Collection of Various Compression Schemes for Gemma 4
Prithiv Sakthi PRO
prithivMLmods
AI & ML interests
computer vision, nlp, multimodality
- HuggingFace Fellow🤗
Recent Activity
updated a collection about 5 hours ago
Gemma-4 Compression(s) updated a collection about 6 hours ago
Gemma-4 Compression(s) updated a collection about 7 hours ago
Gemma-4 Compression(s)Organizations
Version 2 in the Unredacted series, with much lower refusal limits, is available in different compression schemes.
-
prithivMLmods/Qwen3-VL-32B-Instruct-v2-MAX-MXFP4
Image-Text-to-Text • 19B • Updated • 7 • 2 -
prithivMLmods/Qwen3.5-9B-abliterated-v2-MAX
Image-Text-to-Text • 9B • Updated • 1.67k • 2 -
prithivMLmods/Qwen3.5-9B-abliterated-v2-MAX-NVFP4
Image-Text-to-Text • 7B • Updated • 10 • 1 -
prithivMLmods/Qwen3.5-9B-abliterated-v2-MAX-FP8
Image-Text-to-Text • 9B • Updated • 3 • 1
capable of accurately locating and understanding 'any' object | State: Experimental, Category: Object Detection, High-depth analysis in visual tasks
Expert Image Captioning System
-
prithivMLmods/Gliese-Qwen3.5-27B-Abliterated-Caption
Image-Text-to-Text • 27B • Updated • 450 • 6 -
prithivMLmods/Gliese-Qwen3.5-9B-Abliterated-Caption
Image-Text-to-Text • 9B • Updated • 16k • 39 -
prithivMLmods/Gliese-Qwen3.5-4B-Abliterated-Caption
Image-Text-to-Text • 5B • Updated • 3.05k • 7 -
prithivMLmods/Gliese-Qwen3.5-2B-Abliterated-Caption
Image-Text-to-Text • 2B • Updated • 2.3k • 7
Collection of Region Bounding LoRAs
-
prithivMLmods/QIE-2509-Object-Mover-Bbox
Image-to-Image • Updated • 41 • • 2 -
prithivMLmods/QIE-2511-Object-Mover-Bbox
Image-to-Image • Updated • 156 • • 4 -
prithivMLmods/QIE-2509-Object-Remover-Bbox-v3
Image-to-Image • Updated • 3.48k • • 9 -
prithivMLmods/QIE-2511-Object-Remover-Bbox-v3
Image-to-Image • Updated • 743 • • 3
Collection of Compressed Multimodal VLM Editions on the Hub [ vLLM / LLM Compressor ]
-
prithivMLmods/Gliese-CUA-Tool-Call-8B-FP8
Image-Text-to-Text • 8B • Updated • 9 • 2 -
prithivMLmods/Gliese-OCR-7B-Post2.0-final-FP8
Image-Text-to-Text • 8B • Updated • 7 • 1 -
prithivMLmods/MedMO-8B-FP8
Image-Text-to-Text • 9B • Updated • 5 • 1 -
prithivMLmods/Jan-v2-VL-med-FP8
Image-Text-to-Text • 9B • Updated • 6 • 1
Collection of FP8 compression techniques, Diffusers–Transformers converted weights, and more for QIE.
multi-stage trained continual "abliteration" approach for the qwen3-vl series models
-
prithivMLmods/Qwen3-VL-4B-Instruct-Unredacted-MAX
Image-Text-to-Text • 4B • Updated • 1.86k • 17 -
prithivMLmods/Qwen3-VL-4B-Thinking-Unredacted-MAX
Image-Text-to-Text • 4B • Updated • 28 • 1 -
prithivMLmods/Qwen3-VL-8B-Instruct-Unredacted-MAX
Image-Text-to-Text • 9B • Updated • 856 • 10 -
prithivMLmods/Qwen3-VL-8B-Thinking-Unredacted-MAX
Image-Text-to-Text • 9B • Updated • 43 • 3
Iterations of my doc ocr models timeline of continual training built on top of qwen-vl models.
-
prithivMLmods/Camel-Doc-OCR-062825
Image-Text-to-Text • 8B • Updated • 57 • 13 -
prithivMLmods/Megalodon-OCR-Sync-0713
Image-Text-to-Text • 4B • Updated • 22 • 4 -
prithivMLmods/Camel-Doc-OCR-080125
Image-Text-to-Text • 8B • Updated • 227 • 8 -
prithivMLmods/Gliese-OCR-7B-Post1.0
Image-Text-to-Text • 8B • Updated • 62 • 13
adapter LoRA developed for Qwen’s Qwen-Image-Edit-2511 image-to-image model
-
prithivMLmods/Qwen-Image-Edit-2511-Ultra-Realistic-Portrait
Image-to-Image • Updated • 32.7k • • 54 -
prithivMLmods/QIE-2511-Cinematic-FlatLog-Control
Image-to-Image • Updated • 3.33k • • 4 -
prithivMLmods/Qwen-Image-Edit-2511-Object-Adder
Image-to-Image • Updated • 31.1k • • 32 -
prithivMLmods/Qwen-Image-Edit-2511-Hyper-Realistic-Portrait
Image-to-Image • Updated • 22.2k • • 17
SFT, RL
-
prithivMLmods/KAIROS-MM-Qwen2.5-VL-7B-RL
Video-Text-to-Text • Updated • 9 • 5 -
prithivMLmods/KAIROS-MM-Qwen2.5-VL-7B-SFT
Video-Text-to-Text • 8B • Updated • 12 • 5 -
prithivMLmods/KAIROS-MM-Qwen2.5-VL-SFT-GGUF
Video-Text-to-Text • 8B • Updated • 25 • 1 -
prithivMLmods/KAIROS-MM-Qwen2.5-VL-7B-SFT-GGUF-AIO-GGUF
Video-Text-to-Text • 8B • Updated • 377 • 1
Document-AI, HTML, OCR
-
prithivMLmods/proxima-ocr-d.markdown-post3.0.l
Image-Text-to-Text • 9B • Updated • 69 • 5 -
prithivMLmods/epsilon-ocr-d.markdown-post3.0.m
Image-Text-to-Text • 4B • Updated • 16 • 3 -
prithivMLmods/proxima-ocr-d.markdown-post3.0.l-GGUF
Image-Text-to-Text • 8B • Updated • 90 • 2 -
prithivMLmods/epsilon-ocr-d.markdown-post3.0.m-GGUF
Image-Text-to-Text • 3B • Updated • 122 • 1
abliterated & [safe and controlled caption generation]
-
prithivMLmods/Qwen3-VisionCaption-2B
Image-Text-to-Text • 2B • Updated • 48 • 5 -
prithivMLmods/Qwen3-VisionCaption-2B-GGUF
Image-Text-to-Text • 2B • Updated • 829 • 9 -
prithivMLmods/Qwen3-VisionCaption-2B-it-REDACTED
Image-Text-to-Text • 2B • Updated • 10 • 1 -
prithivMLmods/Qwen3-VisionCaption-2B-it-REDACTED-GGUF
Image-Text-to-Text • 2B • Updated • 312 • 1
All-in-One Quants
-
prithivMLmods/Qwen3-VL-8B-Abliterated-Caption-it-GGUF
Image-Text-to-Text • 8B • Updated • 1.46k • 6 -
prithivMLmods/Qwen2.5-VL-Abliterated-Caption-GGUF
Image-Text-to-Text • 3B • Updated • 819 • 16 -
prithivMLmods/DeepCaption-VLA-V2.0-7B
Image-Text-to-Text • 8B • Updated • 107 • 7 -
prithivMLmods/Qwen3-VL-8B-Instruct-abliterated-v2
Image-Text-to-Text • 9B • Updated • 1.97k • 27
Multiple Adapters for Heterogeneous Angles
Qwen3VL, Qwen2.5VL
-
prithivMLmods/Qwen3-VL-8B-Abliterated-Caption-it
Image-Text-to-Text • 9B • Updated • 1.11k • 31 -
prithivMLmods/Qwen2.5-VL-7B-Abliterated-Caption-it
Image-Text-to-Text • 8B • Updated • 2.49k • 44 -
prithivMLmods/Qwen2.5-VL-3B-Abliterated-Caption-it
Image-Text-to-Text • 4B • Updated • 48 • 7 -
prithivMLmods/Qwen2.5-VL-Abliterated-Caption-GGUF
Image-Text-to-Text • 3B • Updated • 819 • 16
Qwen2.5-VL and Qwen3-VL
-
prithivMLmods/Qwen3-VL-4B-Instruct-abliterated-v1
Image-Text-to-Text • 4B • Updated • 1.01k • 21 -
prithivMLmods/Qwen3-VL-4B-Thinking-abliterated-v1
Image-Text-to-Text • 4B • Updated • 187 • 18 -
prithivMLmods/Qwen2.5-VL-7B-Abliterated-Caption-it
Image-Text-to-Text • 8B • Updated • 2.49k • 44 -
prithivMLmods/Qwen2.5-VL-3B-Abliterated-Caption-it
Image-Text-to-Text • 4B • Updated • 48 • 7
List of Models for Multimodal VLM Parsing
agentic reasoning, web search orchestration
-
prithivMLmods/Dorado-WebSurf_Tool-ext
Text Generation • 4B • Updated • 6 • 4 -
prithivMLmods/Dorado-WebSurf_Tool-ext-GGUF
Text Generation • 4B • Updated • 120 • 1 -
prithivMLmods/Gliese-Query_Tool-0.6B
Text Generation • 0.6B • Updated • 5 -
prithivMLmods/Gliese-Query_Tool-0.6B-GGUF
Text Generation • 0.6B • Updated • 141
I2I Optimization
Polished Tokens, Improved Multilingual Support, and Controlled Abliteration.
-
prithivMLmods/Carinae-Qwen3-Radiation-4B
Text Generation • 4B • Updated • 5 • 2 -
prithivMLmods/MobileLLM-R1-950M-Radiation
Text Generation • 0.9B • Updated -
prithivMLmods/Leporis-Qwen3-Radiation-1.7B
Text Generation • 2B • Updated • 8 -
prithivMLmods/Leporis-Qwen3-Radiation-1.7B-GGUF
Text Generation • 2B • Updated • 83 • 2
Multimodal models
-
prithivMLmods/Qwen2.5-VL-7B-Abliterated-Caption-it
Image-Text-to-Text • 8B • Updated • 2.49k • 44 -
prithivMLmods/Qwen2.5-VL-Abliterated-Caption-GGUF
Image-Text-to-Text • 3B • Updated • 819 • 16 -
prithivMLmods/Caption3o-XL-2B-Qwen2VL
Image-Text-to-Text • 2B • Updated • 20 • 2 -
prithivMLmods/Qwen2.5-VL-3B-Abliterated-Caption-it
Image-Text-to-Text • 4B • Updated • 48 • 7
post1.0 ft. camel-doc-ocr-062825
Vision Language Attribution
Qwen3 base
-
prithivMLmods/Demeter-LongCoT-Qwen3-1.7B
Text Generation • 2B • Updated • 19 • 1 -
prithivMLmods/Demeter-LongCoT-Qwen3-1.7B-GGUF
Text Generation • 2B • Updated • 162 • 2 -
prithivMLmods/Canum-med-Qwen3-Reasoning
Text Generation • 2B • Updated • 62 • 3 -
prithivMLmods/Canum-med-Qwen3-Reasoning-GGUF
Text Generation • 2B • Updated • 91
Mixture of Domains
-
prithivMLmods/Gacrux-R1-Qwen3-1.7B-MoD
Text Generation • 2B • Updated • 19 • 3 -
prithivMLmods/Gacrux-R1-Qwen3-1.7B-MoD-GGUF
Text Generation • 2B • Updated • 35 -
prithivMLmods/Panacea-MegaScience-Qwen3-1.7B
Text Generation • 2B • Updated • 9 -
prithivMLmods/Panacea-MegaScience-Qwen3-1.7B-GGUF
Text Generation • 2B • Updated • 43
Flux.1 (Krea, Dev, Schnell), Qwen-Image, Nano-Banana, Qwen-Image-Edit
qwen2.5-vl : 3b, 7b caption
max - f32
-
prithivMLmods/Qwen3-4B-Thinking-2507-GGUF
Text Generation • 4B • Updated • 120 • 1 -
prithivMLmods/Qwen3-4B-Instruct-2507-GGUF
Text Generation • 4B • Updated • 194 • 2 -
prithivMLmods/Qwen3-4B-2507-abliterated-GGUF
Text Generation • 4B • Updated • 901 • 9 -
prithivMLmods/MegaScience-Qwen-GGUF
Text Generation • 2B • Updated • 150 • 1
<think>
qwen3
Document Retrieval, Content Extraction, and Analysis Recognition.
