-
Torchtune is a great project that explaining such a complex fine-tuning process in such an elegant way.
I would think having a simple benchmark againt other popular LLM fine-tuning approach is valu…
-
### Reminder
- [X] I have read the README and searched the existing issues.
### System Info
[2024-09-17 10:58:53,418] [INFO] [real_accelerator.py:203:get_accelerator] Setting ds_accelerator to cuda…
-
## Current Default
- `target_file_size_multiplier = 1`
- `block_size = 4096`
- `OptimizeLevelStyleCompaction(512M)` implies
- `target_file_size_base = 64M`
- snappy/lz4 compression types
…
-
支持Alpaca等指令数据集的SFT和RLHF流程:https://github.com/hiyouga/LLaMA-Efficient-Tuning
LoRA微调可在单块3090 GPU上运行,同时支持QLoRA方法。(最低12G显存)
微调模型的 LoRA 权重:https://huggingface.co/hiyouga/baichuan-7b-sft
运行以下指令即可实现…
-
### 🐛 Describe the bug
When I was fine-tuning lLama2-70b on Intel GPU (64G/card, 8 cards), I met out of memory issue after FSDP wrap. Here is the printed log before and after FSDP wrap:
>===memo…
-
### 🚀 The feature, motivation and pitch
PPO and a number of other LLM fine-tuning techniques require autoregressive generation as part of the training process. When using vLLM to speed up the autor…
-
We had a bug in our code that caused us to publish thousands of events in a single unit of work. It ended up triggering some Axon behavior that brought our application to its knees.
If there is a v…
-
Hello
Thanks for the great job you guys did, I was wondering do you have any tips or ideas to improve the current accuracy?, where do you think it lacks the most, I would like to try and improve the …
-
## Is your feature request related to a problem? Please describe.
I'm always frustrated when I'm looking at the replication worker code. It takes and object from the storage, decompresses it, unmarsh…
-
With all the growing activity and focus on multimodal models is this library restricted to tune text only LLM?
Do we plan to have Vision or more in general multimodal models tuning support?
bhack updated
2 months ago