AMD Announces OLMo, Its First Open LLM
AMD has launched OLMo, its first fully open large language model, designed for data centers and smaller organizations. It runs on AMD GPUs, offers strong performance, and is free for developers.
Read original article
AMD has announced its first fully open large language model (LLM) named OLMo, which is designed to enhance AI capabilities for data centers and smaller organizations. The model can be downloaded and run on AMD's Instinct MI250 GPUs and Ryzen AI PCs equipped with neural processing units (NPUs). OLMo features reasoning and chat capabilities similar to other LLMs, such as OpenAI's GPT-4o. The model was pre-trained using a cluster of Instinct GPUs and a dataset of 1.3 trillion tokens. AMD's training process for OLMo involved three stages: pretraining, supervised fine-tuning, and alignment to human preferences. The model has shown strong performance in various benchmarks, particularly in areas like science, coding, and mathematics. It also performed comparably to other open-source LLMs in responsible AI benchmarks, which assess the model's interaction qualities and language toxicity. AMD is making OLMo available for free to developers, allowing them to customize the model for their specific needs.
- AMD has launched OLMo, its first fully open large language model.
- OLMo can run on AMD Instinct MI250 GPUs and Ryzen AI PCs.
- The model was trained in three stages to enhance its capabilities.
- OLMo performed well in benchmarks, particularly in science and coding.
- The model is available for free, enabling customization for developers.
Related
How to run an LLM on your PC, not in the cloud, in less than 10 minutes
You can easily set up and run large language models (LLMs) on your PC using tools like Ollama, LM Suite, and Llama.cpp. Ollama supports AMD GPUs and AVX2-compatible CPUs, with straightforward installation across different systems. It offers commands for managing models and now supports select AMD Radeon cards.
AMD Unveils Its First Small Language Model AMD-135M
AMD has launched its first small language model, AMD-135M, trained on 670 billion tokens. It features speculative decoding for improved speed and is open-sourced to foster AI community collaboration.
NVLM 1.0: Nvidia new open-source model
NVIDIA's NVLM 1.0 introduces multimodal large language models excelling in vision-language tasks, with the 72B version showing improved text performance, novel architecture, and open-sourced resources for community benefit.
Nvidia releases NVLM 1.0 72B open weight model
NVIDIA launched NVLM 1.0, featuring the open-sourced NVLM-D-72B model, which excels in multimodal tasks, outperforms competitors like GPT-4o, and supports multi-GPU loading for text and image interactions.
OpenCoder: Open-Source LLM for Coding
OpenCoder is an open-source large language model for code generation, offering resources like model weights and training data. It aims to match proprietary models while promoting transparency and accessibility.
1 commentsRelated
How to run an LLM on your PC, not in the cloud, in less than 10 minutes
You can easily set up and run large language models (LLMs) on your PC using tools like Ollama, LM Suite, and Llama.cpp. Ollama supports AMD GPUs and AVX2-compatible CPUs, with straightforward installation across different systems. It offers commands for managing models and now supports select AMD Radeon cards.
AMD Unveils Its First Small Language Model AMD-135M
AMD has launched its first small language model, AMD-135M, trained on 670 billion tokens. It features speculative decoding for improved speed and is open-sourced to foster AI community collaboration.
NVLM 1.0: Nvidia new open-source model
NVIDIA's NVLM 1.0 introduces multimodal large language models excelling in vision-language tasks, with the 72B version showing improved text performance, novel architecture, and open-sourced resources for community benefit.
Nvidia releases NVLM 1.0 72B open weight model
NVIDIA launched NVLM 1.0, featuring the open-sourced NVLM-D-72B model, which excels in multimodal tasks, outperforms competitors like GPT-4o, and supports multi-GPU loading for text and image interactions.
OpenCoder: Open-Source LLM for Coding
OpenCoder is an open-source large language model for code generation, offering resources like model weights and training data. It aims to match proprietary models while promoting transparency and accessibility.