-
prithivMLmods/Camel-Doc-OCR-080125
Image-Text-to-Text • 8B • Updated • 227 • 8 -
prithivMLmods/Camel-Doc-OCR-080125-GGUF
Image-Text-to-Text • 8B • Updated • 346 • 2 -
prithivMLmods/Camel-Doc-OCR-062825
Image-Text-to-Text • 8B • Updated • 57 • 13 -
prithivMLmods/Camel-Doc-OCR-062825-mmp-GGUF
Image-Text-to-Text • 8B • Updated • 36 • 1
Thinking / No-Thinking
Image and video frame understanding, contextual analysis, and natural language reasoning, Abliterated Captioning / Uncensored Image Captioning,
(LLM) research, benchmarking, and STEM-focused
reason/scientific thought mixture
variable-dimensional pairs dataset
trl / @exp
-
prithivMLmods/SmolLM2-Rethink-360M
Text Generation • 0.4B • Updated • 7 • 1 -
prithivMLmods/SmolLM2-Rethink-135M
Text Generation • 0.1B • Updated • 14 • 2 -
prithivMLmods/SmolLM2-Rethink-135M-GGUF
Text Generation • 0.1B • Updated • 107 -
prithivMLmods/SmolLM2-Rethink-360M-GGUF
Text Generation • 0.4B • Updated • 46
new exps
drex [doc ], virex [ video (image ++) exp ]
Reasoning and Non-Reasoning
-
prithivMLmods/Megatron-Bots-1.7B-Reasoning
Text Generation • 2B • Updated • 3 -
prithivMLmods/Megatron-Bots-1.7B-Reasoning-GGUF
Text Generation • 2B • Updated • 44 -
prithivMLmods/Computron-Bots-1.7B-R1
Text Generation • 2B • Updated • 7 -
prithivMLmods/Computron-Bots-1.7B-R1-GGUF
Text Generation • 2B • Updated • 39
RL~Reward Signal
Mixture-of-Thoughts
-
prithivMLmods/Theta-Crucis-0.6B-Turbo1
Text Generation • 0.6B • Updated • 3 -
prithivMLmods/Theta-Crucis-0.6B-Turbo1-GGUF
Text Generation • 0.6B • Updated • 34 -
prithivMLmods/Nenque-MoT-0.6B-Elite14
Text Generation • 0.6B • Updated • 4 -
prithivMLmods/Nenque-MoT-0.6B-Elite14-GGUF
Text Generation • 0.6B • Updated • 30
math, code
-
prithivMLmods/Wolf-Rayet-2B-Prime3
Text Generation • 2B • Updated • 6 -
prithivMLmods/BetaCeti-Beta-4B-Prime1
Text Generation • 4B • Updated • 7 • 2 -
prithivMLmods/Omega-Herculis-7B-Prime2
Text Generation • 8B • Updated • 3 • 2 -
prithivMLmods/BetaCeti-Beta-4B-Prime1-GGUF
Text Generation • 4B • Updated • 58
qwen2vl
siglip2 base
Code, Math, Moderately Abliterated
image detection
There are two means of refuge from the miseries of life: music and cats
spotting diffusion-generated images in realistic, open-world scenarios
-
prithivMLmods/OpenSDI-Flux.1-SigLIP2
Image Classification • 92.9M • Updated • 117 • 1 -
prithivMLmods/OpenSDI-SDXL-SigLIP2
Image Classification • 92.9M • Updated • 9 -
prithivMLmods/OpenSDI-SD1.5-SigLIP2
Image Classification • 92.9M • Updated • 5 -
prithivMLmods/OpenSDI-SD2.1-SigLIP2
Image Classification • 92.9M • Updated • 4
Upto Full precision (float32) version
CoT, LCoT - QwQ / R1 Math
Moderation, Balance, Classifiers
-
prithivMLmods/Realistic-Gender-Classification
Image Classification • 92.9M • Updated • 2.52k • • 7 -
prithivMLmods/Realistic-Portrait-Gender-1024px
Viewer • Updated • 3.2k • 40 • 3 -
prithivMLmods/Document-Type-Detection
Image Classification • 92.9M • Updated • 160 -
prithivMLmods/Document-Type-Detection
Viewer • Updated • 12k • 51 • 1
DocVQA, RealWorldQA, MTVQA
moderately abliterated and improved context awareness and moderate behavioral flexibility variant of Qwen3.
Robust Policy Optimization (RPO)
-
prithivMLmods/Diophantus-14B-R1-Instruct
Text Generation • 15B • Updated • 4 -
prithivMLmods/Belenos-8574-14B-GOP
Text Generation • 15B • Updated • 5 • 1 -
prithivMLmods/Geminorum-Wasat-14B-Instruct
Text Generation • 15B • Updated • 4 -
prithivMLmods/Rapeto-ReDistill-14B-GOP
Text Generation • 15B • Updated • 5
advanced reinforcement learning (RL)
-
prithivMLmods/Gamma-Velorum-1.5B-Thinker
Text Generation • 2B • Updated • 5 -
prithivMLmods/Deepthink-1.5B-Open-PRM
Text Generation • 2B • Updated • 2 -
prithivMLmods/Deepthink-1.5B-Open-PRM-Q8_0-GGUF
Text Generation • 2B • Updated • 5 • 3 -
prithivMLmods/TESS-QwenRe-1.5B
Text Generation • 2B • Updated • 4
Moderation, Balance, Classifiers
-
prithivMLmods/Anime-Classification-v1.0
Image Classification • 92.9M • Updated • 145 • 1 -
prithivMLmods/Facial-Emotion-Detection-SigLIP2
Image Classification • 92.9M • Updated • 185 • 7 -
prithivMLmods/IndoorOutdoorNet
Image Classification • 92.9M • Updated • 52 • 3 -
prithivMLmods/Multilabel-GeoSceneNet
Image Classification • 92.9M • Updated • 10 • 4
advanced reinforcement learning (RL)
Math, Reasoning
-
prithivMLmods/CEERS-2112-14B-Instruct
Text Generation • 15B • Updated • 8 -
prithivMLmods/Canum-Venaticorum-14B-B.1
Text Generation • 15B • Updated • 4 -
prithivMLmods/Magellanic-Qwen-14B-R1
Text Generation • 15B • Updated • 8 -
prithivMLmods/Camelopardalis-650-14B-Instruct
Text Generation • 15B • Updated • 4
Usage, Season, BaseColour, ArticleType, SubCategory, MasterCategory, Gender
-
prithivMLmods/Fashion-Product-Gender
Image Classification • 92.9M • Updated • 13 -
prithivMLmods/Fashion-Product-masterCategory
Image Classification • 92.9M • Updated • 13 -
prithivMLmods/Fashion-Product-subCategory
Image Classification • 92.9M • Updated • 31 • 2 -
prithivMLmods/Fashion-Product-articleType
Image Classification • 93M • Updated • 13
Moderation, Balance, Classifiers
-
prithivMLmods/Age-Classification-SigLIP2
Image Classification • 92.9M • Updated • 92.5k • • 6 -
prithivMLmods/Mature-Content-Detection
Image Classification • 92.9M • Updated • 642 • 7 -
prithivMLmods/Mirage-Photo-Classifier
Image Classification • 92.9M • Updated • 50 • • 2 -
prithivMLmods/Human-Action-Recognition
Image Classification • 92.9M • Updated • 333 • 6
Domain Specific Classification Models : SigLIP2
-
prithivMLmods/Hand-Gesture-2-Robot
Image Classification • 92.9M • Updated • 14 • 2 -
prithivMLmods/Trash-Net
Image Classification • 92.9M • Updated • 207 • 3 -
prithivMLmods/Road-Subsigns-Classification
Image Classification • 92.9M • Updated • 18 • 1 -
prithivMLmods/PussyCat-vs-Doggie-SigLIP2
Image Classification • 92.9M • Updated • 4
Names are randomly assigned to the respective TTS model based on gender, and the generated voice will have a radio and clean essence. [ Llama ]
Raptor X: Advanced UI Coder, Reasoning and General-Purpose Coder, and Math LLM
Math, Code, General-Purpose : Multipurpose
vit, siglip
-
prithivMLmods/Fashion-Mnist-SigLIP2
Image Classification • 92.9M • Updated • 37 • 4 -
prithivMLmods/Alphabet-Sign-Language-Detection
Image Classification • 92.9M • Updated • 614 • 8 -
prithivMLmods/Traffic-Density-Classification
Image Classification • 92.9M • Updated • 134 • 2 -
prithivMLmods/Dog-Breed-120
Image Classification • 93M • Updated • 379 • 1
OpenLLM Leaderboard
-
prithivMLmods/Galactic-Qwen-14B-Exp2
Text Generation • 15B • Updated • 8 • 10 -
prithivMLmods/Sombrero-Opus-14B-Elite5
Text Generation • 15B • Updated • 14 • 3 -
prithivMLmods/Equuleus-Opus-14B-Exp
Text Generation • 15B • Updated • 7 • 2 -
prithivMLmods/Sombrero-Opus-14B-Elite6
Text Generation • 15B • Updated • 10 • 2
Experimentals
-
prithivMLmods/Methuselah-PSR-B1620-26b-14B-Exp
Text Generation • 15B • Updated • 2 • 1 -
prithivMLmods/Galactic-Qwen-14B-Exp2
Text Generation • 15B • Updated • 8 • 10 -
prithivMLmods/Volans-Opus-14B-Exp
Text Generation • 15B • Updated • 7 • 2 -
prithivMLmods/Gaea-Opus-14B-Exp
Text Generation • 15B • Updated • 5 • 2
