This model was generated using llama.cpp at commit 0c21677e4. ——————|—————|——————————|————-| For multi-turn agentic tasks (τ²-Bench and Terminal Bench 2), please turn on Preserved Thinking mode. For τ^2-Bench evaluation, we added an additional prompt to the Retail and Telecom user interaction to avoid failure modes caused by users ending the interaction incorrectly. For the Airline domain, we applied the domain fixes as proposed in the Claude Opus 4.5 release report. For local deployment, GLM-4.7-Flash supports inference frameworks including vLLM and SGLang. Comprehensive deployment instructions are available in the official Github repository. vLLM and SGLang only support GLM-4.7-Flash on their main branches. + Install the supported versions of SGLang and Transformers (using uv is recommended): + For Blackwell GPUs, include —attention-backend triton —speculative-draft-attention-backend triton in your SGLang launch command. If you find our work useful in your research, please consider citing the following paper: «`bibtex @misc{5team2025glm45agenticreasoningcoding, title={GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation…
Модальности:
Генерация текста
Области применения:
Диалог / чат
Задача: Генерация текста
Автор: Mungert
Теги: gguf, en, zh, endpoints_compatible, conversational
Лайков: 3 | Загрузок: 1,823
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
