-
When I train musicgen model using a small training set, the training process can proceed normally.
However, when I switch to a larger training set, which includes about 20000 samples, an error occurs…
-
Not sure exactly what happend, but I was attempting to explore a small dataset and I got this traceback:
```
Note that for multi-users you need to use and configure a launcher.
And to prevent…
-
List of features/changes we want to finish before releasing an official v1 version:
- [x] PostgreSQL support - **done**
- [x] Eager loading - #91 - **done**
- [x] User defined IDs - #127 - **done*…
-
Hello! @jytime I have several questions about the multi-stage training, specifically, the tracker.
In my understanding, you trained the tracker on kubric first, then finetuned it on Co3D or MegaDep…
qsisi updated
3 months ago
-
Hi folks,
As there are multiple issues here regarding fine-tuning DINOv2 on custom data, questions related to semantic segmentation/depth estimation, image similarity and feature extraction etc. th…
-
I modified some of the Pythia models to use LLaMAMoE. However, it didn't run properly.
I attached the the full log below, but in short, the line
`
token_idx, expert_idx = torch.where(mask)
`
will…
-
**_运行run_mask_finetune_raft.sh文件时一直有问题，许久都没有解决，希望解惑，非常感谢！_**
**在修改run_mask_finetune_raft.sh文件至如下并运行时：**
approach=mask_norm_sigmoid_linear
mask_level=layerwise
lr=2e-5
warp_init_val=0.2
reg_a…
-
**Problem:**
Inefficient microservice/database queries.
If I need to return 100 orders with their clients, I have to make 101 requests to microservices (1 for batch of orders, 100 for their clients …
-
- [ ] [HongyeJ on X: "Despite the mixed feelings about Google's latest Gemma model, we're big fans! @GoogleAI Why? Coz we found it pairs incredibly well with our SelfExtend 🤣🤣🤣 - like, perfectly! With…
-
As originally discussed in #5, the JS proxy does not allow non-asynchronous overriding of `=` and `delete`.
However, we could still make use of them by introducing the concept of _batched operations_…