-
Hi, I am trying to use `TestsetGenerator` to produce a synthetic dataset paired with `LlamaIndex` and 'Ollama', it successfully completes the embedding process, but before startin the generation proce…
-
Related
- https://huyenchip.com/2023/04/11/llm-engineering.html
[Tweet thread](https://twitter.com/transitive_bs/status/1646778061160071168?s=46&t=aOEVGBVv9ICQLUYL4fQHlQ) - LLMs in Production host…
-
We want to:
- Offer free LLM api to community
- Build up open dataset
- Collecting feedback of research team model
Probably will be hosted on cloud
-
This is a "living issue". Editing is appreciated.
### Context:
- Most prominent benchmark for embedding models: https://huggingface.co/spaces/mteb/leaderboard
- We can choose to index the pdf dat…
-
### Software
Desktop Application
### Operating System / Platform
macOS
### Your Pieces OS Version
Pieces for Developers 3.1.5 Pieces OS 10.1.6
### Early Access Program
- [X] Yes, this is relate…
-
Hi!
I think this is an interesting tool and I'm very sympathetic to trying out different ways to sort the fediverse timelines algorithmically. Very cool idea!
There are some issues I see however…
-
[paper](https://arxiv.org/pdf/2310.03744.pdf)
see llava https://github.com/long8v/PTIR/issues/128#issue-1749571159 here
## TL;DR
- **I read this because.. :** aka LLaVA1.5 / ShareGPT4V에서 LL…
-
This seems like a very important finding mentioned in your [blog](https://huggingface.co/blog/leaderboard-decodingtrust) and something deserving of further exposition.
Submitting your paper to Gemi…
-
@rayleizhu
I couldn't discern any difference in speed between using `enable_relay_attention = True` and `enable_relay_attention = False`.
I am using the same inference code ([inference.py](https:…
-
**Why**
This feature will enable users to get the full computational power of their machine, reduce latency, and enhance data privacy through a dedicated desktop application. It should empower users …