-
### What happened?
I am running ollama locally on my M1 Mac and have the model `llama3:8b` specified as the default for fabric to use. When running the command `pbpaste | fabric -sp label_and_rate` a…
-
Requesting "German language model"
-
As shown below:
![screenshot 2023-11-21 at 10 41 58@2x](https://github.com/dqbd/tiktokenizer/assets/7106086/94f779d6-aaf4-4789-b2ee-e6dd5253e3b8)
![screenshot 2023-11-21 at 10 42 20@2x](https:…
-
## 创新更多发生在科研网络的边缘
* paper: Innovations are disproportionately likely in the periphery of a scientific network [[paper link](https://link.springer.com/article/10.1007%2Fs12064-021-00359-1)]
* 中文阅读:…
-
I'm always frustrated that I can't estimate the amount of resources the model will consume during the training of large language models, or determine whether my training configuration will lead to out…
yxyOo updated
5 months ago
-
# 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…
-
Having support for vector data types and operations such as exact and approximate nearest neighbor search, L2 distance, inner product, and cosine distance on these would open up semantic search use ca…
-
### 🚀 The feature, motivation and pitch
https://arxiv.org/pdf/2403.11421.pdf
This paper might be interesting.
> Cost of serving large language models (LLM) is high, but the
expensive and scarc…
-
When I asked "Who is founder of goolge.com?", the result of llama13B answered as shown in the figure below:
“tro tro tro tro tro tro tro tro tro tro tro tro tro tro tro tro tro tro tro tro tro tr…
-
# URL
- https://arxiv.org/abs/2310.06692
# Affiliations
- Anni Zou, N/A
- Zhuosheng Zhang, N/A
- Hai Zhao, N/A
- Xiangru Tang, N/A
# Abstract
- Large language models (LLMs) have unveiled rem…