Experimentals
Coding, Mathematical Problem Solving
14b - 32b experimental ft
general purpose 14b llms
-
prithivMLmods/Messier-Opus-14B-Elite7
Text Generation • 15B • Updated • 76 • 2 -
prithivMLmods/Lacerta-Opus-14B-Elite8
Text Generation • 15B • Updated • 5 • 2 -
prithivMLmods/Viper-OneCoder-UIGEN
Text Generation • 15B • Updated • 11 • 3 -
prithivMLmods/Viper-Coder-v1.4
Text Generation • 15B • Updated • 14 • 4
SiglipForImageClassification
-
prithivMLmods/AI-vs-Deepfake-vs-Real-Siglip2
Image Classification • 92.9M • Updated • 24.3k • • 2 -
prithivMLmods/Guard-Against-Unsafe-Content-Siglip2
Image Classification • 92.9M • Updated • 7 -
prithivMLmods/Deepfake-Detect-Siglip2
Image Classification • 92.9M • Updated • 1.26k • • 3 -
prithivMLmods/Fire-Detection-Siglip2
Image Classification • 92.9M • Updated • 1.2k • • 4
based on recent dataset
-
prithivMLmods/AI-vs-Deepfake-vs-Real
Image Classification • 85.8M • Updated • 380 • 9 -
prithivMLmods/AI-vs-Deepfake-vs-Real-ONNX
Image Classification • Updated • 504 • 2 -
prithivMLmods/AI-vs-Deepfake-vs-Real
Viewer • Updated • 10k • 49 • 13 -
prithivMLmods/Deepfake-Detection-Exp-02-22
Image Classification • 87.5M • Updated • 140 • 4
providing assistance
-
prithivMLmods/Sombrero-Opus-14B-Elite5
Text Generation • 15B • Updated • 14 • 3 -
prithivMLmods/Dinobot-Opus-14B-Exp
Text Generation • 15B • Updated • 52 • 3 -
prithivMLmods/Magellanic-Opus-14B-Exp
Text Generation • 15B • Updated • 9 • 2 -
prithivMLmods/Viper-Coder-v1.1
Text Generation • 15B • Updated • 19 • 8
Classification of Good and Bad Quality Deepfakes { Datasets }
Controllable Classification of Good and Bad Quality Deepfakes
-
prithivMLmods/Deepfake-QualityAssess-88M
Image Classification • 87.5M • Updated • 7 • 1 -
prithivMLmods/Deepfake-QualityAssess2.0-85M
Image Classification • 85.8M • Updated • 10 • 1 -
prithivMLmods/Deepfake-QualityAssess2.0-85M-ONNX
Image Classification • Updated • 9 • 1 -
prithivMLmods/Deepfake-QualityAssess2.1-85M
Image Classification • 85.8M • Updated • 13 • 1
1.5B, 1B, 0.5B param's
7B, 14B [ Saturation ]
-
prithivMLmods/Bellatrix-1.5B-xElite
Text Generation • 2B • Updated • 7 • 3 -
prithivMLmods/Calcium-Opus-14B-Elite-1M
Text Generation • 15B • Updated • 13 • • 4 -
prithivMLmods/COCO-7B-Instruct-1M
Text Generation • 8B • Updated • 16 • 4 -
prithivMLmods/Taurus-Opus-7B
Text Generation • 7B • Updated • 15 • 4
VLM - Multimodality
phi 4 custom ft [ qwq, lcot, math ]
Solve Math with Python
Llama with Questions for reasoning / long chain of thought
ChemQwen Based on InChI
Open Eval < 500, long chain of thought and keyword based answering, reasoning
Best for Deepthink and Reasoning
Text Generation Cook with it's GGUF
-
prithivMLmods/QwQ-LCoT-7B-Instruct
Text Generation • 8B • Updated • 33 • 20 -
prithivMLmods/QwQ-LCoT-7B-Instruct-GGUF
Text Generation • 8B • Updated • 46 • 3 -
prithivMLmods/QwQ-LCoT-3B-Instruct
Text Generation • 3B • Updated • 15 • 5 -
prithivMLmods/QwQ-LCoT-3B-Instruct-GGUF
Text Generation • 3B • Updated • 35 • 7
ease of reading
-
prithivMLmods/Triangulum-10B-GGUF
Text Generation • 10B • Updated • 117 • 2 -
prithivMLmods/Codepy-Deepthink-3B-GGUF
Text Generation • 3B • Updated • 68 • 7 -
prithivMLmods/Marco-o1-GGUF
Text Generation • 8B • Updated • 73 • 6 -
prithivMLmods/Qwen2.5-Coder-14B-Instruct-F16-GGUF
Text Generation • 15B • Updated • 131 • 2
Flux & Sdxl
Only Stable
Flux THE LoRA
-
strangerzonehf/Flux-Midjourney-Mix2-LoRA
Text-to-Image • Updated • 2.18k • • 546 -
strangerzonehf/Flux-Super-Realism-LoRA
Text-to-Image • Updated • 2.93k • • 270 -
strangerzonehf/Flux-Midjourney-Mix-LoRA
Text-to-Image • Updated • 18 • • 60 -
strangerzonehf/Flux-Animex-v2-LoRA
Text-to-Image • Updated • 107 • • 35
Collection of Gemma-4 Quants
-
prithivMLmods/gemma-4-31B-it-F32-GGUF
Image-Text-to-Text • 31B • Updated • 2 -
prithivMLmods/gemma-4-26B-A4B-it-F32-GGUF
Image-Text-to-Text • 25B • Updated • 1 -
prithivMLmods/gemma-4-E4B-it-F32-GGUF
Image-Text-to-Text • 8B • Updated • 1 -
prithivMLmods/gemma-4-E2B-it-F32-GGUF
Image-Text-to-Text • 5B • Updated • 1
Multimodal Collections Sublist
Audio, Image, Image-to-Text
-
Qwen3 VL HF Demo
🔥33Object Detection, Visual Grounding, Keypoint Detection
-
Multimodal OCR2
💻141FireRed / Nanonets / Monkey / Thyme / Typhoon / SmolDocling
-
CUA GUI Operator
💻10Ultra-compact Computer-Use Agent [GUI Localization]
-
NVIDIA Nemotron Parse OCR
🥠7understand document semantics, extract text and tables.
Continual “abliteration” models – experimental.
-
prithivMLmods/Qwen3.5-35B-A3B-Unredacted-MAX
Image-Text-to-Text • 35B • Updated • 117 • 1 -
prithivMLmods/Qwen3.5-27B-Unredacted-MAX
Image-Text-to-Text • 27B • Updated • 217 • 4 -
prithivMLmods/Qwen3.5-9B-Unredacted-MAX
Image-Text-to-Text • 9B • Updated • 2.05k • 6 -
prithivMLmods/Qwen3.5-4B-Unredacted-MAX
Image-Text-to-Text • 5B • Updated • 238 • 6
Collection of Lightweight Qwen3.5 GGUF Models
-
prithivMLmods/Qwen3.5-Thinking-AIO-GGUF
Image-Text-to-Text • 0.8B • Updated • 2.85k • 1 -
prithivMLmods/Qwen3.5-0.8B-f32-GGUF
Image-Text-to-Text • 0.8B • Updated • 824 • 1 -
prithivMLmods/Qwen3.5-2B-f32-GGUF
Image-Text-to-Text • 2B • Updated • 476 • 1 -
prithivMLmods/Qwen3.5-4B-f32-GGUF
Image-Text-to-Text • 4B • Updated • 493 • 1
Continual “abliteration” models – experimental.
-
prithivMLmods/Qwen2.5-VL-32B-Instruct-Unredacted-MAX
Image-Text-to-Text • 33B • Updated • 233 • 4 -
prithivMLmods/Qwen2.5-VL-7B-Instruct-Unredacted-MAX
Image-Text-to-Text • 8B • Updated • 88 • 4 -
prithivMLmods/Qwen2.5-VL-3B-Instruct-Unredacted-MAX
Image-Text-to-Text • 4B • Updated • 25 • 2 -
prithivMLmods/Qwen2.5-VL-32B-Instruct-Unredacted-MAX-FP8
Image-Text-to-Text • 33B • Updated • 9 • 1
[FP8_DYNAMIC] multi-stage trained continual "abliteration" approach for the qwen3-vl series models
-
prithivMLmods/Qwen3-VL-32B-Instruct-Unredacted-MAX-FP8
Image-Text-to-Text • 33B • Updated • 207 • 3 -
prithivMLmods/Qwen3-VL-32B-Thinking-Unredacted-MAX-FP8
Image-Text-to-Text • 33B • Updated • 17 • 1 -
prithivMLmods/Qwen3-VL-8B-Instruct-Unredacted-MAX-FP8
Image-Text-to-Text • 9B • Updated • 24 • 2 -
prithivMLmods/Qwen3-VL-8B-Thinking-Unredacted-MAX-FP8
Image-Text-to-Text • 9B • Updated • 8 • 1
multi-stage trained continual "abliteration" approach for the qwen3-vl series models (GGUF)
-
prithivMLmods/Qwen3-VL-4B-Instruct-Unredacted-MAX-GGUF
Image-Text-to-Image • 4B • Updated • 3.17k • 7 -
prithivMLmods/Qwen3-VL-4B-Thinking-Unredacted-MAX-GGUF
Image-Text-to-Text • 4B • Updated • 171 • 1 -
prithivMLmods/Qwen3-VL-8B-Instruct-Unredacted-MAX-GGUF
Image-Text-to-Text • 8B • Updated • 905 • 5 -
prithivMLmods/Qwen3-VL-8B-Thinking-Unredacted-MAX-GGUF
Image-Text-to-Image • 8B • Updated • 1.49k • 3
adapter LoRA developed for Qwen’s Qwen-Image-Edit-2511 image-to-image model
-
prithivMLmods/QIE-2511-Studio-DeLight
Image-to-Image • Updated • 12.7k • • 22 -
prithivMLmods/QIE-2511-Outfit-Design-Layout
Image-to-Image • Updated • 3.33k • • 4 -
prithivMLmods/QIE-2511-Zoom-Master
Image-to-Image • Updated • 1.23k • • 18 -
prithivMLmods/QIE-2511-Object-Remover-v2
Image-to-Image • Updated • 3.09k • • 18
Add or remove the specified objects, flexible for both single-image and multi-image modes.
