valkryhx

请问 continuous-finetune 的实现原理是什么？是语料的不断merge还是合并了各个批次的LoRa Adapter？

3

对Vicuna模型很感兴趣，刚看到这个项目，想请教一下。 LoRA finetune会生成Adapter， 想请教一下项目主页中提到的continuous-finetune是合并了不同语料finetune后不同批次的LAdapter吗？ 还是说是训练语料的merge来实现？ 谢谢。

max_context_length > 2048 (比如langchain 场景下很长的上下文)时 报错: ggml_new_tensor_impl: not enough space in the scratch memory pool

4

首先大赞本项目的推理加速效果！666！ 环境Linux py38 我在使用python 绑定编译后的chatglm.cpp 模块后，使用q4_0量化chatglm2-6b 推理设置 generation_kwargs = dict( max_length=6000, **max_context_length=2400,** do_sample=args.temp > 0, top_k=args.top_k, top_p=args.top_p, temperature=args.temp, repetition_penalty=args.repeat_penalty, stream=True, ) **设置max_context_length > 2048 (比如langchain 场景下很长的上下文)时 报错: ggml_new_tensor_impl: not enough...

### 🐛 Describe the bug when I try to replace GPT2 with FLAN-T5-small model to run this demo: https://colab.research.google.com/github/CarperAI/trlx/blob/main/examples/notebooks/trlx_sentiments.ipynb it output a lot of "using bos_token ,but it is not...

how to well model a grid env when it changes frequently?

8

Suppose there is a game, a grid 10 by 10 ,each position was placed a piece of gold with a randomly positive value , and an agent do the mining...

[Bug]: No similarity score returns when calling HTTP/Python API of [Converse with chat assistant]

3

### Is there an existing issue for the same bug? - [x] I have checked the existing issues. ### RAGFlow workspace code commit ID main ### RAGFlow image version main...