-
Basically, that is my question. How did you re-align/replace Blip2's LLM (flan-xl from what I have seen) with mT0-XL?
-
Hi! First of all, thank you for this amazing repo :)
While spending time with the medium model, I noticed this:
```
>>> import spacy
>>> nlp = spacy.load("tr_core_news_md")
>>> nlp("Erzurum'da …
-
### System Info
qianfan version: 0.3.9
### Reproduction
Traceback (most recent call last):
File "xxx/python3.9/site-packages/langchain_core/language_models/llms.py", line 246, in invoke
s…
chxb updated
7 months ago
-
你好，大佬，出现这种错误怎么解决，
我网上查了解决方案，还是没没找到。
百度智能云中也也建了一个应用，如下图
![image](https://github.com/Mao…
-
### Is there an existing issue for this?
- [X] I have searched the existing issues
### Current Behavior
ds_train_finetune.sh 多卡训练时，我用到24G 3090 四张显卡还是`torch.cuda.OutOfMemoryError: CUDA out of memory…
-
### System Info
peft 0.5.0
transformers 4.32.0
### Who can help?
_No response_
### Information
- [ ] The official example scripts
- [X] My own modified scripts
### Tasks
- [ ] A…
-
import os
# 可以指定一个绝对路径，统一存放所有的Embedding和LLM模型。
# 每个模型可以是一个单独的目录，也可以是某个目录下的二级子目录。
# 如果模型目录名称和 MODEL_PATH 中的 key 或 value 相同，程序会自动检测加载，无需修改 MODEL_PATH 中的路径。
MODEL_ROOT_PATH = ""
# 选用的 Embedding …
-
I run bloomz-2b6 on 8 X V100 GPU, i found the larger batch, the longger latency cost, batch and latncy seems a linear relationship，did't i have wrong usage ? or V100 did't support batch feature we…
-
**问题描述 / Problem Description**
用简洁明了的语言描述这个问题 / Describe the problem in a clear and concise manner.
![image](https://github.com/chatchat-space/Langchain-Chatchat/assets/147698475/63df3417-5eb1-474d-…
-
### Reminder
- [X] I have read the README and searched the existing issues.
### Reproduction
对BLOOMZ模型进行sft后保存了checkpoint，在加载sft后的checkpoint进行predict时发生以下错误：
ValueError: Tokenizer class BloomTok…