-
Excellent work! However, I have some concerns regarding the testing results of C-LoRA method. In the `sample` function of `lora_ddim.py`, you obtain the specific task index by executing `task_id = (la…
-
RuntimeError: Unsloth: `unsloth/llama-3-8b-bnb-4bit` is not a full model or a PEFT model.
-
Hi, I am trying to train the example training/peft-flan-t5-int8-summarization.ipynb
I am using a
p3dn.24xlarge | 8GPU | 96 | 768 | 256(vram). I am simply trying to run the example directly on th…
-
python -m lightllm.server.api_server --model_dir /root/autodl-tmp/Qwen2-7B-Instruct --host 0.0.0.0 --port 8000 --trust_remote_code --model_name Qwen2-7B-Instruct --data_type=bfloat16 --eos_id 151…
-
## Description
As a user of prompt tuning, I want to be able to leverage multiple GPUs at train time!
## Discussion
Extends https://github.com/caikit/caikit-nlp/issues/175 to leverage PyTorch…
-
This link [smangrul/peft-lora-sd-dreambooth](https://huggingface.co/spaces/smangrul/peft-lora-sd-dreambooth) from https://huggingface.co/blog/peft doesn't appear to exist anymore.
-
Hi,
First of all, thank you for your excellent work on this project. I tried to run your code on my machine, but I encountered an error that seems to indicate an issue with loading the model from a n…
-
### Describe the issue
Issue:
```
deepspeed llava/train/train_mem.py \
--lora_enable True --lora_r 128 --lora_alpha 256 \
--deepspeed ./scripts/zero3_offload.json \
--model_name_o…
-
### System Info
System Info
Python version: 3.11.0
PyTorch version: 2.4.1 or 2.5.0
Transformers version: 4.46.0
TRL version: 0.11.4
PEFT version: 0.13.2
### In…
-
I am trying to train TheBloke/Llama-2-7b-Chat-GPTQ & am running into the following error:
```
NotImplementedError: LlamaGPTQForCausalLM not support LORA peft type yet.
```
Where might I look to …