lmstudio-community/internlm2_5-1_8b-chat-GGUF - Каталог нейросетей
Генерация текста

lmstudio-community/internlm2_5-1_8b-chat-GGUF

Добавлено:
lmstudio-community/internlm2_5-1_8b-chat-GGUF

👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord. Model creator: internlm Original model: internlm25-18b-chat GGUF quantization: provided by bartowski based on llama.cpp release b3561 InternLM has continued their 2.5 series of models with a 1.8b chat model release. This model has advanced math and reasoning abilities, and surpasses other models in this size category.Additionally, 2.5 features strong tool use and instruction following. It can be used with the InternLM tool MindSearch. Choose the ChatML preset in your LM Studio. Under the hood, the model will see a prompt that’s formatted like so: This 1.8B model is great for edge compute or mobile devices, and achieves great scores for its size. You can view the results and more comparisons on OpenCompass here 🙏 Special thanks to Georgi Gerganov and the whole team working on llama.cpp for making all of this possible. 🙏 Special thanks to Kalomaze and Dampf for their work on the dataset (linked here) that was used for calculating the imatrix for all sizes. LM Studio is not the creator, originator, or owner of any Model featured in the Community…

Модальности:
Генерация текста

Области применения:
Диалог / чат


Задача: Генерация текста
Автор: lmstudio-community
Теги: gguf, endpoints_compatible, imatrix, conversational
Лайков: 3  |  Загрузок: 99

Открыть на HuggingFace →

Описание основано на материалах HuggingFace. Перевод выполнен автоматически.