-
# Patterns for Building LLM-based Systems & Products
Evals, RAG, fine-tuning, caching, guardrails, defensive UX, and collecting user feedback.
[https://eugeneyan.com/writing/llm-patterns/](https://e…
-
Great library, a light library for all the main evals was really needed!💯
I just came across this [line](https://github.com/huggingface/lighteval/blob/af24080ea4f16eaf1683e353042a2dfc9099f038/src/…
-
# Modifying parameters of FSDP-wrapped module by hand without summon_full_params context
## Issue description
I am training a large language module using FSDP.
I want to store EMA weights wh…
-
Hi, team.
I am developing a brand new agent framework [instinct.cpp](https://github.com/RobinQu/instinct.cpp). In [latest version](https://github.com/RobinQu/instinct.cpp/blob/main/modules/instinc…
-
# URL
- https://arxiv.org/abs/2308.07968
# Affiliations
- Cheng Li, N/A
- Mingyang Zhang, N/A
- Qiaozhu Mei, N/A
- Yaqing Wang, N/A
- Spurthi Amba Hombaiah, N/A
- Yi Liang, N/A
- Michael…
-
I recently encountered documentation that was clearly written by a Large Language Model (LLM) in a JOSS submission. I wondered what the policy of JOSS is on the use of LLMs, on authorship etc.
Pers…
-
The money spent purchasing market-based instruments (offsets) means investment goes **away** from green software and energy efficiency initiatives and **towards** low-carbon energy suppliers and carbo…
-
Hi,
We're running a project in the CivicLab in Grenoble, France. The project is based on LLM and is building as opensource project.
We're trying to build, test, prototype and evaluate an assistant…
-
I would like to generate a separate interface, like the chatGPT interface, for an Assistant's Playground to be used by others for testing. How can I do this, and do the developers have plans to accomm…
-
### What is the issue?
After the update, it's just stuck with:
> time=2024-05-28T20:08:58.624-07:00 level=INFO source=server.go:564 msg="waiting for server to become available" status="llm server …