Qwen-7B
Qwen-7B, also known as Qwen-7B, is the 7B-parameter variant of the large language models series Qwen. Tongyi Qianwen, proposed by Alibaba Cloud. Qwen-7B, a Transformer-based language model, is pretrained using a large volume data, such as web texts, books, code, etc. Qwen-7B is also used to train Qwen-7B Chat, an AI assistant that uses large models and alignment techniques. The Qwen-7B features include:
Pre-trained with high quality data. We have pretrained Qwen-7B using a large-scale, high-quality dataset that we constructed ourselves. The dataset contains over 2.2 trillion tokens. The dataset contains plain texts and codes and covers a wide range domains including general domain data as well as professional domain data.
Strong performance. We outperform our competitors in a series benchmark datasets that evaluate natural language understanding, mathematics and coding.
And more.
Learn more
Smaug-72B
Smaug 72B is an open-source large-language model (LLM), which is known for its key features.
High Performance: It is currently ranked first on the Hugging face Open LLM leaderboard. This model has surpassed models such as GPT-3.5 across a range of benchmarks. This means that it excels in tasks such as understanding, responding to and generating text similar to human speech.
Open Source: Smaug-72B, unlike many other advanced LLMs is available to anyone for free use and modification, fostering collaboration, innovation, and creativity in the AI community.
Focus on Math and Reasoning: It excels at handling mathematical and reasoning tasks. This is attributed to the unique fine-tuning technologies developed by Abacus, the creators Smaug 72B.
Based on Qwen 72B: This is a finely tuned version of another powerful LLM, called Qwen 72B, released by Alibaba. It further improves its capabilities.
Smaug-72B is a significant advance in open-source AI.
Learn more
OLMo 2
OLMo 2 is an open language model family developed by the Allen Institute for AI. It provides researchers and developers with open-source code and reproducible training recipes. These models can be trained with up to 5 trillion tokens, and they are competitive against other open-weight models such as Llama 3.0 on English academic benchmarks. OLMo 2 focuses on training stability by implementing techniques that prevent loss spikes in long training runs. It also uses staged training interventions to address capability deficits during late pretraining. The models incorporate the latest post-training methods from AI2's Tulu 3 resulting in OLMo 2-Instruct. The Open Language Modeling Evaluation System, or OLMES, was created to guide improvements throughout the development stages. It consists of 20 evaluation benchmarks assessing key capabilities.
Learn more
Phi-3
Small language models (SLMs), a powerful family of small language models, with low cost and low-latency performance. Maximize AI capabilities and lower resource usage, while ensuring cost-effective generative AI implementations across your applications. Accelerate response time in real-time interaction, autonomous systems, low latency apps, and other critical scenarios. Phi-3 can be run in the cloud, on the edge or on the device. This allows for greater flexibility in deployment and operation. Phi-3 models have been developed according to Microsoft AI principles, including accountability, transparency and fairness, reliability, safety and security, privacy, and inclusivity. Operate efficiently in offline environments, where data privacy or connectivity are limited. Expanded context window allows for more accurate, contextually relevant and coherent outputs. Deploy at edge to deliver faster response.
Learn more