paper doesn't mention this comparision.
Looking forward to hearing fr…
-
Hello. Nice repo. I have some questions related to the result of Experiment 5.3 (Figure 7). How is these result image generated? Based on the current code, I can't seem to determine where the model ch…
-