-
Would love to see Llama-Guard2 tested on the PINT benchmark!
-
**System Info**
- transformers version == 4.42.4
- dp-transformers version == 1.0.1
- accelerate version == 0.29.3
- llm == Distil-gpt2
- torch version == 2.0.0
- The model is runned under ddp…
-
In line with the main philosophy of the Symbiont app, we want to use products that are open source and provide the option for self-hosting for maximum privacy and control.
-
To reduce costs, improve privacy, and accelerate development and testing, let's use an open source models instead of OpenAI models (for text embeddings, as well as for the LLM).
Consider using Lla…
s2t2 updated
8 months ago
-
Thank you for this amazing project. Is is something I hoped for a long time 🙏🏻❤️
It would be handy though to have some support for fragment queries so that I can save it as a search engine and use …
-
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
-
Better inform users on chatbot privacy -
while users log in, before they get shown the login, and when using it should be clear that:
-we only need them to login to maximize the number of queries p…
-
### 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…
-
### Summary of the Enhanced LLM Inference System
**Objective**: To create a robust, transparent, and efficient system for large language model (LLM) inference using CUDA, ensuring reproducibility, qu…
-
In inference_local.py, get_prompt func just supports single query, so how to get prompt for multiturn conversation?
```
def get_prompt(user_query: str, functions: list = []) -> str:
"""
Ge…