-
The `seen_tokens` attribute is deprecated and will be removed in v4.41. Use the `cache_position` model input instead.
Traceback (most recent call last):
File "/hpc2hdd/home/yhuang489/junhao/Emu3/e…
-
### Description
When using memory=True for a crew that uses Azure Open AI, there is an error creating long term memory.
### Steps to Reproduce
```
import os
from chromadb.utils.embedding_…
-
- [ ] [system-2-research/README.md at main · open-thought/system-2-research](https://github.com/open-thought/system-2-research/blob/main/README.md?plain=1)
# OpenThought - System 2 Research Links
He…
-
## Description
## To Reproduce
Steps to reproduce the behavior:
1. Choose 'blur' for qc in the tile extraction step:
```
dataset.extract_tiles(qc='blur', # ‘otsu’, ‘blur’, ‘both’, or None #…
-
## 🚀 Feature
Add support for self supervised learning, especially for multimodal input and improve the current vissl backed features.
### Motivation
I have been working on multimodal self super…
-
Hi,
I was really impressed by SPHINX's capability.
However, is it possible to do in-context learning with it?
Something similar to your example for Multimodal LLaMA2 https://alpha-vllm.github.i…
-
### Before
```python
def make_initial_point_fn(
*,
free_rvs: Sequence[TensorVariable],
rvs_to_transforms: dict[TensorVariable, Transform],
initval_strategies: dict[TensorVariable,…
-
### Motivation
I notice that internval_chat/eval/evaluate_vqa.py has parameters for few-shot learning but have not been implemented correctly.
My question is:
How can we do few-shot learning …
-
- [ ] [LMOps/README.md at main · microsoft/LMOps](https://github.com/microsoft/LMOps/blob/main/README.md?plain=1)
# LMOps/README.md at main · microsoft/LMOps
## LMOps
LMOps is a research initiati…
-
# Goal
------
* Many of the new LLMs models support long context. For example, lamma 3.1 and Mistral 2 support 128k;
* The trend is upwards, e.g. Gemini support 1M - 10M. Claude supports 200k;
* …