-
### Model description
Jina AI has just released an open source embedding model that can handle 8k sequence on huggingface:
- https://huggingface.co/jinaai/jina-embeddings-v2-base-en
- https://huggi…
-
Hi - I'm trying to download the en and zh data from [this page](https://data.baai.ac.cn/details/BAAI-MTP). However, it keeps asking me to scan a WeChat login and then doesn't work. Is there any other …
-
Would you consider supporting [Transformers.js](https://github.com/huggingface/transformers.js) as an additional provider? This library provides access to text generation and content classification fu…
-
### Model/Pipeline/Scheduler description
From the [repository](https://github.com/tyxsspa/AnyText):
> AnyText comprises a diffusion pipeline with two primary elements: an auxiliary latent module …
-
handle all chromadb operations
There should be a file in `task_queue` folder called `db.py`
3 functions in total
`get_connection()` return a connection object to our chromadb instance hard co…
-
Hi @raven38 thanks for building this. I'm looking forward to testing it
Which diffusers version are you using? Running into some tensor mismatch on the text encoder embeddings
``` File "..../tr…
-
### Project Name
Property LLM
### Description
### Motivation
Many London university students struggle to find suitable accommodation, particularly when it comes to meeting the specific requi…
-
hi,
I'm using
```
self.kv_creator = de.CuckooHashTableCreator(
saver=de.FileSystemSaver(proc_size=1, proc_rank=hvd.local_rank())
)
self.emb = de.keras.layers.…
-
Hi, I am using llm as part of a multimodal model, so the model needs to pass `input embedding tensor` directly to generate, and also need to access the language model's `embed_tokens` member to fist c…
-