bigcode-project starcoder issues

bigcode-project / starcoder

Home of StarCoder: fine-tuning & inference!

Apache License 2.0

7.28k stars 518 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

Can starcoder be used to create a structured file format?

#162 dwightkelly opened 1 month ago
0
zero3 DPO starcoder OOM

#161 oo0-0-0oo opened 3 months ago
0
Removal request & notice: permissive licensing might often still be unsuitable(!) for training set inclusion

#160 ell1e opened 6 months ago
2
RuntimeError: CUDA error: CUDA-capable device(s) is/are busy or unavailable CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect. For debugging consider passing CUDA_LAUNCH_BLOCKING=1. Compile with `TORCH_USE_CUDA_DSA` to enable device-side assertions.

#159 NyanNat opened 6 months ago
0
v0.10.0 of Peft breaks finetune.py

#158 umm-maybe opened 6 months ago
0
What should be masking id . should it be -100 only . giving device side assert triggered

#157 nileshdhul opened 6 months ago
0
Is finetune.py incompatible with older GPUs?

#156 umm-maybe opened 6 months ago
0
FileNotFoundError: [Errno 2] No such file or directory: 'checkpoint-100/model-00001-of-00003.safetensors'

#155 dshwei opened 6 months ago
0
Better inference based on starcode2-3b model

#154 HeroSong666 opened 6 months ago
1
Question about Improving Code Generation with Promting

#153 icnahom opened 7 months ago
0
Update finetune.py

#152 jiagaoxiang opened 7 months ago
0
torch.cuda.OutOfMemoryError on HuhhingFace NVidia 4xA10G Large

#151 lkthomas opened 7 months ago
2
Fine tuning With SQLcoder-7b

#150 bhrt95 opened 9 months ago
0
How many shots are used for evaluating HumanEval?

#149 zhimin-z closed 7 months ago
1
Empty Generations / Failing Reproducing 40% on HumanEval

#148 leonardtang opened 10 months ago
3
HuggingFaceH4/oasst1_en - missing dataset

#147 erap129 opened 10 months ago
1
Could somebody guide me how to fine-tune with fill-in-middle task based on StarCoderBase?

#146 FlyingPiggyKing opened 10 months ago
1
Fix run finetune.py from torch.distributed.launch

#145 iohub opened 11 months ago
0
inference problem

#144 Maomaoxion opened 11 months ago
0
does this support deepspeed zero train?

#143 CEfanmin closed 11 months ago
0
Fine-tuning Starcoder or Octocoder for IDE Integration: Instruction Tuning vs Base Model Training Approach

#142 JunHyungKang opened 1 year ago
1
Generating Embeddings of Code Tokens using StarCoder

#141 code2graph opened 1 year ago
1
StarCoder Fine Tuning

#140 samitugal closed 1 year ago
0
generates nonsense for me?

#139 nyspsycho opened 1 year ago
1
Effect of FIM on StarCoder pre-training

#138 gojkoc54 opened 1 year ago
2
Model size doubles after .merge_and_unload() and .save_pretrained()

#137 anudeep-peela opened 1 year ago
4
Usage of LoadBestPeftModelCallback in Finetuning stage

#136 ttssp opened 1 year ago
1
Why utilizing the 'question' column of the 'ArmelR/stack-exchange-instruction' dataset for gradient backpropagation?

#135 HIT-cwh opened 1 year ago
1
Issue with running Starcoder Model on Mac M2 with Transformers library in CPU environment

#134 code2graph opened 1 year ago
1
Deprecated warning during inference with starcoder fp16

#133 code2graph opened 1 year ago
1
Error during inference with starcoder

#132 nashid opened 1 year ago
0
How to run StarCoder for inference on macOS and feasibility without a GPU?

#131 code2graph opened 1 year ago
0
fix mask_user_labels

#130 DoffeBupt opened 1 year ago
3
some concern in "mask_user_labels"?

#129 DoffeBupt opened 1 year ago
1
How to fine-tune Starchat-beta on my question-answer dataset?

#128 AIAnytime opened 1 year ago
2
chat/dialogues.py mask_user_labels is bug?

#127 wanglongxingtianxia opened 1 year ago
1
Have a question about learning rate decay?

#126 strokesegment opened 1 year ago
1
Customizing Starcoder for FIM with Only Code Content Data

#125 tclxmeng-jia closed 1 year ago
2
Updated README Getting Started instructions

#124 massenz opened 1 year ago
0
Finetuning on SageMaker

#123 dshah3 opened 1 year ago
0
Running in offline mode

#122 dhingratul closed 1 year ago
0
Which model is the bigcode/starcoder model trained on?

#121 HIT-cwh closed 1 year ago
1
Why do we have 2 scripts for fine-tuning?

#120 samin-batra opened 1 year ago
3
How to save and load custom finetune

#119 LazerJesus opened 1 year ago
3
ValueError: Cannot merge LORA layers when the model is loaded in 8-bit mode

#118 mathav95raj closed 1 year ago
4
Questions about tokenizer

#117 Dmm2584v closed 11 months ago
1
Demo snippet pulls all checkpoints

#116 dhingratul opened 1 year ago
2
Explain code

#115 CodingmanJC opened 1 year ago
3
Readme BUG

#114 SmartMapple opened 1 year ago
0
Update train.py to match structure of HuggingFaceH4/oasst1_en

#113 sarthak405 opened 1 year ago
0