Localization, Tool Calling, and Navigation
-
prithivMLmods/Gliese-CUA-Tool-Call-8B
Image-Text-to-Text • 8B • Updated • 11 • 3 -
prithivMLmods/Gliese-CUA-Tool-Call-8B-GGUF
Image-Text-to-Text • 8B • Updated • 223 • 2 -
prithivMLmods/Gliese-CUA-Tool-Call-8B-Localization-GGUF
Image-Text-to-Text • 8B • Updated • 145 • 1 -
prithivMLmods/Herculis-CUA-GUI-Actioner-4B
Image-Text-to-Text • 4B • Updated • 13 • 2
Collection of Gliese series OCR models
-
prithivMLmods/Gliese-OCR-7B-Post1.0
Image-Text-to-Text • 8B • Updated • 62 • 13 -
prithivMLmods/Gliese-OCR-7B-Post1.0-GGUF
Image-Text-to-Text • 8B • Updated • 86 • 1 -
prithivMLmods/Gliese-OCR-7B-Post2.0-final
Image-Text-to-Text • 8B • Updated • 13 • 6 -
prithivMLmods/Gliese-OCR-7B-Post2.0-final-GGUF
Image-Text-to-Text • 8B • Updated • 328 • 1
Domain-Specific Downstream Tasks
-
prithivMLmods/MetaCLIP-2-Age-Range-Estimator
Image Classification • 21.7M • Updated • 10 • 7 -
prithivMLmods/MetaCLIP-2-Gender-Identifier
Image Classification • 21.7M • Updated • 13 • 2 -
prithivMLmods/MetaCLIP-2-Open-Scene
Image Classification • 21.7M • Updated • 12 • 1 -
prithivMLmods/MetaCLIP-2-Cifar10
Image Classification • 21.7M • Updated • 9 • 1
All-in-One Quants
-
prithivMLmods/Gliese-OCR-7B-Post2.0-final-GGUF
Image-Text-to-Text • 8B • Updated • 328 • 1 -
prithivMLmods/Gliese-OCR-7B-Post1.0-GGUF
Image-Text-to-Text • 8B • Updated • 86 • 1 -
prithivMLmods/Camel-Doc-OCR-080125-GGUF
Image-Text-to-Text • 8B • Updated • 346 • 2 -
prithivMLmods/granite-docling-258M-f32-GGUF
Image-Text-to-Text • 0.2B • Updated • 149 • 3
Qwen2.5VL OCR (Model Tree)
-
prithivMLmods/Gliese-OCR-7B-Post2.0-final
Image-Text-to-Text • 8B • Updated • 13 • 6 -
prithivMLmods/Gliese-OCR-7B-Post1.0
Image-Text-to-Text • 8B • Updated • 62 • 13 -
prithivMLmods/Camel-Doc-OCR-080125
Image-Text-to-Text • 8B • Updated • 227 • 8 -
prithivMLmods/Megalodon-OCR-Sync-0713
Image-Text-to-Text • 4B • Updated • 22 • 4
Qwen3-VL Abliterated Model Collection [ Version 1.0 ]
-
prithivMLmods/Qwen3-VL-32B-Instruct-abliterated-v1
Image-Text-to-Text • 33B • Updated • 97 • 6 -
prithivMLmods/Qwen3-VL-32B-Thinking-abliterated-v1
Image-Text-to-Text • 33B • Updated • 71 • 6 -
prithivMLmods/Qwen3-VL-30B-A3B-Thinking-abliterated-v1
Image-Text-to-Text • 31B • Updated • 29 • 4 -
prithivMLmods/Qwen3-VL-30B-A3B-Instruct-abliterated-v1
Image-Text-to-Text • 31B • Updated • 13.5k • 3
Multilingual upstream VLMs - Caption, OCR, Markdown, HTML Render
-
prithivMLmods/DeepCaption-VLA-V2.0-7B
Image-Text-to-Text • 8B • Updated • 107 • 7 -
prithivMLmods/DeepCaption-VLA-7B
Image-Text-to-Text • 8B • Updated • 245 • 22 -
prithivMLmods/Camel-Doc-OCR-080125
Image-Text-to-Text • 8B • Updated • 227 • 8 -
prithivMLmods/Camel-Doc-OCR-062825
Image-Text-to-Text • 8B • Updated • 57 • 13
Multimodal VLM and LLM : 'Gliese' Collection of Models
Abliterated Reasoning & polished token probabilities, enhancing balanced multilingual generation
-
prithivMLmods/Kepler-186f-Qwen3-Instruct-4B
Text Generation • 4B • Updated • 6 • 3 -
prithivMLmods/Kepler-186f-Qwen3-Instruct-4B-GGUF
Text Generation • 4B • Updated • 83 • 3 -
prithivMLmods/Kepler-Qwen3-4B-Super-Thinking
Text Generation • 4B • Updated • 4 • 5 -
prithivMLmods/Kepler-Qwen3-4B-Super-Thinking-GGUF
Text Generation • 4B • Updated • 179
Polished and Controlled Gen
Photo Restore, Polaroid, Inter-style Mix and more...
filtered for an sfw captioning set of image pairs.
random event simulations, logical problem analysis, and structured reasoning tasks
-
prithivMLmods/Capella-Qwen3-DS-V3.1-4B
Text Generation • 4B • Updated • 8 • 4 -
prithivMLmods/Capella-Qwen3-DS-V3.1-4B-GGUF
Text Generation • 4B • Updated • 256 -
prithivMLmods/Mintaka-Qwen3-1.6B-V3.1
Text Generation • 2B • Updated • 6 • 1 -
prithivMLmods/Mintaka-Qwen3-1.6B-V3.1-GGUF
Text Generation • 2B • Updated • 135 • 1
experimental
-
prithivMLmods/Pyxidis-Manim-CodeGen-1.7B
Text Generation • 2B • Updated • 43 • 3 -
prithivMLmods/Pyxidis-Manim-CodeGen-1.7B-GGUF
Text Generation • 2B • Updated • 639 • 3 -
prithivMLmods/Regulus-Qwen3-R1-Llama-Distill-1.7B
Text Generation • 2B • Updated • 10 -
prithivMLmods/Regulus-Qwen3-R1-Llama-Distill-GGUF
Text Generation • 2B • Updated • 130 • 2
Illustration Design, Style Intermix
Reasoning, Document Extraction, Table Reconstruction
vlm extended reasoning, captioning
DAG, STEM Reasoning
-
prithivMLmods/Cerium-Qwen3-R1-Dev
Text Generation • 0.6B • Updated • 5 -
prithivMLmods/Cerium-Qwen3-R1-Dev-GGUF
Text Generation • 0.6B • Updated • 80 -
prithivMLmods/Telescopium-Acyclic-Qwen3-0.6B
Text Generation • 0.6B • Updated • 7 -
prithivMLmods/Telescopium-Acyclic-Qwen3-0.6B-GGUF
Text Generation • 0.6B • Updated • 21
mixture of domains
tiny models
-
Super OCRs Demo
🧪41Experiment with small super OCR models here.
-
Multimodal OCR2
💻141FireRed / Nanonets / Monkey / Thyme / Typhoon / SmolDocling
-
Multimodal OCR
🍍404Nanonets / olmOCR / RolmOCR / Aya-Vision / Qwen2-VL-OCR
-
VisionScope-R2
🔍109DeepCaption / SkyCaptioner / SpaceThinker / Core / SpaceOm
(FLUX.1-schnell + FLUX.1-Krea-dev) | (Flux.1-Dev + Flux.1-Krea-Dev)
(Flux.1-Dev + Flux.1-Krea-Dev)
Multimodal VLMs for Domain-Specific Tasks: OCR, Reasoning, and Captioning
-
prithivMLmods/Camel-Doc-OCR-080125
Image-Text-to-Text • 8B • Updated • 227 • 8 -
prithivMLmods/Camel-Doc-OCR-062825
Image-Text-to-Text • 8B • Updated • 57 • 13 -
prithivMLmods/VIREX-062225-exp
Image-Text-to-Text • 8B • Updated • 9 • 3 -
prithivMLmods/coreOCR-7B-050325-preview
Image-Text-to-Text • 8B • Updated • 207 • 13
qwen2.5, 3
Mixed Model Operations
Deep Caption VL - Trained with variable-dimensional pairs
Chain-of-Thought Reasoning, Detailed Image Captioning
enhances document comprehension capabilities
Based on Qwen2.5 VL, Qwen2 VL
-
prithivMLmods/docscopeOCR-7B-050425-exp
Image-Text-to-Text • 8B • Updated • 170 • 7 -
prithivMLmods/coreOCR-7B-050325-preview
Image-Text-to-Text • 8B • Updated • 207 • 13 -
prithivMLmods/visionOCR-3B-061125
Image-Text-to-Text • 4B • Updated • 538 • 5 -
prithivMLmods/docscopeOCR-7B-050425-exp-GGUF
Image-Text-to-Text • 8B • Updated • 77 • 3
coder
-
prithivMLmods/Blitzar-Coder-4B-F.1
Text Generation • 4B • Updated • 20 • 9 -
prithivMLmods/Blitzar-Coder-4B-F.1-GGUF
Text Generation • 4B • Updated • 172 • 7 -
prithivMLmods/Lambda-Equulei-1.5B-xLingual
Text Generation • 2B • Updated • 4 • 3 -
prithivMLmods/Lambda-Equulei-1.5B-xLingual-GGUF
Text Generation • 2B • Updated • 53
Mixture-of-Thoughts
-
prithivMLmods/Lacaille-MoT-4B-Supreme2
Text Generation • 4B • Updated • 16 • 9 -
prithivMLmods/Lacaille-MoT-4B-Supreme2-GGUF
Text Generation • 4B • Updated • 65 -
prithivMLmods/Capricornus-MoT-1.7B-Supreme1
Text Generation • 2B • Updated • 3 -
prithivMLmods/Capricornus-MoT-1.7B-Supreme1-GGUF
Text Generation • 2B • Updated • 32
audio classifiers
-
prithivMLmods/Common-Voice-Gender-Detection
Audio Classification • 94.6M • Updated • 185k • 22 -
prithivMLmods/Common-Voice-Gender-Detection-ONNX
Audio Classification • Updated • 698 • 5 -
prithivMLmods/Speech-Emotion-Classification
Audio Classification • 94.6M • Updated • 963 • 9 -
prithivMLmods/Speech-Emotion-Classification-ONNX
Audio Classification • Updated • 15 • 3
models, datasets
-
prithivMLmods/shoe-type-detection
Image Classification • 92.9M • Updated • 70 • 1 -
prithivMLmods/facial-age-detection
Image Classification • 92.9M • Updated • 932 • 9 -
prithivMLmods/tooth-agenesis-siglip2
Image Classification • 92.9M • Updated • 15 • 1 -
strangerguardhf/Tooth-Agenesis-6_Types
Viewer • Updated • 12.3k • 5
custom llms
-
prithivMLmods/Lynx-TinySync-0.6B
Text Generation • 0.6B • Updated • 4 -
prithivMLmods/Lynx-TinySync-0.6B-GGUF
Text Generation • 0.6B • Updated • 48 -
prithivMLmods/Oganesson-TinyLlama-1.2B
Text Generation • 1B • Updated • 5 -
prithivMLmods/Oganesson-TinyLlama-1.2B-GGUF
Text Generation • 1B • Updated • 140
(direct, reactive, retrieval-based responses), (reasoning, planning, deeper analysis)
-
prithivMLmods/Magpie-Qwen-DiMind-1.7B
Text Generation • 2B • Updated • 7 • 2 -
prithivMLmods/Magpie-Qwen-DiMind-1.7B-GGUF
Text Generation • 2B • Updated • 26 -
prithivMLmods/Magpie-Qwen-CortexDual-0.6B
Text Generation • 0.6B • Updated • 6 • 2 -
prithivMLmods/Magpie-Qwen-CortexDual-0.6B-GGUF
Text Generation • 0.6B • Updated • 68
trajectory
vit, siglip2
Math, Code, Reasoning – Edge Device LLMs
classification net.
