-
I find that the number of the grammar rules is 94 when I follow the instructions to preprocess the data (with the hyper-parameter fs=2). But the size of rule_embedding in the pre-trained model is 97.
…
-
为什么总是训练到第6个epoch的时候，损失函数就会变成nan
-
### Question Validation
- [X] I have searched both the documentation and discord for an answer.
### Question
**Can we apply the **Retry** Agent for the Query Time Sample Row Retrieval with ch…
-
Hello,
I am attempting to train the T5 model with the command below:
`python3 main_allennlp.py train configs/t5_text2sql_sede.jsonnet -s experiments/name_of_experiment --include-package src`
…
-
在text2SQL任务中，请问该模型的输出总是会重复输入的promp，导致输出长度限制，真正的select语句被截断。
请问怎么让模型只输出有用的SQL语句呢
-
Given similar names for other projects -text2sql.ai, etc, this project to should adopt a new name with no clashes to existing ones. Please share your ideas below and we will name it based on upvotes.
-
Adding schema of all tables in prompt can exceed LLM context limit hence not viable. How PremSQL handles schema with large number of tables? Is there a strategy to only add schema of relevant tables …
-
求助：如何通过微调提升模型的text2sql能力？
1. 如何给模型注入库表信息、业务知识？
2. 如何校正模型输出的SQL？
-------------
当前给出一个建表语句（比如一张用户登录日志表），再问一个问题（比如 当天的DAU是多少）， chatglm会给出错误的sql语句。 比如加了一些无关的字段、sql关键字之间没有空格、用户没有去重等
期望通过微调，提升模型的te…
-
Hi @tscholak - Appreciate your work on text2sql. I am trying to implement this in one of our usecase where data is in Snowflake. However, for POC I have created sqlite instance of small subset of data…
-
import autogen
import logging
from virus_agent import VirusAgent
from text2sql_agent import GoldenEyesAgent
from autogen import ConversableAgent
from autogen import config_list_from_json
from au…