←Search results

Search “Hugging Face”

By relevance · Total 1193 results Clear search

Wednesday

  1. Ai2 Blog

    Ai2's Bolmo byte-level language model research is published in Nature, and a new checkpoint is released

    Ai2's Bolmo byte-level language model research has been published in Nature, and a new checkpoint has been released on Hugging Face, extending the byteifying method from Olmo to Qwen 3 8B and Llama 3 8B, yielding Bwen 8B and BlamaLlama-B 8B. Bwen 8B is the strongest byteified model to date, surpassing Bolmo 7B on the comprehensive evaluation suite. Ai2 has also released a Stage 1 checkpoint, which freezes the original model and trains only the newly added byte-level components.

    Matched fieldsSummary、Body

    #lab#Papers/Research#Open-source ecosystem#English text is being prepared.
  2. Hugging Face

    NVIDIA Fine-Tunes the Nemotron Family, Achieving Gold-Medal-Level Results at IOI and IMO

    NVIDIA used the same fine-tuning recipe to turn Nemotron into a specialized model for competitive programming and math olympiad: at IOI 2026, Nemotron-3-Ultra-CC scored 535.4 points (out of 600), and the IMO system scored 30 points (out of 42), exceeding the official gold medal line. The recipe includes a strong base model, domain problems and reasoning trajectory data, SFT and RL post-training, and a generate-evaluate-improve inference loop. The related SFT and RL checkpoints, training datasets, the Nemotron-IMO-Bench benchmark, and the NeMo-Skills inference pipeline have been open-sourced on Hugging Face.

    math olympiad: at IOI 2026, Nemotron-3-Ultra-CC scored 535.4 points (out of 600), and the IMO system scored 30 points (out of 42), exceeding the official gold medal line. The recipe includes a strong base model, domain problems and reasoning trajectory data, SFT and RL post-training, and a generate-evaluate-improve inference loop. The related SFT and RL checkpoints, training datasets, the Nemotron-IMO-Bench benchmark, and the NeMo-Skills inference pipeline have been open-sourced on Hugging Face.

    Matched fieldsSummary、Body

    #lab#Model releases#English text is being prepared.#Reasoning

Tuesday

  5. Clément Delangue

    Reflection launches Beam, an open-source agentic model with 501B total parameters and 23B active

    Reflection has released Beam, an efficient open-source agentic model with 501B total parameters and 23B active parameters, emphasizing frontier reasoning efficiency and advancing the Western open-source frontier on coding and agentic tasks, trained end-to-end from scratch. Full weights will be released this month. Hugging Face CEO Clément Delangue reposted the news.

    Matched fieldsSummary

    #editorial#English text is being prepared.#Model releases#English text is being prepared.
  7. Cailian Press

    Inference spending to surpass training for the first time in 2026, rise of Token factories to change AI infrastructure investment logic

    Gartner predicts that global inference spending will reach $23.3 billion in 2026, surpassing training spending of $19 billion for the first time and accounting for 55% of total AI IaaS spending; a CAICT report predicts that in 2026 inference computing power will account for 70.5% of total AI computing load. Multiple industry insiders point out that Hugging Face weight downloads and OpenRouter Token call volumes are often conflated as overseas expansion results, but Token call volume does not equal revenue; Token going global is essentially inference services going global, which is more directly related to actual revenue. Public cloud giants, independent MaaS inference service providers, and GPU vendors are all laying out Token factories, with compliance and global low-latency distribution being the main current bottlenecks.

    total AI IaaS spending; a CAICT report predicts that in 2026 inference computing power will account for 70.5% of total AI computing load. Multiple industry insiders point out that Hugging Face weight downloads and OpenRouter Token call volumes are often conflated as overseas expansion results, but Token call volume does not equal revenue; Token going global is essentially inference services going global, which is more directly related to actual revenue. Public cloud giants, independent MaaS infe

    Matched fieldsSummary、Body

    #chinese#English text is being prepared.#English text is being prepared.#English text is being prepared.

Monday