Cot, LCoT - Reasoning
-
prithivMLmods/Cetus-Qwen3_4B-GeneralThought
Text Generation • 4B • Updated • 6 • 1 -
prithivMLmods/Cetus-Qwen3_4B-GeneralThought-Q4_K_M-GGUF
Text Generation • 4B • Updated • 12 -
prithivMLmods/Bootes-Qwen3_Coder-Reasoning
Text Generation • 4B • Updated • 17 • 9 -
prithivMLmods/Bootes-Qwen3_Coder-Reasoning-Q4_K_M-GGUF
Text Generation • 4B • Updated • 38 • 2
CoT, LCoT - QwQ Math
-
prithivMLmods/Draconis-Qwen3_Math-4B-Preview
Text Generation • 4B • Updated • 51 -
prithivMLmods/Hatshepsut-Qwen3_QWQ-LCoT-4B
Text Generation • 4B • Updated • 8 -
prithivMLmods/Hatshepsut-Qwen3_QWQ-LCoT-4B-Q4_K_M-GGUF
Text Generation • 4B • Updated • 5 -
prithivMLmods/Tureis-Qwen3_QWQ-4B-Exp
Text Generation • 4B • Updated • 12 • 1
Moderation, Balance, Classifiers
-
prithivMLmods/Weather-Image-Classification
Image Classification • 92.9M • Updated • 1.17k -
prithivMLmods/Watermark-Detection-SigLIP2
Image Classification • 92.9M • Updated • 3.03k • • 30 -
prithivMLmods/TurkishFoods-25
Image Classification • 92.9M • Updated • 7 -
prithivMLmods/Marathi-Sign-Language-Detection
Image Classification • 92.9M • Updated • 5
Moderation, Balance, Classifiers
Moderation, Balance, Classifiers
-
prithivMLmods/RESISC45-SigLIP2
Image Classification • 92.9M • Updated • 27 -
prithivMLmods/PACS-DG-SigLIP2
Image Classification • 92.9M • Updated • 1.1k -
prithivMLmods/Watermark-Detection-SigLIP2
Image Classification • 92.9M • Updated • 3.03k • • 30 -
prithivMLmods/3D-Printed-Or-Not-SigLIP2
Image Classification • 92.9M • Updated • 11
classify one or more scene categories
standard language modeling objective
-
prithivMLmods/Lang-Exster-0.5B-Instruct
Text Generation • 0.5B • Updated • 4 -
prithivMLmods/Lambda-Cancri-1.5B-Exp
Text Generation • 2B • Updated • 3 -
prithivMLmods/Lang-Exster-0.5B-Instruct-ONNX
Text Generation • Updated • 1 -
prithivMLmods/Lang-Exster-0.5B-Instruct-Q8_0-GGUF
Text Generation • 0.5B • Updated • 6
advanced reinforcement learning (RL)
-
prithivMLmods/Castula-U2-QwenRe-1.5B
Text Generation • 2B • Updated • 5 • 2 -
prithivMLmods/Lang-Exster-0.5B-Instruct
Text Generation • 0.5B • Updated • 4 -
prithivMLmods/Lang-Exster-0.5B-Instruct-Q8_0-GGUF
Text Generation • 0.5B • Updated • 6 -
prithivMLmods/Lang-Exster-0.5B-Instruct-ONNX
Text Generation • Updated • 1
Coder, Math. [ Reinforcement learning ]
Y.2 for Coding and Math
Math, Code, General-Purpose
Moderation, Balance, Classifiers
Qwen2 VL
-
prithivMLmods/Callisto-OCR3-2B-Instruct
Image-Text-to-Text • 2B • Updated • 744 • 7 -
Multimodal VLM Thinking
🥠57Lumian-VLR / VisionThink / MiniCPM-V / Typhoon-OCR / olmOCR
-
prithivMLmods/Qwen2-VL-OCR-2B-Instruct
Image-Text-to-Text • 2B • Updated • 998 • 102 -
prithivMLmods/Qwen2-VL-OCR-2B-Instruct-GGUF
Image-Text-to-Text • 2B • Updated • 581 • 4
Age, Gender, Race and More ..
-
prithivMLmods/Age-Classification-SigLIP2
Image Classification • 92.9M • Updated • 92.5k • • 6 -
prithivMLmods/Gender-Classifier-Mini
Image Classification • 92.9M • Updated • 250 • 2 -
prithivMLmods/Rice-Leaf-Disease
Image Classification • 92.9M • Updated • 59 -
prithivMLmods/Indian-Western-Food-34
Image Classification • 92.9M • Updated • 68
Multi-Source Domain Adaptation : Infograph, Quickdraw, Real, Sketch, Fashion
-
prithivMLmods/Painting-126-DomainNet
Image Classification • 93M • Updated • 3 -
prithivMLmods/Sketch-126-DomainNet
Image Classification • 93M • Updated • 4 -
prithivMLmods/Clipart-126-DomainNet
Image Classification • 93M • Updated • 1 -
prithivMLmods/Multisource-121-DomainNet
Image Classification • 93M • Updated • 4
Math, Code, General-Purpose
0.5B - 1B - 3B
-
prithivMLmods/Bellatrix-Tiny-1B-v3-abliterated
Text Generation • 1B • Updated • 7 • 1 -
prithivMLmods/Bellatrix-Tiny-1B-v2-abliterated
Text Generation • 1B • Updated • 6 -
prithivMLmods/Bellatrix-Tiny-1B-R1-abliterated
Text Generation • 1B • Updated • 2 -
prithivMLmods/Bellatrix-Tiny-3B-R1-abliterated
Text Generation • 3B • Updated • 4
Mathematical Models, <=58 Avg
Test finetune
-
prithivMLmods/Deepfake-Quality-Classifier-SigLIP2
Image Classification • 92.9M • Updated • 8 • 1 -
prithivMLmods/Gym-Workout-Classifier-SigLIP2
Image Classification • 92.9M • Updated • 20 • 6 -
prithivMLmods/Facial-Emotion-Detection-SigLIP2
Image Classification • 92.9M • Updated • 185 • 7 -
prithivMLmods/Deepfake-Quality-Classifier2-SigLIP2
Image Classification • 92.9M • Updated • 25 • 2
Comprehensive Demo of Multimodal VLMs on the Hub
StreamlinedMemory
-
prithivMLmods/Sombrero-Opus-14B-Sm1
Text Generation • 15B • Updated • 57 • 2 -
prithivMLmods/Sombrero-Opus-14B-Sm2
Text Generation • 15B • Updated • 63 • 2 -
prithivMLmods/Sombrero-Opus-14B-Sm3
Text Generation • 15B • Updated • 12 • 1 -
prithivMLmods/Sombrero-Opus-14B-Sm4
Text Generation • 15B • Updated • 51 • 3
general purpose r999 multilingual LLMs
-
prithivMLmods/Eridanus-Opus-14B-r999
Text Generation • 15B • Updated • 4 • 3 -
prithivMLmods/Berenices-Opus-14B-r999
Text Generation • 15B • Updated • 2 • 1 -
prithivMLmods/Tucana-Opus-14B-r999
Text Generation • 15B • Updated • 6 • 3 -
prithivMLmods/SmolLM2-360M-Grpo-r999
Text Generation • 0.4B • Updated • 4 • 3
Coding Logic and Creativity !!
-
prithivMLmods/Viper-Coder-v0.1
Text Generation • 15B • Updated • 13 • 1 -
prithivMLmods/Viper-Coder-v1.1
Text Generation • 15B • Updated • 19 • 8 -
prithivMLmods/Viper-Coder-Hybrid-v1.2
Text Generation • 15B • Updated • 16 • 2 -
prithivMLmods/Viper-Coder-Hybrid-v1.3
Text Generation • 15B • Updated • 25 • 9
reasoning+coding
-
prithivMLmods/Viper-Coder-Hybrid-v1.3
Text Generation • 15B • Updated • 25 • 9 -
prithivMLmods/Viper-Coder-Hybrid-v1.2
Text Generation • 15B • Updated • 16 • 2 -
prithivMLmods/Viper-Coder-HybridMini-v1.3
Text Generation • 8B • Updated • 29 • 9 -
prithivMLmods/Viper-Coder-v1.7-Vsm6
Text Generation • 15B • Updated • 19 • 6
Trained based on Flux-generated images and their enhanced prompt captioning and annotations in a simple JSON format.
Coder Models
The garage for 14B and 7B reasoning models, listed based on benchmarks.
-
prithivMLmods/Calcium-Opus-14B-Elite2
Text Generation • 15B • Updated • 20 • 2 -
prithivMLmods/Calcium-Opus-14B-Elite
Text Generation • 15B • Updated • 37 • 4 -
prithivMLmods/Calcium-Opus-14B-Elite2-R1
Text Generation • 15B • Updated • 40 • 7 -
prithivMLmods/Elita-1
Text Generation • 15B • Updated • 21 • 2
14b, 7b reasoning models
-
prithivMLmods/Megatron-Opus-14B-Exp
Text Generation • 15B • Updated • 30 • 3 -
prithivMLmods/Calcium-Opus-14B-Elite2-R1
Text Generation • 15B • Updated • 40 • 7 -
prithivMLmods/Primal-Opus-14B-Optimus-v1
Text Generation • 15B • Updated • 17 • 4 -
prithivMLmods/Megatron-Opus-14B-Stock
Text Generation • 15B • Updated • 4 • 3
Based on Qwen's 2 vL
Model contention for gradual increments in reasoning-specific model evaluations.
-
prithivMLmods/Calcium-Opus-14B-Elite
Text Generation • 15B • Updated • 37 • 4 -
prithivMLmods/Calcium-Opus-14B-Elite2
Text Generation • 15B • Updated • 20 • 2 -
prithivMLmods/Calcium-Opus-14B-Elite3
Text Generation • 15B • Updated • 28 • 2 -
prithivMLmods/Calcium-Opus-14B-Elite4
Text Generation • 15B • Updated • 7 • 3
Express Tiny LLM's
conversational, instruct, 14b Convos < 350 in OpenLLM Evals
-
prithivMLmods/QwQ-LCoT-7B-Instruct
Text Generation • 8B • Updated • 33 • 20 -
prithivMLmods/QwQ-LCoT2-7B-Instruct
Text Generation • 8B • Updated • 9 • 6 -
prithivMLmods/QwQ-LCoT1-Merged
Text Generation • 8B • Updated • 6 • 2 -
prithivMLmods/QwQ-LCoT-14B-Conversational
Text Generation • 15B • Updated • 9 • 5
Opus for chat
Multimodality
Text Generation, Vision Language, Image Generation
Reasoning, Long Chain of Thought, Keyword based problem solve
Grounding, chat
-
prithivMLmods/Qwen2-VL-OCR-2B-Instruct
Image-Text-to-Text • 2B • Updated • 998 • 102 -
prithivMLmods/Qwen2-VL-OCR-2B-Instruct-GGUF
Image-Text-to-Text • 2B • Updated • 581 • 4 -
Multimodal OCR
🍍404Nanonets / olmOCR / RolmOCR / Aya-Vision / Qwen2-VL-OCR
-
Multimodal VLM Thinking
🥠57Lumian-VLR / VisionThink / MiniCPM-V / Typhoon-OCR / olmOCR
Artificial general intelligence
-
strangerzonehf/Flux-Midjourney-Mix2-LoRA
Text-to-Image • Updated • 2.18k • • 546 -
strangerzonehf/Flux-Super-Realism-LoRA
Text-to-Image • Updated • 2.93k • • 270 -
strangerzonehf/Flux-Midjourney-Mix-LoRA
Text-to-Image • Updated • 18 • • 60 -
strangerzonehf/Flux-Animeo-v1-LoRA
Text-to-Image • Updated • 324 • • 22
large, medium, turbo lora
-
prithivMLmods/SD3.5-Large-Photorealistic-LoRA
Text-to-Image • Updated • 129 • 61 -
prithivMLmods/SD3.5-Large-Turbo-HyperRealistic-LoRA
Text-to-Image • Updated • 101 • 22 -
prithivMLmods/SD3.5-Large-Minimal-Blacked-LoRA
Text-to-Image • Updated • 25 • 10 -
prithivMLmods/SD3.5-Turbo-Realism-2.0-LoRA
Text-to-Image • Updated • 27 • 11
Image Gen - Text -to-Image
Are just in initial stage sdxl LoRA
Collection of Various Compression Schemes for Gemma 4
Collection of Gemma-4 Quants
-
prithivMLmods/gemma-4-31B-it-F32-GGUF
Image-Text-to-Text • 31B • Updated • 2 -
prithivMLmods/gemma-4-26B-A4B-it-F32-GGUF
Image-Text-to-Text • 25B • Updated • 1 -
prithivMLmods/gemma-4-E4B-it-F32-GGUF
Image-Text-to-Text • 8B • Updated • 1 -
prithivMLmods/gemma-4-E2B-it-F32-GGUF
Image-Text-to-Text • 5B • Updated • 1
Version 2 in the Unredacted series, with much lower refusal limits, is available in different compression schemes.
