Lei Zhang

### Feature request Hello, I would like to inquire about the potential inclusion of [RingAttention](https://github.com/lhao499/ring-attention) in `Transformers`, which could enable training with longer sequences. ### Motivation The incorporation of `RingAttention`...

Greetings, I have been thoroughly impressed by the exceptional performance of `InternLM-Xcomposer2`. May I inquire if there are plans to release the training data?

Reproduce FIM Evaluation

1

Hello, thanks a lot for your great work. Could you kindly advise on how to reproduce the evaluation results of FIM as shown in Table 6 of your [paper](https://arxiv.org/abs/2401.14196)? I...

Could you provide specific version information for the programs used to evaluate each language, such as Python: `python==3.9.0`, Node.js: `node==12.22.12`, etc.? I have not seen any related information so far,...

Provide some inference examples

1

Could you provide some simple examples for inference? Like this one [SPHINX-inference](https://github.com/Alpha-VLLM/LLaMA2-Accessory/tree/main/SPHINX#inference) 🤥

This PR updates the evaluation code and data for testing on the `bird` and `spider` benchmarks.

This PR update quantization evaluation results of `Qwen2.5-Coder-32B-Instruct`.