Llama 2
A series of open-weight large language models released by Meta, available in multiple parameter sizes including 7B, 13B, and 70B. It supports local deployment and is among the first open-source LLMs to achieve broad commercial adoption.
Core Facts
When Meta previously released LLaMA 2 and LLaMA 3, it used a custom community license that set additional authorization thresholds for companies with more than 700 million monthly active users.
Meta's Llama series license explicitly prohibits use by commercial products with more than 700 million monthly active users and requires derivative models to retain brand identifiers.
CodeLlama was trained by Meta through continued pre-training and instruction fine-tuning of Llama 2 in the code domain, offered in multiple parameter scales including 7B, 13B, and 34B.
Timeline (last 90 days)
GQA compresses the KV Cache by about 8x relative to MHA and has become the standard choice for mainstream open-source models such as Llama 2/3, Qwen, and Mistral.
The releases of Llama 2 and Llama 3 broke the monopoly of closed-source models over high-performance AI capabilities.
Llama 3 relaxed the license restrictions to some extent compared to Llama 2, but it is still not an OSI-certified standard open-source license.
Meta has made the weights of Llama 2/3 publicly available, but with specific commercial use restrictions.
The LLaMA leak prompted Meta to adjust its licensing strategy in the subsequent releases of Llama 2 and Llama 3.
Llama 2 is one of the first commercially successful open-weight models, released by Meta.
Llama 2 is available in multiple versions with 7 billion, 13 billion, and 70 billion parameters.
Meta's Llama 2 (70-billion-parameter version) used 1.8 million GPU hours for training.
Between 2023 and 2024, Meta open-sourced the Llama 2 and Llama 3 series in succession, causing advanced model architectures and training methodologies to rapidly spread throughout the industry, compressing the technology gap window between companies from 6–12 months to 2–3 months.
The GQA technique was initially proposed by Google Research in 2023 and was subsequently widely adopted by mainstream models such as Llama 2 and Mistral.
5 more timeline events
All Facts (19)
When Meta previously released LLaMA 2 and LLaMA 3, it used a custom community license that set additional authorization thresholds for companies with more than 700 million monthly active users.
75%VerifiedMeta's Llama series license explicitly prohibits use by commercial products with more than 700 million monthly active users and requires derivative models to retain brand identifiers.
65%VerifiedCodeLlama was trained by Meta through continued pre-training and instruction fine-tuning of Llama 2 in the code domain, offered in multiple parameter scales including 7B, 13B, and 34B.
65%UnverifiedMistral的7B模型在发布时超越了Llama 2 13B的表现
85%UnverifiedMeta's Llama 3 made extensive use of synthetic data generated by Llama 2 during training to enhance specific capabilities.
70%UnverifiedGQA compresses the KV Cache by about 8x relative to MHA and has become the standard choice for mainstream open-source models such as Llama 2/3, Qwen, and Mistral.
50%UnverifiedThe releases of Llama 2 and Llama 3 broke the monopoly of closed-source models over high-performance AI capabilities.
50%UnverifiedLlama 3 relaxed the license restrictions to some extent compared to Llama 2, but it is still not an OSI-certified standard open-source license.
50%UnverifiedMeta has made the weights of Llama 2/3 publicly available, but with specific commercial use restrictions.
50%UnverifiedThe LLaMA leak prompted Meta to adjust its licensing strategy in the subsequent releases of Llama 2 and Llama 3.
50%UnverifiedLlama 2 is one of the first commercially successful open-weight models, released by Meta.
50%UnverifiedLlama 2 is available in multiple versions with 7 billion, 13 billion, and 70 billion parameters.
50%UnverifiedMeta's Llama 2 (70-billion-parameter version) used 1.8 million GPU hours for training.
50%UnverifiedThe GQA technique was initially proposed by Google Research in 2023 and was subsequently widely adopted by mainstream models such as Llama 2 and Mistral.
50%UnverifiedIn the safety report released alongside Llama 2, Meta acknowledged that safety fine-tuning caused the model's scores to decline on certain benchmarks.
50%UnverifiedAndrej Karpathy implemented the llama2.c project for Llama 2 inference in approximately 700 lines of C code.
50%UnverifiedLlama 2 的 chat 模板使用 [INST] 和 [/INST] 标记界定用户指令，使用 <<SYS>> 和 <</SYS>> 标记界定系统提示
50%UnverifiedMeta的Llama系列最新版本为Llama 4
50%UnverifiedBetween 2023 and 2024, Meta open-sourced the Llama 2 and Llama 3 series in succession, causing advanced model architectures and training methodologies to rapidly spread throughout the industry, compressing the technology gap window between companies from 6–12 months to 2–3 months.
50%