ra

kite, mtb, running and ruby

[ra @raulkite_]

@0xSero @MolokaiHex https://t.co/VtbzI8v9aE ?

Too tight maybe. Is there accuracy benchmarks is the model.

If it performs near the original one and is able to run with Sglang or vllm with decent tps and batch with a couple of rtx6000 96gb this could be great

[ra @raulkite_]

@barckcode Pero no me lo has dicho! Supongo que tendrás 8xh100 o similar. Y que ya no será hierro comprado.

[ra @raulkite_]

@danieltvela Mtp of 2 tokens? Can you share your exact vllm command?

Thanks 🙏

[ra @raulkite_]

@ivanfioravanti I hope this new version to spend the half of thinking tokens 😅🎉🎉🎉

[ra @raulkite_]

@stableAPY Vllm takes advantage of this enhancements?

[ra @raulkite_]

@OrganicGPT Would you show us the exact command with parameters that you are using?

Thank you very much

[ra @raulkite_]

@barckcode @danielvigueras Al final has escrito ese post detallado? Gracias

[ra @raulkite_]

@ErickSky @UnslothAI No pasa de 5-8 token/s haciendo offloading casi seguro.

[ra @raulkite_]

@llmdevguy @UnslothAI @Kimi_Moonshot Would you give some feedback if you test this configuration? Thanks 🙏

[ra @raulkite_]

Are you THIS OLD 😅?

[ra @raulkite_]

@geekdegafas Wifi mesh 3 repetidores

[ra @raulkite_]

Madre mía lo que encontré ayer en casa @migueldeicaza

[ra @raulkite_]

@Hesamation @maximelabonne Any organized resource after this?

[ra @raulkite_]

@skalskip92 I mean if pose points have associated a person id that is consistent ( same person, same id) during the scene.

I usually have done this in 2 steps, tracking people, pose estimation and post processing iou of both outputs to pair person id with pose.

[ra @raulkite_]

@skalskip92 Does it track people id?

[Google DeepMind @GoogleDeepMind]

We're thrilled to announce SignGemma, our most capable model for translating sign language into spoken text. 🧏

This open model is coming to the Gemma model family later this year, opening up new possibilities for inclusive tech.

Share your feedback and interest in early testing → https://t.co/C4rV2be4mL

[ra @raulkite_]

@reach_vb RAM needed? Too much for sure.

[ra @raulkite_]

@javisantana Lo haces. En las carreras sale ese puntito más

[MULTIDATA @multidata_eu]

Join us for the third MULTIDATA webinar: a hands-on intro to our project and pipeline!🗓️ May 19, 4 PM (CET)🎤 Cristóbal Pagán (project coordinator)
🔍 Learn about speech transcription, gesture tracking, and more — no tech skills needed!
🎟️ Save your spot: https://t.co/szRDpPzCrA