loubnabnl santacoder-finetuning issues

loubnabnl / santacoder-finetuning

Fine-tune SantaCoder for Code/Text Generation.

Apache License 2.0

179 stars 22 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

FIM Evaluation

#26 Hambaobao closed 4 months ago
0
How to inference the model

#25 athmanar opened 4 months ago
1
Ways to reproduce this approach

#24 Yuyz0112 opened 8 months ago
2
ValueError: Batch does not contain any data (`None`). At the end of all iterable data available before expected stop iteration.

#23 cmosguy opened 9 months ago
2
Formatting FIM data

#22 gojkoc54 opened 10 months ago
1
Can I use it to fine tune bigcode/starcoderplus?

#21 tclxmeng-jia closed 10 months ago
1
moving a fine tuned model to gpt_bigcode

#20 Vipitis closed 10 months ago
2
Why is the inference speed using fp16 or bf16 similar to fp32?

#19 lionday opened 1 year ago
1
Has Santacoder done any pre-training in C or C++?

#18 lionday closed 10 months ago
4
I only generated three files after fine-tuning, is it correct? Why is there no tokenizer.json file?

#17 chen-lee-li closed 10 months ago
1
Cuda OOM even with batch size 1 and lower seq length on 16GB GPU

#16 noobmldude closed 10 months ago
3
I used multiple GPUs for training, but there were the following errors. How can I solve them?

#15 chen-lee-li closed 10 months ago
1
Question (not issue) related to dataset generation

#14 insop closed 10 months ago
2
Issue running inference on Huggingface after model upload

#13 umm-maybe opened 1 year ago
2
Linked Colab isn't working

#12 umm-maybe opened 1 year ago
0
Make FIM optional

#11 loubnabnl closed 1 year ago
1
Add in batch shuffling to `ConstantLengthDataset`

#10 lvwerra closed 1 year ago
0
Added the ability to train with bf16 through arguments

#9 esslushy closed 1 year ago
2
FIM permutations

#8 Stillerman closed 1 year ago
6
Update README.md

#7 Muhtasham closed 1 year ago
1
add comment about use_cache arg for inference

#6 loubnabnl closed 1 year ago
0
DeepSpeed Integration

#5 windspirit95 closed 1 year ago
2
Finetuning on multiple language

#4 windspirit95 closed 1 year ago
2
no_fp16 ?

#3 mrT23 closed 1 year ago
2
Add distributed training command to readme

#2 loubnabnl closed 1 year ago
0
weird behavior when setting batch_size

#1 DachengLi1 closed 1 year ago
2