Ecosyste.ms: Issues

An open API service for providing issue and pull request metadata for open source projects.

GitHub / ziwang-com/zero-lora issues and pull requests

#80 - awq

Issue - State: closed - Opened by jychen21 14 days ago

#79 - SPQR 稀疏量-llm模型压缩

Issue - State: open - Opened by ziwang-com over 1 year ago

#77 - perf添加lora-hub实用程序

Issue - State: open - Opened by ziwang-com over 1 year ago

#76 - PEFT多LoRA切换

Issue - State: open - Opened by ziwang-com over 1 year ago

#75 - 在 不同LoRA 适配器之间切换？

Issue - State: open - Opened by ziwang-com over 1 year ago

#73 - 将 LoRA 应用于更多线性图层

Issue - State: open - Opened by ziwang-com over 1 year ago

#72 - 无法从 HF #280 转换羊驼重量

Issue - State: open - Opened by ziwang-com over 1 year ago

#71 - 将微调的 lora 权重导出到基本模型

Issue - State: open - Opened by ziwang-com over 1 year ago

#70 - lit-llama使用 LoRA 进行微调

Issue - State: open - Opened by ziwang-com over 1 year ago

#69 - HF官方lora叠加案例-AI制图

Issue - State: open - Opened by ziwang-com over 1 year ago

#68 - ggml-lora合并脚本

Issue - State: open - Opened by ziwang-com over 1 year ago

#67 - LoRA 合并

Issue - State: open - Opened by ziwang-com over 1 year ago

#66 - llm微调器与 LoRA 适配器

Issue - State: open - Opened by ziwang-com over 1 year ago

#65 - 合并 Lora 和模型

Issue - State: open - Opened by ziwang-com over 1 year ago

#64 - 从头开始的训练美洲驼

Issue - State: open - Opened by ziwang-com over 1 year ago

#62 - Alpaca+（CoT+Storytelling）三重模型合并

Issue - State: open - Opened by ziwang-com over 1 year ago

#61 - 合乎逻辑的选择！双lora叠加30B模型

Issue - State: open - Opened by ziwang-com over 1 year ago

#60 - CaMA: 中英双语LLaMA模型。

Issue - State: open - Opened by ziwang-com over 1 year ago

#58 - QLoRA 4 位量化

Issue - State: open - Opened by ziwang-com over 1 year ago

#57 - 如何创建自己的 LoRA 适配器？

Issue - State: open - Opened by ziwang-com over 1 year ago

#56 - LoRA 应用于复合模型

Issue - State: open - Opened by ziwang-com over 1 year ago

#55 - coco-LoR大型语言模型小规模学习

Issue - State: open - Opened by ziwang-com over 1 year ago

#54 - LoRACSE： 使用 LoRA 对句子嵌入的对比学习

Issue - State: open - Opened by ziwang-com over 1 year ago

#52 - LoRA双网络

Issue - State: open - Opened by ziwang-com over 1 year ago

#51 - lora情绪分析

Issue - State: open - Opened by ziwang-com over 1 year ago

#50 - 注意力权重可视化

Issue - State: open - Opened by ziwang-com over 1 year ago

#49 - TOT思维树，zero-lora的广义扩展

Issue - State: open - Opened by ziwang-com over 1 year ago

#47 - 4位QLora的即将到来

Issue - State: open - Opened by ziwang-com over 1 year ago

#46 - llama能加载多个lora模型的参数吗

Issue - State: open - Opened by ziwang-com over 1 year ago

#44 - xTuring提供快速、高效和简单的LLM微调

Issue - State: open - Opened by ziwang-com over 1 year ago

#43 - 加载 LoRa 大小不匹配 49954 与 32000

Issue - State: open - Opened by ziwang-com over 1 year ago

#42 - xturing 低 VRAM 微调

Issue - State: open - Opened by ziwang-com over 1 year ago

