-
### 环境
transformers:4.35.2
微调方式:lora
训练模型:sqlcoder2(GPTBigCodeModel架构)
LLaMA-Factory:v0.3.0
> 对于LLaMA-Factory做了一些小的适配如下(为了支持最新版transformer中gptbigcode的flashattn2):
> ![image](https://github.com/h…
-
### Using Open source LLM models in SQL Chain
Is it possible to use open source LLM models in SQL chain ?
I have tried using tapex/Flan models in SQL Chain, but getting a serialization error on di…
-
-
Can you push a version/branch that uses a Nvidia A100 (80GB) GPU?
I'm getting a CUDA OOM error because my schema is large.
-
### Description
When trying to set up local models, I will run into what appears to be an unrecoverable problem. This happens both working on a linux box that has a NVIDIA card and on my M1 Mac. In b…