-
prithivMLmods/Qwen3-VL-32B-Instruct-v2-MAX-MXFP4
Image-Text-to-Text • 19B • Updated • 7 • 2 -
prithivMLmods/Qwen3.5-9B-abliterated-v2-MAX
Image-Text-to-Text • 9B • Updated • 1.67k • 2 -
prithivMLmods/Qwen3.5-9B-abliterated-v2-MAX-NVFP4
Image-Text-to-Text • 7B • Updated • 10 • 1 -
prithivMLmods/Qwen3.5-9B-abliterated-v2-MAX-FP8
Image-Text-to-Text • 9B • Updated • 3 • 1
Multimodal Collections Sublist
capable of accurately locating and understanding 'any' object | State: Experimental, Category: Object Detection, High-depth analysis in visual tasks
Audio, Image, Image-to-Text
-
Qwen3 VL HF Demo
🔥33Object Detection, Visual Grounding, Keypoint Detection
-
Multimodal OCR2
💻141FireRed / Nanonets / Monkey / Thyme / Typhoon / SmolDocling
-
CUA GUI Operator
💻10Ultra-compact Computer-Use Agent [GUI Localization]
-
NVIDIA Nemotron Parse OCR
🥠7understand document semantics, extract text and tables.
Expert Image Captioning System
-
prithivMLmods/Gliese-Qwen3.5-27B-Abliterated-Caption
Image-Text-to-Text • 27B • Updated • 450 • 6 -
prithivMLmods/Gliese-Qwen3.5-9B-Abliterated-Caption
Image-Text-to-Text • 9B • Updated • 16k • 39 -
prithivMLmods/Gliese-Qwen3.5-4B-Abliterated-Caption
Image-Text-to-Text • 5B • Updated • 3.05k • 7 -
prithivMLmods/Gliese-Qwen3.5-2B-Abliterated-Caption
Image-Text-to-Text • 2B • Updated • 2.3k • 7
Continual “abliteration” models – experimental.
-
prithivMLmods/Qwen3.5-35B-A3B-Unredacted-MAX
Image-Text-to-Text • 35B • Updated • 117 • 1 -
prithivMLmods/Qwen3.5-27B-Unredacted-MAX
Image-Text-to-Text • 27B • Updated • 217 • 4 -
prithivMLmods/Qwen3.5-9B-Unredacted-MAX
Image-Text-to-Text • 9B • Updated • 2.05k • 6 -
prithivMLmods/Qwen3.5-4B-Unredacted-MAX
Image-Text-to-Text • 5B • Updated • 238 • 6
Collection of Region Bounding LoRAs
-
prithivMLmods/QIE-2509-Object-Mover-Bbox
Image-to-Image • Updated • 41 • • 2 -
prithivMLmods/QIE-2511-Object-Mover-Bbox
Image-to-Image • Updated • 156 • • 4 -
prithivMLmods/QIE-2509-Object-Remover-Bbox-v3
Image-to-Image • Updated • 3.48k • • 9 -
prithivMLmods/QIE-2511-Object-Remover-Bbox-v3
Image-to-Image • Updated • 743 • • 3
Collection of Lightweight Qwen3.5 GGUF Models
-
prithivMLmods/Qwen3.5-Thinking-AIO-GGUF
Image-Text-to-Text • 0.8B • Updated • 2.85k • 1 -
prithivMLmods/Qwen3.5-0.8B-f32-GGUF
Image-Text-to-Text • 0.8B • Updated • 824 • 1 -
prithivMLmods/Qwen3.5-2B-f32-GGUF
Image-Text-to-Text • 2B • Updated • 476 • 1 -
prithivMLmods/Qwen3.5-4B-f32-GGUF
Image-Text-to-Text • 4B • Updated • 493 • 1
Collection of Compressed Multimodal VLM Editions on the Hub [ vLLM / LLM Compressor ]
-
prithivMLmods/Gliese-CUA-Tool-Call-8B-FP8
Image-Text-to-Text • 8B • Updated • 9 • 2 -
prithivMLmods/Gliese-OCR-7B-Post2.0-final-FP8
Image-Text-to-Text • 8B • Updated • 7 • 1 -
prithivMLmods/MedMO-8B-FP8
Image-Text-to-Text • 9B • Updated • 5 • 1 -
prithivMLmods/Jan-v2-VL-med-FP8
Image-Text-to-Text • 9B • Updated • 6 • 1
Continual “abliteration” models – experimental.
-
prithivMLmods/Qwen2.5-VL-32B-Instruct-Unredacted-MAX
Image-Text-to-Text • 33B • Updated • 233 • 4 -
prithivMLmods/Qwen2.5-VL-7B-Instruct-Unredacted-MAX
Image-Text-to-Text • 8B • Updated • 88 • 4 -
prithivMLmods/Qwen2.5-VL-3B-Instruct-Unredacted-MAX
Image-Text-to-Text • 4B • Updated • 25 • 2 -
prithivMLmods/Qwen2.5-VL-32B-Instruct-Unredacted-MAX-FP8
Image-Text-to-Text • 33B • Updated • 9 • 1
Collection of FP8 compression techniques, Diffusers–Transformers converted weights, and more for QIE.
[FP8_DYNAMIC] multi-stage trained continual "abliteration" approach for the qwen3-vl series models
-
prithivMLmods/Qwen3-VL-32B-Instruct-Unredacted-MAX-FP8
Image-Text-to-Text • 33B • Updated • 207 • 3 -
prithivMLmods/Qwen3-VL-32B-Thinking-Unredacted-MAX-FP8
Image-Text-to-Text • 33B • Updated • 17 • 1 -
prithivMLmods/Qwen3-VL-8B-Instruct-Unredacted-MAX-FP8
Image-Text-to-Text • 9B • Updated • 24 • 2 -
prithivMLmods/Qwen3-VL-8B-Thinking-Unredacted-MAX-FP8
Image-Text-to-Text • 9B • Updated • 8 • 1
multi-stage trained continual "abliteration" approach for the qwen3-vl series models
-
prithivMLmods/Qwen3-VL-4B-Instruct-Unredacted-MAX
Image-Text-to-Text • 4B • Updated • 1.86k • 17 -
prithivMLmods/Qwen3-VL-4B-Thinking-Unredacted-MAX
Image-Text-to-Text • 4B • Updated • 28 • 1 -
prithivMLmods/Qwen3-VL-8B-Instruct-Unredacted-MAX
Image-Text-to-Text • 9B • Updated • 856 • 10 -
prithivMLmods/Qwen3-VL-8B-Thinking-Unredacted-MAX
Image-Text-to-Text • 9B • Updated • 43 • 3
multi-stage trained continual "abliteration" approach for the qwen3-vl series models (GGUF)
-
prithivMLmods/Qwen3-VL-4B-Instruct-Unredacted-MAX-GGUF
Image-Text-to-Image • 4B • Updated • 3.17k • 7 -
prithivMLmods/Qwen3-VL-4B-Thinking-Unredacted-MAX-GGUF
Image-Text-to-Text • 4B • Updated • 171 • 1 -
prithivMLmods/Qwen3-VL-8B-Instruct-Unredacted-MAX-GGUF
Image-Text-to-Text • 8B • Updated • 905 • 5 -
prithivMLmods/Qwen3-VL-8B-Thinking-Unredacted-MAX-GGUF
Image-Text-to-Image • 8B • Updated • 1.49k • 3
Iterations of my doc ocr models timeline of continual training built on top of qwen-vl models.
-
prithivMLmods/Camel-Doc-OCR-062825
Image-Text-to-Text • 8B • Updated • 57 • 13 -
prithivMLmods/Megalodon-OCR-Sync-0713
Image-Text-to-Text • 4B • Updated • 22 • 4 -
prithivMLmods/Camel-Doc-OCR-080125
Image-Text-to-Text • 8B • Updated • 227 • 8 -
prithivMLmods/Gliese-OCR-7B-Post1.0
Image-Text-to-Text • 8B • Updated • 62 • 13
adapter LoRA developed for Qwen’s Qwen-Image-Edit-2511 image-to-image model
-
prithivMLmods/QIE-2511-Studio-DeLight
Image-to-Image • Updated • 12.7k • • 22 -
prithivMLmods/QIE-2511-Outfit-Design-Layout
Image-to-Image • Updated • 3.33k • • 4 -
prithivMLmods/QIE-2511-Zoom-Master
Image-to-Image • Updated • 1.23k • • 18 -
prithivMLmods/QIE-2511-Object-Remover-v2
Image-to-Image • Updated • 3.09k • • 18
adapter LoRA developed for Qwen’s Qwen-Image-Edit-2511 image-to-image model
-
prithivMLmods/Qwen-Image-Edit-2511-Ultra-Realistic-Portrait
Image-to-Image • Updated • 32.7k • • 54 -
prithivMLmods/QIE-2511-Cinematic-FlatLog-Control
Image-to-Image • Updated • 3.33k • • 4 -
prithivMLmods/Qwen-Image-Edit-2511-Object-Adder
Image-to-Image • Updated • 31.1k • • 32 -
prithivMLmods/Qwen-Image-Edit-2511-Hyper-Realistic-Portrait
Image-to-Image • Updated • 22.2k • • 17
Add or remove the specified objects, flexible for both single-image and multi-image modes.
