-
### Please check that this issue hasn't been reported before.
- [X] I searched previous [Bug Reports](https://github.com/OpenAccess-AI-Collective/axolotl/labels/bug) didn't find any similar reports.
…
-
### Your current environment
```text
In this example https://github.com/vllm-project/vllm/blob/main/examples/multilora_inference.py if you gave two different loras instead of same loras with diff…
-
`python qlora.py --model_name_or_path decapoda-research/llama-13b-hf`
(I have updated the tokenizer_config.json and config.json as per the various discussions [here](https://huggingface.co/decapoda…
-
Hi I am trying to fine tune my llama model using DeepSpeed, accelerate and SFTTrainer along with QLORA. I have already pretrained my LLama model.
During the pretraining, I used DeepSpeed and Peft as …
-
xtuner train cfg-gamma7b/gemma_7b_it_qlora_alpaca_e3_copy.py --deepspeed deepspeed_zero2
10/28 18:19:05 - mmengine - WARNING - WARNING: command error: ''Adafactor is already registered in optimizer a…
-
### Please check that this issue hasn't been reported before.
- [X] I searched previous [Bug Reports](https://github.com/OpenAccess-AI-Collective/axolotl/labels/bug) didn't find any similar reports.
…
-
XTuner 已支持 百川2 QLora 单卡微调，欢迎加入 [Wechat](https://cdn.vansin.top/internlm/xtuner.jpg) 群交流
```python
git clone https://github.com/internLM/xtuner
cd xtuner
pip install -e .
xtuner train con…
-
Right now, [`requirements.txt`](https://github.com/artidoro/qlora/blob/main/requirements.txt) has `accelerate @ git+https://github.com/huggingface/accelerate.git`, but as of now this breaks QLoRA func…
-
Currently, `tune ls` is a bit unweildy. Can we make it better?
@joecummings
-
from https://huggingface.co/blog/4bit-transformers-bitsandbytes ?