LLMS

→ View original post on X — @thom_wolf

Mistral Releases 123B Model: New Open-Weight Option Between 70B and 405B

By

@thom_wolf

–

24 July 2024 17h50

And if you think there is too much distance between the 70B and the 405B the good folks at Mistral have now added a very nice 123B with some cool capabilities on code/math/multilingual What a week my friends, what a week for
open-weight models. And it’s only Wednesday

Mistral Large 2 Now Available Free on Le Chat

By

–

24 July 2024 17h42

You can use Mistral Large 2 on Le Chat — it's free! https://
chat.mistral.ai

→ View original post on X — @dotcsv

Mistral Large 2 Update Challenges GPT-4o and Sonnet

By

@dotcsv

–

24 July 2024 17h39

¡MISTRAL LARGE 2! Los franceses actualizan su modelo Large llevándolo a estar cerca de los mayores (GPT-4o, Sonnet 3.5). Es una mejora importante respecto al anterior modelo Mistral Large, pero claro… Muy a la par con Llama 3.1, que a diferencia de este modelo, es open

Mistral Large Improved Alignment and Instruction Capabilities Performance

By

–

24 July 2024 17h38

Compared to the previous Mistral Large, much more effort was dedicated to alignment and instruction capabilities. On WildBench, ArenaHard, and MT Bench, it performs on par with the best models, while being significantly less verbose. (4/N)

Mistral Large Instruct 2407 Model Released on HuggingFace

By

–

24 July 2024 17h38

The model is available (for research purposes only!) on HuggingFace: https://
huggingface.co/mistralai/Mist
ral-Large-Instruct-2407
…
Blog post:

Mistral Large 2 outperforms Llama 3.1 on Multilingual MMLU

By

–

24 July 2024 17h38

On Multilingual MMLU, the performance of Mistral Large 2 significantly outperforms Llama 3.1 70B base (+6.3% average over 9 languages) and is on par with Llama 3 405B (-0.4% below). (3/N)

Mistral Large 2 outperforms Llama 3.1 405B on coding benchmarks

By

–

24 July 2024 17h38

On HumanEval and on MultiPL-E, Mistral Large 2 outperforms Llama 3.1 405B instruct, and scores just below GPT-4o. On MATH (0-shot, without CoT) it only falls behind GPT-4o.
(2/N)

Mistral Large 2: New 123B Model Outperforms Llama 3.1 405B

By

–

24 July 2024 17h38

Today, we release Mistral Large 2, the new version of our largest model. Mistral Large 2 is a 123B-parameter model with a 128k context window. On many benchmarks (notably in code generation and math), it is superior or on par with Llama 3.1 405B. Like Mistral NeMo, it was trained