starcoder

starcoder copied to clipboard

Does anyone run successfully with CPU only offline?

5

I try to run the model with a CPU-only python driving file but unfortunately always got failure on making some attemps. And here is my adapted file: **Attempt 1:** ```...

ztxjack

Cuda OOM during generate() call on 4 GPUs

5

I'm using the ```starcoderbase``` model across four GPUs to run inference. For some reason, one of the prompts I'm using causes a CUDA OOM error. Putting the tensor on GPU...

rggs

torch.cuda.OutOfMemoryError: CUDA out of memory When Trying to Save the Model

9

Howdy! I am using the `finetune/finetune.py` script. It trains on NVIDIA A40, and at the end when it tries to save the model/checkpoints it raises the `torch.cuda.OutOfMemoryError: CUDA out of...

cpt9m0

Trying to fine tune starcoderbase model using finetuning.oy - multiple GPUs

5

I am trying to fine tune bigcode/starcoderbase model on compute A100 with 8 GPUs 80Gb VRAM. My initial steps are to adjust parameters. I get some impression that it becomes...

dimichgh

Can/How StarCoder model can be used for encoding?

5

Beside the well-kown ChatGPT, now more and more startups and researchers note the great value and potential in OpenAI embedding API (https://platform.openai.com/docs/guides/embeddings). It enables many domain-specific adaptation and applications, like...

Symbolk

Generate (Android,..) project and use it as context in StarCoder (for whole life-cycle help)?

5

Seeing a lot of typical test examples like a Python counting function or code completion I'm wondering if there is something in the works to help on the project level....

ai-bits

How to disable "wandb" while running finetune.py

3

Hi there. I am wondering how to disable the functionality of wanddb, when running finetune.py. Is it possible to do this by executing the "**$wandb offline**" command? Or are there...

leemgs

only small amount coming as output.

1

I run the model and when running the model this message appears: Setting `pad_token_id` to `eos_token_id`:0 for open-end generation. Input length of input_ids is 21, but `max_length` is set to...

EngOMAR2030

AssertionError: Check batch related parameters. train_batch_size is not equal to micro_batch_per_gpu * gradient_acc_step * world_size

3

Hi I am working on FineTuning StarCoder by following the [README](https://github.com/bigcode-project/starcoder/tree/main/chat#fine-tuning-starcoder-for-chat-based-applications) in the `/chat` directory. I encounter the following Assertion error: ``` AssertionError: Check batch related parameters. train_batch_size is not...

vishal-kvn

Has anyone attempted to fine-tune the Starcoder model with your own code?

3

As per the title, I have attempted to fine-tune Starcoder with my own 400MB Python code. I concatenated all .py files into a single text file, similar to the content...

h-clickshift