starcoder

starcoder copied to clipboard

8bit model output <endoftext>

2

Hi, I'm using the 8bit version, and tried the demo case. However, I got an output . This is my code: from transformers import AutoModelForCausalLM, AutoTokenizer checkpoint = "bigcode/starcoder" device...

para-lost

RuntimeError: RuntimeError: IndexError: list index out of range - multiple GPUs

3

Trying to fine tune bigcode/starcoderbase model on compute A100 with 2 GPUs , 40 GBx2 so 80GB. Finetune.py is slightly modified and loaded the model with 4bit, adopt Qlora and...

Kushalamummigatti

code refactoring

2

I want to fine tune star coder for code refactoring tasks and I was thinking if it is possible and in this context, how can I get a dataset and...

Muntahabintealam

KeyError: 'response '

4

Hi,I am trying to run the fine-tuning code on my computer, but I got KeyError: 'response'，the environment is installed according to the README. Traceback (most recent call last): File "/home/starcoder/finetune/finetune.py",...

camhfwang

TypeError: expected str, bytes or os.PathLike object, not NoneType

6

I tried to fine-tune using the commands provided in the README and encountered the aforementioned error. For specific details, please refer to my [wandb log](https://wandb.ai/hansbug/huggingface/runs/9wdymnye/overview?workspace=).

HansBug

Hello, I want to reproduce the lm evaluation harness results reported in the blog. Since the prompts need to be formatted with the user, assistant, system, end tokens, the evaluation...

dh2shin

The blog post says the alpha and beta version of StarChat have not been aligned to human preferences with techniques like RLHF, so they can produce problematic outputs (especially when...

dh2shin

matrixssy

How to train a instruction code generated model based on starcoder and ta-prompt?

1

How can I do to train a instruction code generated model based on starcoder and ta-prompt? The official document mentioned that we can use ta-prompt to turn it into a...

jsuper

Training Loss vs Evaluation Loss during Fine Tuning Star Coder

10

Hi @ArmelRandy and @loubnabnl I am fine-tuning star coder on my custom dataset and was monitoring the training and validation loss. The training loss seems to decrease however in case...

ruchaa0112