-
Assuming Lambda Labs 8xA100 and 80gb, which is 12 bucks. Can get a reasonable $ estimate that way.
-
Maybe I missed a critical step, but I had to do some manual work:
!python -m pip install torch==2.0.1+cu117 --extra-index-url https://download.pytorch.org/whl/cu117 --no-cache-dir
!pip install …
-
### System Info
File "/home/mukuro/projects/LLaMA-Factory/src/llamafactory/model/adapter.py", line 299, in init_adapter
model = _setup_lora_tuning(
^^^^^^^^^^^^^^^^^^^
File "/hom…
-
Hi I'm a beginner to fine tuning and unsloth.
When I ran the code in the notebook related to Llama 3 (8B) , I got the following error in generate the output.
I could not find out any similar cases…
-
PEFT finetuning (LoRA, adapter) raises the following warning for each FSDP-wrapped layer (transformer block in our case):
```python
The following parameters have requires_grad=True:
['transformer…
-
你好作者，我在研究您的LLM微调模型的时候发现，以下错误，代码无法跑通
ValueError: Please specify `target_modules` in `peft_config`
模型运行train的时候发现以下这些方法都没有找到
'ChatGLMForConditionalGeneration' object has no attribute 'enable_input_re…
-
Is there a way to finetune using V2? Thanks.
-
## 개요
- LLM.int8() + LoRA를 활용한 memory¶meter efficient fine tuning
- BitsAndBytes + Peft 활용한 모델 학습 예정
- Backbone은 [polyglot-ko-5.8b](https://huggingface.co/EleutherAI/polyglot-ko-5.8b) 활용(KoGPT는…
-
I have been using a new model that claimed to be built upon fastchat,
I have downloaded all these models file and put them into the folder but they still won't work out
https://huggingface.co/james…
-
I would like to report a bug using `MatMul8bitLt`.
### Bug description
When I used the following three in my code:
- `flash_attn_varlen_func` from flash_attn (v2.0.8, [Github Link](https://github…