Tag: Llama 3
-
LLama 3 vs GPT-4
Llama 3 is a cutting-edge large language model introduced by Meta AI on April 18, 2024. This model family offers three sizes: 8B, 70B, and 400B. The 8B and 70B versions are available to the public, whereas the 400B version is currently undergoing training. Llama 3 boasts benchmark scores that match or surpass those of…
-
Llama-3 Is Not Really Censored
It turns out that Llama-3, right out of the box, is not heavily censored. In the release blog post, Meta indicated that we should expect fewer prompt refusals, and this appears to be accurate. For example, if you were to ask the Llama-3 70 billion model to tell you a joke about women or men,…
-
LLama 3 on Groq
Okay, so this is the actual speed of generation, and we’re achieving more than 800 tokens per second, which is unprecedented. Since the release of LLama 3 earlier this morning, numerous companies have begun integrating this technology into their platforms. One particularly exciting development is its integration with Groq Cloud, which boasts the fastest inference…