Weekly digest

Deterministic Markdown built from the latest snapshot, ready to paste into the newsletter. No model writes this text.
# Hugging Face London: Community Pulse, week of 2026-10-07

What moved on the Hugging Face Hub, taken 2026-10-07 12:54 UTC. Week-on-week deltas appear once seven days of snapshots exist.

## Trending models

- [Cloudflare/clef](https://huggingface.co/Cloudflare/clef) by Cloudflare: image text to text, 27B params, 1.8k likes.
- [autotrust/JEV-27B-VL](https://huggingface.co/autotrust/JEV-27B-VL) by autotrust: image text to text, 28B params, 1.5k likes.
- [autotrust/GEV-26B-Decide](https://huggingface.co/autotrust/GEV-26B-Decide) by autotrust: text classification, 26B params, 982 likes.
- [google/embeddinggemma-2](https://huggingface.co/google/embeddinggemma-2) by google: feature extraction, 744M params, 787 likes.
- [Aleph-Alpha/Kolibri-1](https://huggingface.co/Aleph-Alpha/Kolibri-1) by Aleph-Alpha: text generation, 78B params, 754 likes.

## Trending datasets

- [XiaomiMiMo/MiMo-V2.6-RL-oss](https://huggingface.co/datasets/XiaomiMiMo/MiMo-V2.6-RL-oss) by XiaomiMiMo: 849 likes.
- [datasocial/tiktok-5.6B-videos](https://huggingface.co/datasets/datasocial/tiktok-5.6B-videos) by datasocial: 85 likes.
- [nisten/opus5-5-doctor-patient-conversations-all-human-diseases](https://huggingface.co/datasets/nisten/opus5-5-doctor-patient-conversations-all-human-diseases) by nisten: 270 likes.
- [espnet/yodas3](https://huggingface.co/datasets/espnet/yodas3) by espnet: 217 likes.
- [ankitjh4/bharat-government-documents](https://huggingface.co/datasets/ankitjh4/bharat-government-documents) by ankitjh4: 54 likes.

## Trending Spaces

- [MiniMax H3 Turbo LoRA (Pepe104/MiniMax-H3-Turbo-Lora-UNCENSORED)](https://huggingface.co/spaces/Pepe104/MiniMax-H3-Turbo-Lora-UNCENSORED) by Pepe104: gradio, 1.2k likes. Video generation with a synchronized soundtrack
- [The ultimate guide to multi-harness RL (FineEnvs/multi-harness-rl)](https://huggingface.co/spaces/FineEnvs/multi-harness-rl) by FineEnvs: docker, 184 likes. Train open models with RL inside real agent harnesses
- [Qwen Image 2.1 Uncensored GGUF Studio (arudradey/qwen-image-2.1-uncensored-gguf)](https://huggingface.co/spaces/arudradey/qwen-image-2.1-uncensored-gguf) by arudradey: gradio, 348 likes. Qwen-Image-2.1 Uncensored GGUF demo on ZeroGPU
- [Jev Decision Index (multimodalart/jev-decision-index)](https://huggingface.co/spaces/multimodalart/jev-decision-index) by multimodalart: static, 490 likes. Benchmarks and news on various repros of TypeSafe's Jev
- [Wan2.2 14B Preview (kulkas2pintu/wan777)](https://huggingface.co/spaces/kulkas2pintu/wan777) by kulkas2pintu: gradio, 362 likes. generate a video from an image with a text prompt

## Papers to watch

- [Rethinking Cross-Tokenizer On-Policy Distillation: From Alignment Coverage to Supervision Reliability](https://huggingface.co/papers/2610.08448): 147 upvotes, 1 Space on the Hub.
- [DuoMatching: Joint-Marginal Distribution Matching for Few-Step Video Generation](https://huggingface.co/papers/2610.03543) from ByteDance: 57 upvotes, 1 Space on the Hub.
- [TRACE: Rollout-Guided Quantization-Aware Training for FP4 Reinforcement Learning of MoE Language Models](https://huggingface.co/papers/2610.07767) from Qwen: 41 upvotes, 1 Space on the Hub.
- [EVISKILL: Grounding Skill Evolution in Replayable Evidence](https://huggingface.co/papers/2610.05030) from DEEP Group at Jilin University: 32 upvotes, 1 Space on the Hub.
- [From Evidence to Action: How Tool-Using Agents Fail](https://huggingface.co/papers/2610.07753) from National University of Singapore: 29 upvotes, 1 Space on the Hub.

## London and UK activity

- Stability AI: [stabilityai/SAME-L](https://huggingface.co/stabilityai/SAME-L) updated 2026-10-06, 26 likes.
- Stability AI: [stabilityai/SAME-S](https://huggingface.co/stabilityai/SAME-S) updated 2026-10-06, 15 likes.
- PolyAI: [PolyAI/minds14](https://huggingface.co/datasets/PolyAI/minds14) updated 2025-08-12, 111 likes.
- PolyAI: [PolyAI/banking77](https://huggingface.co/datasets/PolyAI/banking77) updated 2024-09-10, 108 likes.
- The Alan Turing Institute: [alan-turing-institute/turing-synthetic-radar-dataset](https://huggingface.co/datasets/alan-turing-institute/turing-synthetic-radar-dataset) updated 2026-06-01, 52 likes.
- The Alan Turing Institute: [alan-turing-institute/t0-s1.1-32B](https://huggingface.co/alan-turing-institute/t0-s1.1-32B) updated 2026-05-27, 0 likes.
- Imperial College London: [ImperialCollegeLondon/health_fact](https://huggingface.co/datasets/ImperialCollegeLondon/health_fact) updated 2024-01-18, 28 likes.
- ElevenLabs: [elevenlabs/tts](https://huggingface.co/spaces/elevenlabs/tts) updated 2024-10-17, 624 likes.
- Graphcore: [Graphcore/GTSQA](https://huggingface.co/datasets/Graphcore/GTSQA) updated 2025-11-07, 2 likes.


Source: Hugging Face Hub API via the Community Pulse dashboard. 41 API calls, seed list 2026-10-07.