Dragon LLM (ex Lingua Custodia)

Crafting AI Models for Finance

[Dragon LLM (ex Lingua Custodia) @DragonLLM]

It’s a new name! We are Dragon LLM and we craft models. https://t.co/SkzLzNKFB3

[Dragon LLM (ex Lingua Custodia) @DragonLLM]

We wanted to share this important news ! https://t.co/s9hYXPkUgd

[Dragon LLM (ex Lingua Custodia) @DragonLLM]

If you are in Paris, don't miss these talks!
📅 our wonderful team will be participating at 2 unmissable events tomorrow on Feb 3, go meet them.

@JG_Barthelemy and @AlexandreTL2 are presenting at the @datacraft "Mamba and AI Factories" event from 16:30 , 55 Rue La Boëtie, 75008.
👉 https://t.co/2JVFAgJ6hB

Gaëtan Caillaud will be joining an AI-in-Finance round table organised by @LouisBachelier in collaboration with @Genci_fr and AI Factory France at Palais Brongniart from 16:30.
👉 https://t.co/JbfFbmZOgG

Sign up for these events, see you there!

[Alexandre TL @AlexandreTL2]

Well, works really great compared to Diff Attn v1! 0.01 loss gap with a faster model

[Dragon LLM (ex Lingua Custodia) @DragonLLM]

https://t.co/dBM2pTJ38s

[Dragon LLM (ex Lingua Custodia) @DragonLLM]

@Pydantic #logfire is extremely useful to evaluate performance and we completed by integrating @langfuse, to support our upcoming toy examples evaluations. Follow us if you build for finance (multilingual).

[Dragon LLM (ex Lingua Custodia) @DragonLLM]

https://t.co/xbQMyQoZwu

[Dragon LLM (ex Lingua Custodia) @DragonLLM]

The chosen model is a fine tuned Qwen3 Reasoning 8B, we can evaluate its ability to call tools and produce structured outputs. Our Open Finance models are all there :
https://t.co/1Vkz9mzhY5

[Alexandre TL @AlexandreTL2]

This is the best I got for Muon on a hybrid architecture compared to AdamW. Anyone knows what could be happening here ?

[Dragon LLM (ex Lingua Custodia) @DragonLLM]

We can only agree with @Lagarde latest speech on EU risk of lagging on #AI.
As @AndreeaNiculcea puts it (c) ,

"We become users of someone else’s models, someone else’s compute, someone else’s innovation — with our margins squeezed and our clients drifting to whoever offers real intelligence, not generic chatbots."
#Hint 👉 Dragon LLM is not generic.

The full transcript is worth reading :
https://t.co/FghkGsEVym

[Dragon LLM (ex Lingua Custodia) @DragonLLM]

🥳 #Adopt_AI - Grand Palais is rapidly approaching!
Iconic event at an iconic venue! 😍

We'll be at booth F6—we'd love to see you there! 🤗

📅 25-26 November
🗺️ The Grand Palais, Paris 🥖

👉 https://t.co/GVHMOtGyFo

[Dragon LLM (ex Lingua Custodia) @DragonLLM]

@mervenoyann @huggingface https://t.co/cv1gfk4ddm

[Dragon LLM (ex Lingua Custodia) @DragonLLM]

@mervenoyann @huggingface Dragon LLM

[Dragon LLM (ex Lingua Custodia) @DragonLLM]

If you would enjoy some ready made cookbooks or recipes to use them with @langchain @LLamaIndex @Pydantic_ai or @Mastra, just ❤️ this post.

[Dragon LLM (ex Lingua Custodia) @DragonLLM]

Introducing LLM Pro Finance models with @AgefiFrance today.
‣ Gemma Pro Finance 12B
‣ Qwen Pro Finance 32B
‣ Llama Pro Finance 70B
They are fine tuned for FR/EN finance and show significantly better performance vs base models. Find them here 👇

[Dragon LLM (ex Lingua Custodia) @DragonLLM]

One more 🍪: try or train the two Open Finance models:
‣ Llama Open Finance 8B
‣ Qwen Open Finance R 8B
https://t.co/1Vkz9mzhY5

[Dragon LLM (ex Lingua Custodia) @DragonLLM]

Today is the day. Parlez-vous finance en français dans le texte?
@DragonLLM releases its fine tuned models for french finance. Stay tuned.

[Dragon LLM (ex Lingua Custodia) @DragonLLM]

These LLM-Pro-Finance models will be presented at the AGEFI AMTech Event on Nov, 4th. Join us to see live demonstrations and learn how these models can transform financial operations in both English and French-speaking markets.