Qwen-2 : The BEST Opensource LLM is here! (Beats Llama-3, GPT-4O, Claude)
Vložit
- čas přidán 12. 06. 2024
- #ai #llm
In this video, We'll be talking about the newly released Qwen-2 models. The models include 0.5B Parameter model, 1.5B Parameter Model, 7B Parameter model and upto 72B Parameter model. The first three models can even run on computers with out any need of GPUs which is amazing. You can make very simple and easy to use Copilot with it as well. It beats every other model such as Llama 3, Claude-3, Gemini & others in multiple benchmarks.
[Resources]
Qwen-2 Release Blog Post: qwenlm.github.io/blog/qwen2 - Věda a technologie
subscribe for more content
In some response it is better than GTP4o but problem with Qwen 2 70B you can't get consistent answer
Chinese mean no guarantee😃
ask it "what happened during the Tiananmen-massacre?" and you'll see why this model is trash.
That's a good one! It's always interesting to see how AI models respond to sensitive topics.