tan-630 Goto Github PK

arima_soh

chatglm-6b-qlora

使用peft库，对chatGLM-6B/chatGLM2-6B实现4bit的QLoRA高效微调，并做lora model和base model的merge及4bit的量化（quantize）。

chatglm-finetuning

基于ChatGLM-6B、ChatGLM2-6B、ChatGLM3-6B模型，进行下游具体任务微调，涉及Freeze、Lora、P-tuning、全参微调等

chatlm-mini-chinese

中文对话0.2B小模型（ChatLM-Chinese-0.2B），开源所有数据集来源、数据清洗、tokenizer训练、模型预训练、SFT指令微调、RLHF优化等流程的全部代码。支持下游任务sft微调。

chinese-mixtral-8x7b

中文Mixtral-8x7B（Chinese-Mixtral-8x7B）

chinese-textcnn-sentimentanalysis

flagembedding

Retrieval and Retrieval-augmented LLMs

langchain-chatchat

Langchain-Chatchat（原Langchain-ChatGLM）基于 Langchain 与 ChatGLM 等语言模型的本地知识库问答 | Langchain-Chatchat (formerly langchain-ChatGLM), local knowledge based LLM (like ChatGLM) QA app with langchain

lstm_cosine

nasa_li-ion_battery_soh_prediction_with_mvip-trans

This research provides a prognostic framework for off-line SOH estimation of Li-ion battery. With a CNN-Transformer architecture, this program is capable of modeling the temporal correlations of battery signals from both local and global views. In this way, the learning ability of both local features and long period contexts will be enhanced.

pinn-battery-prognostics

State of Health (SoH) and Remaining Useful Life (RUL) prediction for Li-ion batteries based on Physics-Informed Neural Networks (PINN).

pykan

Kolmogorov Arnold Networks

soh_estimation_of_lithium-ion_battery

State of health (SOH) prediction for Lithium-ion batteries using regression and LSTM