SFT, RL
-
prithivMLmods/KAIROS-MM-Qwen2.5-VL-7B-RL
Video-Text-to-Text • Updated • 9 • 5 -
prithivMLmods/KAIROS-MM-Qwen2.5-VL-7B-SFT
Video-Text-to-Text • 8B • Updated • 12 • 5 -
prithivMLmods/KAIROS-MM-Qwen2.5-VL-SFT-GGUF
Video-Text-to-Text • 8B • Updated • 25 • 1 -
prithivMLmods/KAIROS-MM-Qwen2.5-VL-7B-SFT-GGUF-AIO-GGUF
Video-Text-to-Text • 8B • Updated • 377 • 1
Localization, Tool Calling, and Navigation
-
prithivMLmods/Gliese-CUA-Tool-Call-8B
Image-Text-to-Text • 8B • Updated • 11 • 3 -
prithivMLmods/Gliese-CUA-Tool-Call-8B-GGUF
Image-Text-to-Text • 8B • Updated • 223 • 2 -
prithivMLmods/Gliese-CUA-Tool-Call-8B-Localization-GGUF
Image-Text-to-Text • 8B • Updated • 145 • 1 -
prithivMLmods/Herculis-CUA-GUI-Actioner-4B
Image-Text-to-Text • 4B • Updated • 13 • 2
Document-AI, HTML, OCR
-
prithivMLmods/proxima-ocr-d.markdown-post3.0.l
Image-Text-to-Text • 9B • Updated • 69 • 5 -
prithivMLmods/epsilon-ocr-d.markdown-post3.0.m
Image-Text-to-Text • 4B • Updated • 16 • 3 -
prithivMLmods/proxima-ocr-d.markdown-post3.0.l-GGUF
Image-Text-to-Text • 8B • Updated • 90 • 2 -
prithivMLmods/epsilon-ocr-d.markdown-post3.0.m-GGUF
Image-Text-to-Text • 3B • Updated • 122 • 1
Collection of Gliese series OCR models
-
prithivMLmods/Gliese-OCR-7B-Post1.0
Image-Text-to-Text • 8B • Updated • 62 • 13 -
prithivMLmods/Gliese-OCR-7B-Post1.0-GGUF
Image-Text-to-Text • 8B • Updated • 86 • 1 -
prithivMLmods/Gliese-OCR-7B-Post2.0-final
Image-Text-to-Text • 8B • Updated • 13 • 6 -
prithivMLmods/Gliese-OCR-7B-Post2.0-final-GGUF
Image-Text-to-Text • 8B • Updated • 328 • 1
abliterated & [safe and controlled caption generation]
-
prithivMLmods/Qwen3-VisionCaption-2B
Image-Text-to-Text • 2B • Updated • 48 • 5 -
prithivMLmods/Qwen3-VisionCaption-2B-GGUF
Image-Text-to-Text • 2B • Updated • 829 • 9 -
prithivMLmods/Qwen3-VisionCaption-2B-it-REDACTED
Image-Text-to-Text • 2B • Updated • 10 • 1 -
prithivMLmods/Qwen3-VisionCaption-2B-it-REDACTED-GGUF
Image-Text-to-Text • 2B • Updated • 312 • 1
Domain-Specific Downstream Tasks
-
prithivMLmods/MetaCLIP-2-Age-Range-Estimator
Image Classification • 21.7M • Updated • 10 • 7 -
prithivMLmods/MetaCLIP-2-Gender-Identifier
Image Classification • 21.7M • Updated • 13 • 2 -
prithivMLmods/MetaCLIP-2-Open-Scene
Image Classification • 21.7M • Updated • 12 • 1 -
prithivMLmods/MetaCLIP-2-Cifar10
Image Classification • 21.7M • Updated • 9 • 1
All-in-One Quants
-
prithivMLmods/Qwen3-VL-8B-Abliterated-Caption-it-GGUF
Image-Text-to-Text • 8B • Updated • 1.46k • 6 -
prithivMLmods/Qwen2.5-VL-Abliterated-Caption-GGUF
Image-Text-to-Text • 3B • Updated • 819 • 16 -
prithivMLmods/DeepCaption-VLA-V2.0-7B
Image-Text-to-Text • 8B • Updated • 107 • 7 -
prithivMLmods/Qwen3-VL-8B-Instruct-abliterated-v2
Image-Text-to-Text • 9B • Updated • 1.97k • 27
All-in-One Quants
-
prithivMLmods/Gliese-OCR-7B-Post2.0-final-GGUF
Image-Text-to-Text • 8B • Updated • 328 • 1 -
prithivMLmods/Gliese-OCR-7B-Post1.0-GGUF
Image-Text-to-Text • 8B • Updated • 86 • 1 -
prithivMLmods/Camel-Doc-OCR-080125-GGUF
Image-Text-to-Text • 8B • Updated • 346 • 2 -
prithivMLmods/granite-docling-258M-f32-GGUF
Image-Text-to-Text • 0.2B • Updated • 149 • 3
Multiple Adapters for Heterogeneous Angles
Qwen2.5VL OCR (Model Tree)
-
prithivMLmods/Gliese-OCR-7B-Post2.0-final
Image-Text-to-Text • 8B • Updated • 13 • 6 -
prithivMLmods/Gliese-OCR-7B-Post1.0
Image-Text-to-Text • 8B • Updated • 62 • 13 -
prithivMLmods/Camel-Doc-OCR-080125
Image-Text-to-Text • 8B • Updated • 227 • 8 -
prithivMLmods/Megalodon-OCR-Sync-0713
Image-Text-to-Text • 4B • Updated • 22 • 4
Qwen3VL, Qwen2.5VL
-
prithivMLmods/Qwen3-VL-8B-Abliterated-Caption-it
Image-Text-to-Text • 9B • Updated • 1.11k • 31 -
prithivMLmods/Qwen2.5-VL-7B-Abliterated-Caption-it
Image-Text-to-Text • 8B • Updated • 2.49k • 44 -
prithivMLmods/Qwen2.5-VL-3B-Abliterated-Caption-it
Image-Text-to-Text • 4B • Updated • 48 • 7 -
prithivMLmods/Qwen2.5-VL-Abliterated-Caption-GGUF
Image-Text-to-Text • 3B • Updated • 819 • 16
Qwen3-VL Abliterated Model Collection [ Version 1.0 ]
-
prithivMLmods/Qwen3-VL-32B-Instruct-abliterated-v1
Image-Text-to-Text • 33B • Updated • 97 • 6 -
prithivMLmods/Qwen3-VL-32B-Thinking-abliterated-v1
Image-Text-to-Text • 33B • Updated • 71 • 6 -
prithivMLmods/Qwen3-VL-30B-A3B-Thinking-abliterated-v1
Image-Text-to-Text • 31B • Updated • 29 • 4 -
prithivMLmods/Qwen3-VL-30B-A3B-Instruct-abliterated-v1
Image-Text-to-Text • 31B • Updated • 13.5k • 3
Qwen2.5-VL and Qwen3-VL
-
prithivMLmods/Qwen3-VL-4B-Instruct-abliterated-v1
Image-Text-to-Text • 4B • Updated • 1.01k • 21 -
prithivMLmods/Qwen3-VL-4B-Thinking-abliterated-v1
Image-Text-to-Text • 4B • Updated • 187 • 18 -
prithivMLmods/Qwen2.5-VL-7B-Abliterated-Caption-it
Image-Text-to-Text • 8B • Updated • 2.49k • 44 -
prithivMLmods/Qwen2.5-VL-3B-Abliterated-Caption-it
Image-Text-to-Text • 4B • Updated • 48 • 7
Multilingual upstream VLMs - Caption, OCR, Markdown, HTML Render
-
prithivMLmods/DeepCaption-VLA-V2.0-7B
Image-Text-to-Text • 8B • Updated • 107 • 7 -
prithivMLmods/DeepCaption-VLA-7B
Image-Text-to-Text • 8B • Updated • 245 • 22 -
prithivMLmods/Camel-Doc-OCR-080125
Image-Text-to-Text • 8B • Updated • 227 • 8 -
prithivMLmods/Camel-Doc-OCR-062825
Image-Text-to-Text • 8B • Updated • 57 • 13
List of Models for Multimodal VLM Parsing
Multimodal VLM and LLM : 'Gliese' Collection of Models
agentic reasoning, web search orchestration
-
prithivMLmods/Dorado-WebSurf_Tool-ext
Text Generation • 4B • Updated • 6 • 4 -
prithivMLmods/Dorado-WebSurf_Tool-ext-GGUF
Text Generation • 4B • Updated • 120 • 1 -
prithivMLmods/Gliese-Query_Tool-0.6B
Text Generation • 0.6B • Updated • 5 -
prithivMLmods/Gliese-Query_Tool-0.6B-GGUF
Text Generation • 0.6B • Updated • 141
Abliterated Reasoning & polished token probabilities, enhancing balanced multilingual generation
-
prithivMLmods/Kepler-186f-Qwen3-Instruct-4B
Text Generation • 4B • Updated • 6 • 3 -
prithivMLmods/Kepler-186f-Qwen3-Instruct-4B-GGUF
Text Generation • 4B • Updated • 83 • 3 -
prithivMLmods/Kepler-Qwen3-4B-Super-Thinking
Text Generation • 4B • Updated • 4 • 5 -
prithivMLmods/Kepler-Qwen3-4B-Super-Thinking-GGUF
Text Generation • 4B • Updated • 179
I2I Optimization
Polished and Controlled Gen
Polished Tokens, Improved Multilingual Support, and Controlled Abliteration.
-
prithivMLmods/Carinae-Qwen3-Radiation-4B
Text Generation • 4B • Updated • 5 • 2 -
prithivMLmods/MobileLLM-R1-950M-Radiation
Text Generation • 0.9B • Updated -
prithivMLmods/Leporis-Qwen3-Radiation-1.7B
Text Generation • 2B • Updated • 8 -
prithivMLmods/Leporis-Qwen3-Radiation-1.7B-GGUF
Text Generation • 2B • Updated • 83 • 2
Photo Restore, Polaroid, Inter-style Mix and more...
Multimodal models
-
prithivMLmods/Qwen2.5-VL-7B-Abliterated-Caption-it
Image-Text-to-Text • 8B • Updated • 2.49k • 44 -
prithivMLmods/Qwen2.5-VL-Abliterated-Caption-GGUF
Image-Text-to-Text • 3B • Updated • 819 • 16 -
prithivMLmods/Caption3o-XL-2B-Qwen2VL
Image-Text-to-Text • 2B • Updated • 20 • 2 -
prithivMLmods/Qwen2.5-VL-3B-Abliterated-Caption-it
Image-Text-to-Text • 4B • Updated • 48 • 7
filtered for an sfw captioning set of image pairs.
post1.0 ft. camel-doc-ocr-062825
random event simulations, logical problem analysis, and structured reasoning tasks
-
prithivMLmods/Capella-Qwen3-DS-V3.1-4B
Text Generation • 4B • Updated • 8 • 4 -
prithivMLmods/Capella-Qwen3-DS-V3.1-4B-GGUF
Text Generation • 4B • Updated • 256 -
prithivMLmods/Mintaka-Qwen3-1.6B-V3.1
Text Generation • 2B • Updated • 6 • 1 -
prithivMLmods/Mintaka-Qwen3-1.6B-V3.1-GGUF
Text Generation • 2B • Updated • 135 • 1
Vision Language Attribution
experimental
-
prithivMLmods/Pyxidis-Manim-CodeGen-1.7B
Text Generation • 2B • Updated • 43 • 3 -
prithivMLmods/Pyxidis-Manim-CodeGen-1.7B-GGUF
Text Generation • 2B • Updated • 639 • 3 -
prithivMLmods/Regulus-Qwen3-R1-Llama-Distill-1.7B
Text Generation • 2B • Updated • 10 -
prithivMLmods/Regulus-Qwen3-R1-Llama-Distill-GGUF
Text Generation • 2B • Updated • 130 • 2
Qwen3 base
-
prithivMLmods/Demeter-LongCoT-Qwen3-1.7B
Text Generation • 2B • Updated • 19 • 1 -
prithivMLmods/Demeter-LongCoT-Qwen3-1.7B-GGUF
Text Generation • 2B • Updated • 162 • 2 -
prithivMLmods/Canum-med-Qwen3-Reasoning
Text Generation • 2B • Updated • 62 • 3 -
prithivMLmods/Canum-med-Qwen3-Reasoning-GGUF
Text Generation • 2B • Updated • 91
Illustration Design, Style Intermix
Mixture of Domains
-
prithivMLmods/Gacrux-R1-Qwen3-1.7B-MoD
Text Generation • 2B • Updated • 19 • 3 -
prithivMLmods/Gacrux-R1-Qwen3-1.7B-MoD-GGUF
Text Generation • 2B • Updated • 35 -
prithivMLmods/Panacea-MegaScience-Qwen3-1.7B
Text Generation • 2B • Updated • 9 -
prithivMLmods/Panacea-MegaScience-Qwen3-1.7B-GGUF
Text Generation • 2B • Updated • 43
Reasoning, Document Extraction, Table Reconstruction
Flux.1 (Krea, Dev, Schnell), Qwen-Image, Nano-Banana, Qwen-Image-Edit
vlm extended reasoning, captioning
qwen2.5-vl : 3b, 7b caption
DAG, STEM Reasoning
-
prithivMLmods/Cerium-Qwen3-R1-Dev
Text Generation • 0.6B • Updated • 5 -
prithivMLmods/Cerium-Qwen3-R1-Dev-GGUF
Text Generation • 0.6B • Updated • 80 -
prithivMLmods/Telescopium-Acyclic-Qwen3-0.6B
Text Generation • 0.6B • Updated • 7 -
prithivMLmods/Telescopium-Acyclic-Qwen3-0.6B-GGUF
Text Generation • 0.6B • Updated • 21
max - f32
-
prithivMLmods/Qwen3-4B-Thinking-2507-GGUF
Text Generation • 4B • Updated • 120 • 1 -
prithivMLmods/Qwen3-4B-Instruct-2507-GGUF
Text Generation • 4B • Updated • 194 • 2 -
prithivMLmods/Qwen3-4B-2507-abliterated-GGUF
Text Generation • 4B • Updated • 901 • 9 -
prithivMLmods/MegaScience-Qwen-GGUF
Text Generation • 2B • Updated • 150 • 1
mixture of domains
<think>
tiny models
-
Super OCRs Demo
🧪41Experiment with small super OCR models here.
