Legacy News Archive

Qwen2.5: Advancing Factual Knowledge, Coding, and Multilingual Capabilities

18.09.2024 Announcement qwen2.5

NVIDIA Nemotron Mini: Enhancing Roleplay, RAG, and On-Device Performance

18.09.2024 Announcement nemotron-mini

Mistral Small 3: Advancing Open-Source LLMs with Efficiency and Scalability

18.09.2024 Announcement mistral-small

Introducing Qwen2.5: A Versatile Large Language Model

18.09.2024 Announcement qwen2.5

Bespoke-MiniCheck: Pioneering Efficient Fact-Checking with State-of-the-Art Accuracy

18.09.2024 Announcement bespoke-minicheck

Precision in Text Transformation: Reader Lm's HTML-to-Markdown Innovations

11.09.2024 Announcement reader-lm

Deepseek V2.5: Advancing Conversational and Code-Processing Capabilities

07.09.2024 Announcement deepseek-v2.5

Yi Coder: Efficient Coding with Open-Source Innovation

04.09.2024 Announcement yi-coder

Redefining Mathematical Language Models with Qwen2 Math

30.08.2024 Announcement qwen2-math

Qwen2 Math: Revolutionizing Mathematical Language Models

30.08.2024 Announcement qwen2-math

Hermes3: Advancing Conversational Intelligence with Scalable Models

27.08.2024 Announcement hermes3

Phi3.5: Optimizing AI Efficiency with 3.8 Billion Parameters and Extended Context Handling

21.08.2024 Announcement phi3.5

Smollm: Advancing Small-Model Efficiency and Performance

20.08.2024 Announcement smollm

Paraphrase Multilingual: Advancing Multilingual Semantic Tasks

07.08.2024 Announcement paraphrase-multilingual

Bge M3: Revolutionizing Large Language Models

07.08.2024 Announcement bge-m3

Bge Large: Revolutionizing Language Understanding and Generation

07.08.2024 Announcement bge-large

Gemma2: Efficient, High-Performance Language Understanding

01.08.2024 Announcement gemma2

NuExtract: Precision in Structured Text Analysis with Customizable Templates

25.07.2024 Announcement nuextract

Redefining Open-Source Language Models: Llama3.1's Leap in Scale and Multilingual Capabilities

24.07.2024 Announcement llama3.1

Mistral Nemo: Advancing Open-Source Language Models with Precision and Scale

23.07.2024 Announcement mistral-nemo