CodeGen

CodeGen copied to clipboard

How did you train the large-sized models without out-of-memory?

1

I would like to fine-tune the 2B model, but I got the out-of-memory issue even with the batch size setting to 1 (on a single GPU with 24G memory). I...

jiang719

How to get embedding for javascript and python code snippet?

3

I have a couple of questions: a) How can I use CodeGen to extract embedding for JavaScript and Python code? b) Can I feed incomplete code JavaScript and Python snippet...

smith-co

How to fine tune Codegen?

18

I would like to fine tune the Codegen model. Can you provide any documentation in this regard?

smith-co

Hey! I'm Clay from replicate.com. Really exciting model - thanks so much for releasing the weights! Hopefully this sort of tech can be a little more accessible to those without...

afiaka87

Hello, I'd like to know if the BSD-3 license also applies to the pre-trained models. In particular can the pre-trained models be re-used commercially? In any case thank you for...

timohear

Hello, I saw that you released the MTPB benchmark recently, do you plan to release also the script to evaluate CodeGen in multi-turn or single-turn using the MTPB dataset? Thank...

giulio98

Inference on TPU's

7

Is it possible to setup CodeGen for inference on TPU's? According to Huggingface, Pytorch-XLA generation is not yet supported: https://github.com/huggingface/transformers/issues/12322 Is there another way to use this model on TPU's...

Aryagm

AttributeError: 'CodeGen25Tokenizer' object has no attribute 'encoder'

3

Hi! I am using transformers 4.34 and tiktoken 0.4.0. I am trying to download the tokenizer for CodeGen 2.5, but when I run the command in the tutorial ``` >>>...

velocityCavalry

I have checked the CodeGen2.5 technical report and the CodeGen2 paper, but I cannot find a clue. Can you kindly provide some information about the details? Thank you ~

iCSawyer

Bumps [transformers](https://github.com/huggingface/transformers) from 4.30.0 to 4.36.0. Release notes Sourced from transformers's releases. v4.36: Mixtral, Llava/BakLlava, SeamlessM4T v2, AMD ROCm, F.sdpa wide-spread support New model additions Mixtral Mixtral is the new...

dependabot[bot]