-
I trained embedding model on toy dataset as suggested on the repo
`torchrun --nproc_per_node 1 -m training.run --output_dir test_path --model_name_or_path openaccess-ai-collective/tiny-mistral --tr…
-
I followed the instructions mentioned in README. However, running the command below is giving an error.
>python insults.py --competition
`Traceback (most recent call last):
File "insults.py", lin…
-
### What you would like to be added?
Inspired by this research paper [Vidur: A Large-Scale Simulation Framework For LLM Inference](https://proceedings.mlsys.org/paper_files/paper/2024/file/b74a8de47d…
-
Em chào mọi người, gần đây em có tận dụng code này và code alpaca-lora gốc để thực hiện instruction fine-tuning cho GPT-J 6B của VietAI. Tuy nhiên em đọc code em thấy có một phần khá lạ, code này và c…
-
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…
-
Proposed Sections on POD Documentation,
- README.md: general description and instructions for POD.jl
- Documenter.jl
- Introduction: General solver description
- How to Use: Instruction of…
-
It is a great job! I wonder the reason using InternLM-7B instead of LLama based model? You use the InternLM-7B or InternLM-chat-7B ?
And for the training data, you only use the instruction tuning d…
-
Hello, sorry to bother you. I don't know much about the code and I just want to run it. It performs well on photos with a collar, but
photos of the entire face cannot run
IndexError: list index out…
-
[issue]
The fine-tuning step doesn't increase the scores (it even decreases the score).
Please refer to the green line in the chart below.
![image](https://user-images.githubusercontent.com/39104…
-
# Description
The first huge difficulty for training an AI assistant is to get a dataset reach enough and big enough for starting the training at all.
ChatLLaMA needs three different type of da…