-
#108 is going to be an important place to start.
Twitter is the only context where I do not currently see a need for increased emphasis on self-curation at this time considering how that all appearan…
-
### Reminder
- [X] I have read the README and searched the existing issues.
### Reproduction
CUDA_VISIBLE_DEVICES=0,1 python src/train_bash.py can run sucessfully.
deepspeed --num_gpus 2…
-
Hello every one,
I am in the process of fine-tuning Llama2 using SFT trainer and quantization using Lora.
my dataset is composed of questions structured like:
`[INST] Please select the correct a…
-
Hi all! First off, thank you for putting together this excellent repo, it's saving me quite a bit of time from having to implement my own buffers from scratch. I really like the end-to-end jitting tha…
-
bug信息
--- Logging error ---
Traceback (most recent call last):
File "/usr/lib/python3.8/logging/__init__.py", line 1085, in emit
msg = self.format(record)
File "/usr/lib/python3.8/logging…
-
### System Info
- `transformers` version: 4.33.3 [1/1854]
- Platform: Linux-5.8.0-59-generic-x86_64-with-glibc2.31 …
-
Why did you also train the text encoder? Is training the unet only unable to inject the watermark? Thanks.
-
### System Info
### Describe the bug
I want to use LoRa tuning to fine-tune Whisper, but after I installed peft (parameter-efficient finetuning), it comes to a `segmentation fault` for each speech…
-
Hi. I am using exactly the same code as yours in run_sft.sh:
```
#!/bin/bash
CUR_DIR=`pwd`
ROOT=${CUR_DIR}
export PYTHONPATH=${ROOT}:${PYTHONPATH}
VISION_MODEL=openai/clip-vit-large-pa…
-
I mean, the context of "current" generation, that is super-fast for regeneration of latest action, and for minor editing of history.
I propose adding an option/param, that points to local binary fi…