calme-3.2-instruct-3b
> [!TIP] > This is avery small model, so it might not perform well for some prompts and...
Метка: english
jais-adapted-7b-chat-GGUF
 This is quantized version of inceptionai/jais-adapted-7b-chat created using llama.cpp The Jais family of models is a comprehensive...
jais-family-256m-chat
The Jais family of models is a comprehensive series of bilingual English-Arabic large language models (LLMs). These models...
GOAT-llama3.1-v0.1
!a-captivating-and-surreal-image-of-a-goat-with-wil-XIKQzKvDRjihmI3sKK7IoA-0fxZxe6tRAKlXRRc4S9EPA.jpeg we are happy to announce that we are starting our goat model family this is a finetune...
Sumo-T9-7B-v0.1
Tensorplex Labs) is proud to announce that its latest top-performing model on Bittensor Subnet 9, Sumo-T9-7B, has outperformed...
llama-chinese-81M
使用重新在中英文語料上訓練的 BPE Tokenizer，擁有較佳的分詞效果與邊解碼效率。 > https://github.com/p208p2002/BPE-tokenizer-from-zh-wiki Модальности:Генерация текста Задача: Генерация текста Автор: p208p2002 Теги: llama, chinese, english, zh, en,...
bhasha-7b-8k-hi
Модель базового языка 7B, предварительно обученная на тексте на хинди с размером контекста 8k. Веса инициализированы из модели...
keywordGen-v2
KeywordGen-v1 — это модель на основе T5, точно настроенная для генерации ключевых слов из фрагмента текста. Учитывая входной...
spell_correct_bart_base
This is a model for word-based spell correction tasks. This model is generated by fine-tuning bart base model....
Argon-0.5B
Argon-0.5B 一个自研的基线模型，复刻 DeepSeek-V4 模型训练典型优化器，并加入 Engram 模块。 本仓库计划上传模型权重、切分后的训练数据、训练代码、tokenizer 资产和完整配置，使 Argon-0.5B 成为一个可审计、可复现、可继续训练的研究型预训练样例。 这个项目的初衷是复刻 DeepSeek 技术栈中的关键训练流程，并尝试在 500M 参数规模上实现一个完整的预训练闭环。 — 复刻 、数据...