-
Anyone successful finetune Qwen2-VL-7B-Instruct. I finetuned with 2 card A00 and got error CUDA OOM. Can you share which resources recommend to finetune it?
Thank you!
-
@loubnabnl The code for finetuning the base models are provided in this repo. However, I guess that the same code cannot be used for finetuning the instruct models. So, please provide code for finetun…
-
I was trying to finetuning Meta-Llama-3-8B-Instruct using 4 gpus with the following command:
`torchrun --nproc_per_node 4 -m training.run --output_dir llama3test --model_name_or_path meta-llama/Met…
-
**Describe the bug**
4xA100 gpu fine-tuning llama-3.1-8b-instruct (also tried llama2-13b-ms, same error), cli
```
CUDA_VISIBLE_DEVICES=0,1,2,3 \
NPROC_PER_NODE=4 \
LOCAL_WORLD_SIZE=4 \
swift…
-
Hi all,
I'm trying to run inference on Unsloth finetuned models. I'm using llama.cpp with 2x RTX 4090 GPUs to benchmark the performance of `Qwen2.5-Coder-14B-Instruct-128K-GGUF/Qwen2.5-Coder-14B-In…
-
Please correct me if I'm wrong, but it looks like the current examples for lora training all build a loss function around completion, which lines up with the lora example of using only the 'text' fiel…
-
In this command:
python finetune_mind2web.py --data_dir path/to/Mind2Web/data --base_model codellama/CodeLlama-7b-Instruct-hf --cache_dir --lora_dir --top_k_elements 20
I am not able to understand…
-
qwen2-vl has always been memory hungry (compared to the other vision models) and even with unsloth it still OOMs when the largest llama3.2 11b works fine.
I'm using a dataset that has high resolution…
-
### System Info
python 3.10.15
torch 2.5.1
transformers 4.46.2
tokenizers 0.20.3
### Information
- [ ] The official example scripts
- [x] My own modified scripts
### 🐛 Describe the bug…
-
Hi, i tried finetuning both llama 3.1-8b-instruct and llama 3-8b-instruct following the notebook you provided [here](https://colab.research.google.com/drive/1XamvWYinY6FOSX9GLvnqSjjsNflxdhNc?usp=shari…