Aurora-Nights-70B-v1.0-2.4bpw-h6-exl2
This model is a blend of allenai/tulu-2-dpo-70b, Xwin-LM/Xwin-LM-70B-V0.1, and dreamgen/opus-v0.5-70b. I then merged nRuaif/fiction.live-Kimiko-V2-70B into the resultant blend....
Метка: en
dolphin-2.6-mistral-7b-exl2
Each branch contains an individual bits per weight, with the main one containing only the meaurement.json for further...
longcat-10.7B
Introducing «LongCAT» — the purrfect alternative to that other 10.7B Frankenmerger in town! Our long feline friend here...
codellama-34b-bnb-4bit
We have a Google Colab Tesla T4 notebook for Codellama 7b here: https://colab.research.google.com/drive/1y7A0AxE3y8gdj4AVkl2aZX47Xu3P1wJT?usp=sharing All notebooks are beginner friendly!...
openthaigpt-1.0.0-beta-13B-chat-GPTQ
Chat & support: TheBloke’s Discord server Want to contribute? TheBloke’s Patreon page TheBloke’s LLM work is generously supported...
xDAN-L1-Chat-RL-v1-GPTQ
Chat & support: TheBloke’s Discord server Want to contribute? TheBloke’s Patreon page TheBloke’s LLM work is generously supported...
blossom-v4-qwen-14b
Blossom是一个对话式语言模型，基于Qwen-14B预训练模型，在Blossom Orca/Wizard/Chat/Math混合数据集上进行指令精调得来。Blossom拥有强大的通用能力及上下文理解能力，此外，训练使用的高质量中英文数据集也进行了开源。 训练分为两阶段，第一阶段使用100K Wizard、100K Orca、20K Math单轮指令数据集，训练1个epoch；第二阶段使用50K Blossom chat多轮对话数据集、以及上一阶段中随机采样2%的数据，训练3个epoch。 Модальности:Генерация текста Задача: Генерация текста Автор: Azure99 Теги: qwen, feature-extraction,...
openbuddy-mixtral-8x7b-v16.1-32k
GitHub and Usage Guide: https://github.com/OpenBuddy/OpenBuddy Base model: https://huggingface.co/mistralai/Mixtral-8x7B-v0.1 All OpenBuddy models have inherent limitations and may potentially produce...
Mixtral-8x7B-Instruct-v0.1-limarp-exl2
Exllama v2 quant of Doctor-Shotgun/Mixtral-8x7B-Instruct-v0.1-limarp Branches: — main: measurement.json calculated at 2048 token calibration rows on exl2 default...
Ziya-Visual-Lyrics-14B
Lyrics 是IDEA CCNL研发的大规模视觉语言模型（Large Vision Language Model, LVLM）。Lyrics在预训练（视觉语言的表征对齐）和指令微调（视觉到语言的生成学习）的两阶段训练过程中，构建了视觉细化器来提取局部视觉特征和具化的空间表征，其由图像标记(RAM)、目标检测(Grounding DINO)和语义分割(SAM)模块组成。该方法可以防止细粒度的视觉对象的缺失，造成模型产生不可修复的视觉幻觉和事实错误。 Lyrics 可以以图像、文本、视觉对象作为输入，并以文本和视觉对象的空间表征作为输出。Lyrics模型具有强大的细粒度视觉特征提取和理解能力，能够完成各种以视觉为中心的任务，包括多回合视觉对话、视觉场景理解和推理、基于常识的图像描述、指向性问答。 Lyrics is a Large Vision Language Model (LVLM)...