Issues
- 11
mistal-chat cuda out of memory error
#14 opened by yuvalshachaf - 7
CUDA out of memory during training
#69 opened by CodeWithOz - 0
[BUG: TRL support]
#103 opened by moghadas76 - 0
[BUG: does it support ministral? 3B or above?
#102 opened by ArtificialZeng - 0
[BUG: utils.validate_data has inconsistent use of tabs and spaces in indentation which leads to crashing]
#95 opened by Hackerbone - 11
- 1
[BUG: Error during training
#85 opened by Chasapas - 0
mistral small support
#101 opened by win4r - 1
[BUG: ValueError: setting an array element with a sequence. The requested array has an inhomogeneous shape after 1 dimensions. The detected shape was (32768,) + inhomogeneous part.
#99 opened by nvnk3 - 7
- 0
[BUG] Error with vllm
#93 opened by C3po-D2rd2 - 1
[BUG: Instruction FT (train.py) crashes on AWS g4dn.12xlarge (4 T4s) without precise indication of reasons]
#92 opened by leloss - 2
- 4
I have finetuned mistral-instruct-v0.3 but fine tuned model got worse. It doesn not even answer what original v0.3 can answer.
#82 opened by ZTAP0011 - 0
[BUG: after training the model, i am not able to merge the model and run inference on it
#89 opened by kiranshivaraju - 2
- 3
Fail to finetune with several GPU
#71 opened by banalg - 0
[NOT A BUG] : Is it possible to run the current validation/training scripts on a ray cluster?
#88 opened by SaiKrishnaBala - 3
How to use utils.extend_model_vocab?
#12 opened by CrispStrobe - 0
- 5
Mistral-Finetune creates consolidated.safetensors for mixtral 8x7b instruct v0.1 but mistral-chat fails inference for it complains about LoRA weights file being loaded missing an expected key for one of the model layers.
#75 opened by tensimixt - 1
`flshattF@v2.3.6` is not supported due to requires device with capability > (8, 0) but your GPU has capability (6, 1) (too old)
#79 opened by kamlesh0606 - 1
[BUG]: The _parse_available_tools method does not return all the defined tools.
#77 opened by matheus-prandini - 3
Cannot use wandb logging
#24 opened by jagilley - 1
data validation issue
#66 opened by noviljohnson - 3
How to convert model to GGUF after fine-tuned?
#64 opened by bensonbs - 0
Finetune 22B codestra model
#68 opened by salaki - 0
- 1
- 1
google colab error
#25 opened by silvacarl2 - 0
How to do early stopping
#33 opened by sujoyrc - 0
Tensorboard integration
#32 opened by SaiKrishnaBala - 0
- 5
mixtral 8x7b and 8x22b please
#11 opened by ehartford - 0
- 1
Video tutorial?
#6 opened by gileneusz - 1
`ValueError: min() arg is an empty sequence` in `utils.validate_data` script
#17 opened by aymenkrifa - 1
Avoid symlink `tests/fixtures`
#18 opened by DavidFarago - 0
Error python version 3.9
#9 opened by thomaspernet