Meta released Llama 3.3 70B, which matches the level of the latest 405B model at a lower cost. Already available on @GroqInc
OPEN SOURCE
-
Llama 3.3 Community Launch Excitement Announced
By
–
Excited for the community to get up and running with Llama 3.3!
-
Meta releases Llama 3.3 70B Instruct model
By
–
Hey congrats, my dudes at meta open released Llama 3.3 70B Instruct:
-
Llama 3.3 70B Instruct Now Available on Hugging Chat
By
–
Llama 3.3 70B Instruct now on Hugging Chat! Try it out here: https://
huggingface.co/chat/models/me
ta-llama/Llama-3.3-70B-Instruct
… -
Meta Defies Scaling Laws with Llama 3.3 70B Model
By
–
Meta is challenging “death of scaling law” rumors with Llama 3.3 70B.
They’re defying traditional scaling limits, improving models without increasing parameters or changing the fundamental model architecture. Quality matters, not just quantity. https://
hubs.la/Q02-LBLK0 -
Meta Releases Llama 3.3 70B with 405B-Level Performance
By
–
BOOOOM! Meta released Llama 3.3 70B – 128K context, multilingual, enhanced tool calling, outperforms Llama 3.1 70B and comparable to Llama 405B Comparable performance to 405B with 6x LESSER parameters Llama 3.3 70B vs 405B: > GPQA Diamond (CoT): 50.5% vs 49.0%
> Math -
Llama 3.1 Tool Use Benchmarks Released
By
–
I'm not sure. They even released tool use benchmarks for Llama 3.1
-
Llama 3.3 70B Released: New Features and Language Support
By
–
Llama 3.3 70B – The new license doesn't change anything compared to Llama 3.1 – Supports 8 languages: English, German, French, Italian, Portuguese, Hindi, Spanish, and Thai (no Chinese, Japanese?) – Added "Tool-use" but it was already there…?