view post Post 629 sharing the slides from my talk at Kernel Panic in MadridIt's basically "The ultimate guide to multi-harness RL" turned slides and condensed into a 20 min talk FineEnvs/multi-harness-rl-slidescongrats to @Helmcode for the organization!blog: FineEnvs/multi-harness-rl See translation β€οΈ 1 1 π₯ 1 1 + Reply
view post Post 2363 Google releases EmbeddingGemma 2, a new open embedding model that runs locally on 0.5GB RAM.The 740M parameter Apache 2.0 model combines a 270M text model with vision (170M) + audio (300M).Run & train the model via Unsloth.GGUF: unsloth/embeddinggemma-2-GGUFGuide: https://unsloth.ai/docs/models/embeddinggemma-2 See translation π 6 6 β€οΈ 5 5 π₯ 4 4 π 4 4 π 3 3 + Reply
unsloth/embeddinggemma-2-GGUF Feature Extraction β’ 0.3B β’ Updated about 19 hours ago β’ 11.5k β’ 165
view article Article Welcome RL Environments to the hub +6 burtenshaw, AdithyaSK, sergiopaniego, xeophon, ryanmarten, merve, lhoestq, julien-c β’ 10 days ago β’ 25
Running Featured 511 Jev Decision Index π¬ 511 Benchmarks and news on various repros of TypeSafe's Jev
PixelUMM: Encoder-Free Unified Image and Video Understanding and Generation Paper β’ 2609.38597 β’ Published 9 days ago β’ 32
DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression Paper β’ 2609.19969 β’ Published 21 days ago β’ 224
Running 193 The ultimate guide to multi-harness RL π 193 Train open models with RL inside real agent harnesses
Running on CPU Upgrade 85 MiMo RL Environment Explorer π§ 85 Explore the MiMo-V2.6 RL environments and run rollouts
view post Post 8948 Unsloth has surpassed 500M model downloads on Hugging Face! π¦₯π€Qwen3.8-27B GGUF is already Unslothβs #1 most-downloaded model ever.Thanks for all your support! Follow us: unsloth See translation 1 reply Β· π₯ 31 31 π€ 11 11 π 8 8 β€οΈ 6 6 β 4 4 π 2 2 π€― 2 2 π§ 1 1 π 1 1 π 1 1 π€ 1 1 + Reply