Hugging Face Models (Daily)

- **Risk Threshold:** 0.75 (Confidence score required to flag as SPAM) - **Labels:** ['harvesting', 'legitimate'] - **Dataset:** Trained on forensic recruitment data (Swiss/US/UK).



Open: https://huggingface.co/Cata-Risk-Lab/VIPER-Text-Classifier-v1

Open: https://huggingface.co/chowmean/k8s_Qwen2.5-0.5B-Instruct

ADVANCED MECHANICS ENGINE



Open: https://huggingface.co/DreamBig-ML/Advanced_Mechanics_Problem-Solver

An abliterated version of Google's Gemma 3 12B IT created using Heretic. This model has reduced refusals while maintaining model quality, making it suitable as an uncensored text encoder for video generation models like LTX-2.



Open: https://huggingface.co/DreamFast/gemma-3-12b-it-heretic

Eclipse-ERRL-R1-Qwen3-8B



Open: https://huggingface.co/eclipse-ai/Eclipse-ERRL-R1-Qwen3-8B

This model is part of the **PolyPythias** suite, an extension of the Pythia project providing 45 additional training runs across 5 model sizes with 9 different random seeds each. These models enable systematic study of training stability and reproducibility in language models.



Open: https://huggingface.co/EleutherAI/pythia-160m-seed4

Sample: ``` Prompt: Human: What is artificial intelligence?



Open: https://huggingface.co/FlameF0X/anwgpt4-chat

The **JOSIEFIED** model family represents a series of highly advanced language models built upon renowned architectures such as Alibaba’s Qwen2/2.5/3, Google’s Gemma3, and Meta’s LLaMA3/4. Covering sizes from 0.5B to 32B parameters, these models have been significantly modified (*“abliterated”*) and further fine-tuned to **maximize uncensored beha…



Open: https://huggingface.co/Goekdeniz-Guelmez/Josiefied-Qwen3-0.6B-abliterated-v2

This is a trained agent that learned to walk on two legs from scratch!



Open: https://huggingface.co/hamzasheedi/humanoid17

This is a trained agent that learned to walk on two legs from scratch!



Open: https://huggingface.co/hamzasheedi/humanoid18

This is a trained agent that learned to walk on two legs from scratch!



Open: https://huggingface.co/hamzasheedi/humanoid19

We all know the potential of a model reveals itself only when LoRAs are trained. This is my *third* LTX-2 LoRA after Hydraulic press and Inflate it. It follows the quest of porting some the *classic* VFX LoRAs to LTX-2 (which has sound!).



Open: https://huggingface.co/kabachuha/ltx2-cakeify

**Open-source text-to-speech for European languages with voice cloning capabilities** 7B parameter model powered by an AR + Diffusion architecture



Open: https://huggingface.co/kugelaudio/kugelaudio-0-open

**(주)미디어그룹사람과숲과 (주)마커의 LLM 연구 컨소시엄에서 개발된 모델입니다** **The license is cc-by-nc-sa-4.0.**



Open: https://huggingface.co/kyujinpy/KO-Platypus2-7B-ex

**(주)미디어그룹사람과숲과 (주)마커의 LLM 연구 컨소시엄에서 개발된 모델입니다** **The license is cc-by-nc-sa-4.0.**



Open: https://huggingface.co/kyujinpy/KoR-Orca-Platypus-13B

**(주)미디어그룹사람과숲과 (주)마커의 LLM 연구 컨소시엄에서 개발된 모델입니다**



Open: https://huggingface.co/kyujinpy/Sakura-SOLAR-Instruct

This is the **vSearcher** model introduced in paper "InSight-o3: Empowering Multimodal Foundation Models with Generalized Visual Search". The model is finetuned from Qwen2.5-VL-7B-Instruct via RL as a subagent under **vReasoner** GPT-5-mini. For more information on how to use this model, see our GitHub page.



Open: https://huggingface.co/m-Just/InSight-o3-vS

- **Developed by:** [More Information Needed] - **Funded by [optional]:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed]



Open: https://huggingface.co/malhanharsh/zolve-gemma-2b

These are experimental FP8 merges of the LTX2 diffusion model. "All in ones" do not seem to be in the cards, as LTX2 has lots of (large) moving parts, including 2 VAEs for video and audio. So, for the meantime, I'm just going to focus on the diffusion model. For all other models needed to run LTX2, please refer here: https://huggingface.co/Kijai/LTXV2_comfy



Open: https://huggingface.co/Phr00t/LTX2-Rapid-Merges

This repository contains NLP models trained and evaluated by Wikilangs, specifically on **Tumbuka** Wikipedia data. We analyze tokenizers, n-gram models, Markov chains, vocabulary statistics, and word embeddings.



Open: https://huggingface.co/wikilangs/tum

This is a GGUF-quantized version of Qwen3-30B-A3B-Instruct-2507 produced with **ByteShape's ShapeLearn**, which learns the optimal datatype per tensor to maintain high quality even at very low bitlengths.

Daily delta: +7,585 downloads / +30 likes

Open: https://huggingface.co/byteshape/Qwen3-30B-A3B-Instruct-2507-GGUF

** MiniMax-M2.1 Uncensored PRISM Advanced Abliteration**

Daily delta: +5,968 downloads / +31 likes

Open: https://huggingface.co/Ex0bit/MiniMax-M2.1-PRISM

Stream-DiffVSR is a causally conditioned diffusion framework designed for efficient online Video Super-Resolution (VSR). It operates strictly on past frames to maintain low latency, making it suitable for real-time deployment.

