-
Develop a feature that allows users to customize their application experience, such as choosing their preferred AI model.
-
支持Alpaca等指令数据集的SFT和RLHF流程：https://github.com/hiyouga/LLaMA-Efficient-Tuning
LoRA微调可在单块3090 GPU上运行，同时支持QLoRA方法。（最低12G显存）
微调模型的 LoRA 权重：https://huggingface.co/hiyouga/baichuan-7b-sft
运行以下指令即可实现…
-
### Describe the feature or improvement you're requesting
An idea for an eval which won't suffer from data contamination or overfitting.
maybe use financial news before the opening bell for some t…
-
Hi! Are there video tutorials?
-
# 大規模言語モデル
https://speakerdeck.com/chokkan/llm
統計関連学会
岡崎先生
n-gramからGPT4まで網羅されている最近LLMから自然言語始めた勢（私）にとってはNLPの流れを俯瞰できる良い資料。
もちろんdeep以前から構文解析や形態素解析の研究もされているので、LLMに流されず基礎的なところも勉強したい
-
你好，使用命令进行单机多卡训练的时候报错。命令如下：
CUDA_VISIBLE_DEVICES=0,1,2,3 python src/train_bash.py \
--stage sft \
--model_name_or_path path_to_your_model \
--do_train \
--dataset alpaca_gpt4_zh \
…
-
I specified the -- static option when configuring, but the compiled SRS program is still dynamically linked. There is no such problem in version 3.0, but upgrading to version 4.0 will cause this issue…
-
## Objective
- GPT4 学习step by step的能力
conversion: https://chat.openai.com/chat/ca69da70-2708-4bbb-b000-9c466ea54dbb
## key result:
数学题, 给出规则, 特别是用范例给出的解题思路, 然后performance大大的增强了
```
我们一起玩个24点游戏…
-
PIM can be quite good at holding a conversation and helping to translate sentences. The main problem is that it can be tricky to switch modes.
At the moment, PIM looks for the keywords 'conversatio…
-
Bug report for Colab: http://colab.research.google.com/.
For questions about colab usage, please use [stackoverflow](https://stackoverflow.com/questions/tagged/google-colaboratory/).
- Describe …