Wilame Souza
Commented on If last API message is assistant, it should be continued.If they do this, I would consider it a complete unnecessary indulgence, and I would certainly understand if they didn't. You can easily implement this with ifs and elses, but implementing this directly in the API for all users can benefit you but create problems for other DEVs. Y…Commented on If last API message is assistant, it should be continued.I think your request is a bit exaggerated... This is a feature that needs to be built into the model's capabilities or implemented by you manually. We need to understand that Nebius is a company that resells AI models, it does not produce themCommented on A biblical scene at the city gate of ancient Bethlehem. Boaz, dressed in traditional robes, stands and speaks to a group of elders seated around him. Ruth, a young and modest woman, stands quietly in the background. The atmosphere is dignified and ceremonial, and in the scene an old scroll or document appears as a symbol of redemption. The building is in an ancient Middle Eastern style, with stone walls and arches.What the hell!??!?!!?Created LlaMa 4 Maverick & ScoutCommented on "Fast" DeepSeek-R1If that's the case, then OpenAI's o3 mini is a viable option for you. https://openrouter.ai/openai/o3-mini Very fast and just $1/$4 mtokens Asking for a fast variant of DeepSeek R1 is not very realistic, it is probably unfeasible for Nebius, but let's see if any administrator spe…Upvoted Kokoro TTSUpvoted New DeepSeek R1 ModelUpvoted Auto top-up / balance warningCommented on "Fast" DeepSeek-R1Would you pay if the fast version was almost twice as expensive? If you compare the base version and the fast version of the LlaMa 3.3 you will see that the price difference is almost double. The DeepSeek R1 has a lot of power and uses a lot of resources, and I'm sure a fast vers…Created DeepSeek V3Created Phi4Upvoted Model request: Athene v2 for studioUpvoted Model request for image generationCommented on LlaMa 3.3Great!!! I think there is a display error on the card that shows 25tk/s in the fast version and 60tk/s in the base version 😅Commented on LlaMa 3.3It is really impressive for an Open-Source LLM Can’t wait for LlaMa 4Created LlaMa 3.3Upvoted Gemma 2 27b it contextUpvoted Add quantization infoUpvoted Show model quantization infoCreated Gemma 2 27b it context