Daily delta: +4,980 downloads / +25 likes

Open: https://huggingface.co/Jamichsu/Stream-DiffVSR

Try LFM • Documentation • LEAP • WebGPU demo

Daily delta: +1,902 downloads / +86 likes

Open: https://huggingface.co/LiquidAI/LFM2.5-VL-1.6B

weighted/imatrix quants of https://huggingface.co/vanta-research/atom-80b

Daily delta: +1,154 downloads / +0 likes

Open: https://huggingface.co/mradermacher/atom-80b-i1-GGUF

Daily delta: +896 downloads / +0 likes

Open: https://huggingface.co/llamafactory/tiny-random-qwen3

static quants of https://huggingface.co/vanta-research/atom-80b

Daily delta: +560 downloads / +0 likes

Open: https://huggingface.co/mradermacher/atom-80b-GGUF

weighted/imatrix quants of https://huggingface.co/vanta-research/atom-27b

Daily delta: +471 downloads / +0 likes

Open: https://huggingface.co/mradermacher/atom-27b-i1-GGUF

This model was created by Tanaos with the Artifex Python library.

Daily delta: +442 downloads / +4 likes

Open: https://huggingface.co/tanaos/tanaos-NER-v1

History:

Daily delta: +357 downloads / +1 likes

Open: https://huggingface.co/nphSi/Z-Image-Lora

This model is provided for efficient **CPU** inference using llama.cpp

Daily delta: +296 downloads / +0 likes

Open: https://huggingface.co/trucmtnguyen/Llama-3.1-8B-Instruct-LoRA-Issue-Tagger-GGUF-Inference

**A novel transformer architecture with deterministic Token-Routed MLP and INL Dynamics.**

Daily delta: +227 downloads / +3 likes

Open: https://huggingface.co/Pacific-Prime/pacific-prime

**KarantaOCR** is an open-source document OCR and processing model designed for **high-accuracy text extraction in African languages**. The model focuses on preserving language-specific characters and diacritics that are often lost, normalized, or mis-transcribed by existing OCR systems.

Daily delta: +180 downloads / +5 likes

Open: https://huggingface.co/taresco/KarantaOCR

This model was created by Tanaos with the Artifex Python library.

Daily delta: +147 downloads / +65 likes

Open: https://huggingface.co/tanaos/tanaos-text-anonymizer-v1

📜 Paper   |   💻 GitHub Repository   |   🛠️ Audio.Z.AI

Daily delta: +0 downloads / +17 likes

Open: https://huggingface.co/zai-org/GLM-TTS

The model supports: - Egyptian Arabic text input (language_id = "ar") - Natural prosody and conversational tone - Optional **reference audio prompting** for speaker/style transfer

Daily delta: +0 downloads / +9 likes

Open: https://huggingface.co/oddadmix/chatterbox-egyptian-v0

**TheWhisper-Large-V3-Turbo** is a fine-tuned, high-performance variant of OpenAI’s Whisper Large V3 model — optimized by **TheStage AI** for **real-time**, **low-latency**, and **low-power** speech-to-text (ASR) inference across multiple platforms, including **NVIDIA GPUs** and **Apple Silicon (CoreML)**.

Daily delta: +-255 downloads / +6 likes

Open: https://huggingface.co/TheStageAI/thewhisper-large-v3-turbo

Open: https://huggingface.co/Amudeeshan/WARRIOR

Open: https://huggingface.co/Ananthusajeev190/Dream_viewer_venomoussai

Open: https://huggingface.co/BlackSpaces/IllumiYume-XL-v3.5-Archive

This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.



Open: https://huggingface.co/cody-li/whisper_tuned_test

English | 简体中文 |



Open: https://huggingface.co/CofeAI/FLM-101B

FLM-2 (aka Tele-FLM) is our open-source large language model series. The FLM-2 series demonstrate superior performances at its scale, and sometimes surpass larger models. The currently released versions include (Tele-FLM)[https://huggingface.co/CofeAI/Tele-FLM] and (Tele-FLM-1T)[https://huggingface.co/CofeAI/Tele-FLM-1T]. These models feature a stable, effi…



Open: https://huggingface.co/CofeAI/FLM-2-52B-Instruct-2407

- **Developed by:** BAAI & TeleAI - **Language(s):** English; Chinese; Other languages - **License:** Apache 2.0



Open: https://huggingface.co/CofeAI/Tele-FLM

- **Developed by:** BAAI & TeleAI - **Language(s):** English; Chinese; Other languages - **License:** Apache 2.0



Open: https://huggingface.co/CofeAI/Tele-FLM-1T

Racka



Open: https://huggingface.co/elte-nlp/Racka-4B

A transformer-based language model with adaptive recursive processing mechanism for enhanced text generation.



Open: https://huggingface.co/Girinath11/recursive-language-model-48m

Collection of female characters trained for ZImage turbo Each character has its own trigger word contained in its file: 3V3,CL41R3,S4LL1,N0R4,C4M1,V1CT0R14,AL1C3,C1ND1 In addition to the trigger word, "a woman" must be entered in the prompt to prevent the male version of the character or something else from appearing.



Open: https://huggingface.co/Hectore/Female_models_ZIT

**HyperCLOVAX-SEED-Think-32B-heretic**은 naver-hyperclovax/HyperCLOVAX-SEED-Think-32B를 기반으로, 사후(weight editing) 방식으로 **과잉 거부(refusal) 성향을 완화**하는 방향의 수정이 적용된 변형 모델입니다.



Open: https://huggingface.co/hostkimjang/HyperCLOVAX-SEED-Think-32B-heretic

***AstraX-Redefined*** is a refined stylistic LoRA built on the visual philosophy of ***"HyperX-Sentience/AstraXL"***, focused on warmth, softness, and emotionally present characters. The style blends clean 2D anime illustration with a subtle sense of depth that makes characters feel grounded and alive rather than flat.



Open: https://huggingface.co/HyperX-Sentience/AstraX-Redefined