LMFlow
LMFlow copied to clipboard
An Extensible Toolkit for Finetuning and Inference of Large Foundation Models. Large Models for All.
Do you have the plan to support InternLM-7B & InternLM-20B which is similar to LLaMA model? (https://github.com/InternLM/InternLM) Thanks!
Recently I use the github "https://github.com/OptimalScale/LMFlow" to clone on my desktop computer . I use command "git clone XXXXX" on my "D://",Then ``Error downloading object: assets/multimodal-chatbot-demo.gif (2062965): Smudge error: Error...
您好。我尝试本地部署模型, app.py中加入如下代码才能正常运行, model args.model name or path = '/home/xfwl/huggingface/galactica-1.3b 部署完成后输入问题,机器人回答的是输入的内容,且有时还会回复代码。 http://lmflow.com 网页中微信群和discord链接全部都失效了,想进入社群学习。且这个网页的机器人不能对话。
您好,利用工程自带数据集对Llama7b进行Lora训练,数据集如下图所示 训练后app.py参数如下设置 对话显示如下所示
Hi, I am using LMFlow to invoke the model codellama/CodeLlama-7b-Instruct-hf. However, I found that the output was very repetitive. It seems that the default temperature setting is current set to...
你们好,我自己有一份私有大模型,预训练的时候,输入和输出之间的分隔符是"[SEP]",输出终止token是“\”。现在我想借助lmflow进行微调。我注意到,数据格式只能是text_only 和text2text,请问text_only 和text2text 在使用上有什么区别? 我应该如何构造我的数据集,才能使用你们的微调和推理脚本呢? 比如,我的数据格式是: ``` 问:能否帮我写一个python代码判断一个数字是否是偶数?答:is_even = lambda x: x % 2 == 0 ```
**Is your feature request related to a problem? Please describe.** I am very interested in this project, you guys did a great job. And I wonder if there is a...
Hey, our team is trying to recreate the RAFT (RAFT: Reward rAnked FineTuning for Generative Foundation Model Alignment) paper HH-RLHF benchmarks with Llama-7b. We successfully did the SFT step, however,...
With tons of experiments and tests, we finally support iterative dpo within a python script. Other useful features come alongside with iterative dpo: 1. Multi instance vllm inference (using ray)...
Hi, I attempted to use speculative decoding but encountered some errors. May I ask for your assistance? I used the parameters from the first example. python ./examples/speculative_inference.py \ --model gpt2-xl...