#41 - alpaca_lora_4bit微调lora

Issue - State: open - Opened by ziwang-com over 1 year ago

#40 - vicuna-lora斯坦福羊驼lora

Issue - State: open - Opened by ziwang-com over 1 year ago

#39 - 用大量开源指令遵循微调的LLM模型

Issue - State: open - Opened by ziwang-com over 1 year ago

#37 - LoRA 用于培训多语言教学

Issue - State: open - Opened by ziwang-com over 1 year ago

#35 - qlora，节约50%模型GPU内存

Issue - State: open - Opened by ziwang-com over 1 year ago

#34 - 如何在调整不同 LORA 的重量的同时加载多个 LORA

Issue - State: open - Opened by ziwang-com over 1 year ago - 1 comment

#33 - 通过修剪研究性能提升LLM-Pruner

Issue - State: open - Opened by ziwang-com over 1 year ago

#32 - 大型语言模型的低秩适应 （LoRA）

Issue - State: open - Opened by ziwang-com over 1 year ago

#31 - LoRA 调酒学以获得独特的 LLM 个性

Issue - State: open - Opened by ziwang-com over 1 year ago

#29 - LLM模型Zero-Shot Reasoners

Issue - State: open - Opened by ziwang-com over 1 year ago

#27 - 是否要定期发布新训练的模型检查点？

Issue - State: open - Opened by ziwang-com over 1 year ago

#24 - 训练您自己的 LoRA

Issue - State: open - Opened by ziwang-com over 1 year ago - 2 comments

#23 - LoRA 适配器 #1101 的潜在想法

Issue - State: open - Opened by ziwang-com over 1 year ago

#22 - 添加lora&羊驼模型的正确说明

Issue - State: open - Opened by ziwang-com over 1 year ago

#21 - 重新转换量化羊驼lora模型

Issue - State: open - Opened by ziwang-com over 1 year ago

#19 - 尝试与羊驼-洛拉合并及其量化 @alpaca作者tloen在这里

Issue - State: open - Opened by ziwang-com over 1 year ago - 1 comment

#18 - 如何在合并 Lora 的情况下输出 ggml 文件？

Issue - State: open - Opened by ziwang-com over 1 year ago

#17 - lora使模型组合成为可能

Issue - State: open - Opened by ziwang-com over 1 year ago

#16 - 动态应用 LoRA 适配器

Issue - State: open - Opened by ziwang-com over 1 year ago

#15 - 以交互方式将加载的模型导出到二进制文件

Issue - State: open - Opened by ziwang-com over 1 year ago - 1 comment

#14 - 为任意模型提取 LoRA

Issue - State: open - Opened by ziwang-com over 1 year ago

#13 - 跟踪： LoRA

Issue - State: open - Opened by ziwang-com over 1 year ago

#12 - 8 位量化LoRA 模型研究。

Issue - State: open - Opened by ziwang-com over 1 year ago

#11 - 使用中文指令数据集微调LLaMA-7B

Issue - State: open - Opened by ziwang-com over 1 year ago

#10 - LLaMA-TRL 使用PPO和LoRA微调LLaMA

Issue - State: open - Opened by ziwang-com over 1 year ago

#9 - 用RLHF可选LoRA对LLaMA和MOSS进行训练

Issue - State: open - Opened by ziwang-com over 1 year ago

#8 - LLMTune：消费者GPU上LLM的4位微调

Issue - State: open - Opened by ziwang-com over 1 year ago

#7 - 定制的lora_wrapper，可实现高效的微调

Issue - State: open - Opened by ziwang-com over 1 year ago

#6 - 俄罗斯扁平数据集的美洲驼模型微调

Issue - State: open - Opened by ziwang-com over 1 year ago

#5 - LoRA TCGA-LUAD 发生器

Issue - State: open - Opened by ziwang-com over 1 year ago

#4 - 双LoRA网络实现风格融合

Issue - State: open - Opened by ziwang-com over 1 year ago

#2 - LoRACSE： 使用 LoRA 对句子嵌入的对比学习

Issue - State: open - Opened by ziwang-com over 1 year ago