-
Multimodal OCR2
💻141FireRed / Nanonets / Monkey / Thyme / Typhoon / SmolDocling
-
Multimodal OCR
🍍404Nanonets / olmOCR / RolmOCR / Aya-Vision / Qwen2-VL-OCR
-
VisionScope-R2
🔍109DeepCaption / SkyCaptioner / SpaceThinker / Core / SpaceOm
qwen3
(FLUX.1-schnell + FLUX.1-Krea-dev) | (Flux.1-Dev + Flux.1-Krea-Dev)
Document Retrieval, Content Extraction, and Analysis Recognition.
-
prithivMLmods/Camel-Doc-OCR-080125
Image-Text-to-Text • 8B • Updated • 227 • 8 -
prithivMLmods/Camel-Doc-OCR-080125-GGUF
Image-Text-to-Text • 8B • Updated • 346 • 2 -
prithivMLmods/Camel-Doc-OCR-062825
Image-Text-to-Text • 8B • Updated • 57 • 13 -
prithivMLmods/Camel-Doc-OCR-062825-mmp-GGUF
Image-Text-to-Text • 8B • Updated • 36 • 1
(Flux.1-Dev + Flux.1-Krea-Dev)
Thinking / No-Thinking
Multimodal VLMs for Domain-Specific Tasks: OCR, Reasoning, and Captioning
-
prithivMLmods/Camel-Doc-OCR-080125
Image-Text-to-Text • 8B • Updated • 227 • 8 -
prithivMLmods/Camel-Doc-OCR-062825
Image-Text-to-Text • 8B • Updated • 57 • 13 -
prithivMLmods/VIREX-062225-exp
Image-Text-to-Text • 8B • Updated • 9 • 3 -
prithivMLmods/coreOCR-7B-050325-preview
Image-Text-to-Text • 8B • Updated • 207 • 13
Image and video frame understanding, contextual analysis, and natural language reasoning, Abliterated Captioning / Uncensored Image Captioning,
(LLM) research, benchmarking, and STEM-focused
qwen2.5, 3
reason/scientific thought mixture
Mixed Model Operations
variable-dimensional pairs dataset
Deep Caption VL - Trained with variable-dimensional pairs
trl / @exp
-
prithivMLmods/SmolLM2-Rethink-360M
Text Generation • 0.4B • Updated • 7 • 1 -
prithivMLmods/SmolLM2-Rethink-135M
Text Generation • 0.1B • Updated • 14 • 2 -
prithivMLmods/SmolLM2-Rethink-135M-GGUF
Text Generation • 0.1B • Updated • 107 -
prithivMLmods/SmolLM2-Rethink-360M-GGUF
Text Generation • 0.4B • Updated • 46
Chain-of-Thought Reasoning, Detailed Image Captioning
new exps
enhances document comprehension capabilities
drex [doc ], virex [ video (image ++) exp ]
Based on Qwen2.5 VL, Qwen2 VL
-
prithivMLmods/docscopeOCR-7B-050425-exp
Image-Text-to-Text • 8B • Updated • 170 • 7 -
prithivMLmods/coreOCR-7B-050325-preview
Image-Text-to-Text • 8B • Updated • 207 • 13 -
prithivMLmods/visionOCR-3B-061125
Image-Text-to-Text • 4B • Updated • 538 • 5 -
prithivMLmods/docscopeOCR-7B-050425-exp-GGUF
Image-Text-to-Text • 8B • Updated • 77 • 3
Reasoning and Non-Reasoning
-
prithivMLmods/Megatron-Bots-1.7B-Reasoning
Text Generation • 2B • Updated • 3 -
prithivMLmods/Megatron-Bots-1.7B-Reasoning-GGUF
Text Generation • 2B • Updated • 44 -
prithivMLmods/Computron-Bots-1.7B-R1
Text Generation • 2B • Updated • 7 -
prithivMLmods/Computron-Bots-1.7B-R1-GGUF
Text Generation • 2B • Updated • 39
coder
-
prithivMLmods/Blitzar-Coder-4B-F.1
Text Generation • 4B • Updated • 20 • 9 -
prithivMLmods/Blitzar-Coder-4B-F.1-GGUF
Text Generation • 4B • Updated • 172 • 7 -
prithivMLmods/Lambda-Equulei-1.5B-xLingual
Text Generation • 2B • Updated • 4 • 3 -
prithivMLmods/Lambda-Equulei-1.5B-xLingual-GGUF
Text Generation • 2B • Updated • 53
RL~Reward Signal
Mixture-of-Thoughts
-
prithivMLmods/Lacaille-MoT-4B-Supreme2
Text Generation • 4B • Updated • 16 • 9 -
prithivMLmods/Lacaille-MoT-4B-Supreme2-GGUF
Text Generation • 4B • Updated • 65 -
prithivMLmods/Capricornus-MoT-1.7B-Supreme1
Text Generation • 2B • Updated • 3 -
prithivMLmods/Capricornus-MoT-1.7B-Supreme1-GGUF
Text Generation • 2B • Updated • 32
Mixture-of-Thoughts
-
prithivMLmods/Theta-Crucis-0.6B-Turbo1
Text Generation • 0.6B • Updated • 3 -
prithivMLmods/Theta-Crucis-0.6B-Turbo1-GGUF
Text Generation • 0.6B • Updated • 34 -
prithivMLmods/Nenque-MoT-0.6B-Elite14
Text Generation • 0.6B • Updated • 4 -
prithivMLmods/Nenque-MoT-0.6B-Elite14-GGUF
Text Generation • 0.6B • Updated • 30
audio classifiers
-
prithivMLmods/Common-Voice-Gender-Detection
Audio Classification • 94.6M • Updated • 185k • 22 -
prithivMLmods/Common-Voice-Gender-Detection-ONNX
Audio Classification • Updated • 698 • 5 -
prithivMLmods/Speech-Emotion-Classification
Audio Classification • 94.6M • Updated • 963 • 9 -
prithivMLmods/Speech-Emotion-Classification-ONNX
Audio Classification • Updated • 15 • 3
math, code
-
prithivMLmods/Wolf-Rayet-2B-Prime3
Text Generation • 2B • Updated • 6 -
prithivMLmods/BetaCeti-Beta-4B-Prime1
Text Generation • 4B • Updated • 7 • 2 -
prithivMLmods/Omega-Herculis-7B-Prime2
Text Generation • 8B • Updated • 3 • 2 -
prithivMLmods/BetaCeti-Beta-4B-Prime1-GGUF
Text Generation • 4B • Updated • 58
models, datasets
-
prithivMLmods/shoe-type-detection
Image Classification • 92.9M • Updated • 70 • 1 -
prithivMLmods/facial-age-detection
Image Classification • 92.9M • Updated • 932 • 9 -
prithivMLmods/tooth-agenesis-siglip2
Image Classification • 92.9M • Updated • 15 • 1 -
strangerguardhf/Tooth-Agenesis-6_Types
Viewer • Updated • 12.3k • 5
qwen2vl
custom llms
-
prithivMLmods/Lynx-TinySync-0.6B
Text Generation • 0.6B • Updated • 4 -
prithivMLmods/Lynx-TinySync-0.6B-GGUF
Text Generation • 0.6B • Updated • 48 -
prithivMLmods/Oganesson-TinyLlama-1.2B
Text Generation • 1B • Updated • 5 -
prithivMLmods/Oganesson-TinyLlama-1.2B-GGUF
Text Generation • 1B • Updated • 140
siglip2 base
(direct, reactive, retrieval-based responses), (reasoning, planning, deeper analysis)
-
prithivMLmods/Magpie-Qwen-DiMind-1.7B
Text Generation • 2B • Updated • 7 • 2 -
prithivMLmods/Magpie-Qwen-DiMind-1.7B-GGUF
Text Generation • 2B • Updated • 26 -
prithivMLmods/Magpie-Qwen-CortexDual-0.6B
Text Generation • 0.6B • Updated • 6 • 2 -
prithivMLmods/Magpie-Qwen-CortexDual-0.6B-GGUF
Text Generation • 0.6B • Updated • 68
Code, Math, Moderately Abliterated
trajectory
image detection
vit, siglip2
There are two means of refuge from the miseries of life: music and cats
Math, Code, Reasoning – Edge Device LLMs
spotting diffusion-generated images in realistic, open-world scenarios
-
prithivMLmods/OpenSDI-Flux.1-SigLIP2
Image Classification • 92.9M • Updated • 117 • 1 -
prithivMLmods/OpenSDI-SDXL-SigLIP2
Image Classification • 92.9M • Updated • 9 -
prithivMLmods/OpenSDI-SD1.5-SigLIP2
Image Classification • 92.9M • Updated • 5 -
prithivMLmods/OpenSDI-SD2.1-SigLIP2
Image Classification • 92.9M • Updated • 4
classification net.
Upto Full precision (float32) version
Cot, LCoT - Reasoning
-
prithivMLmods/Cetus-Qwen3_4B-GeneralThought
Text Generation • 4B • Updated • 6 • 1 -
prithivMLmods/Cetus-Qwen3_4B-GeneralThought-Q4_K_M-GGUF
Text Generation • 4B • Updated • 12 -
prithivMLmods/Bootes-Qwen3_Coder-Reasoning
Text Generation • 4B • Updated • 17 • 9 -
prithivMLmods/Bootes-Qwen3_Coder-Reasoning-Q4_K_M-GGUF
Text Generation • 4B • Updated • 38 • 2
CoT, LCoT - QwQ / R1 Math
CoT, LCoT - QwQ Math
-
prithivMLmods/Draconis-Qwen3_Math-4B-Preview
Text Generation • 4B • Updated • 51 -
prithivMLmods/Hatshepsut-Qwen3_QWQ-LCoT-4B
Text Generation • 4B • Updated • 8 -
prithivMLmods/Hatshepsut-Qwen3_QWQ-LCoT-4B-Q4_K_M-GGUF
Text Generation • 4B • Updated • 5 -
prithivMLmods/Tureis-Qwen3_QWQ-4B-Exp
Text Generation • 4B • Updated • 12 • 1
Moderation, Balance, Classifiers
-
prithivMLmods/Realistic-Gender-Classification
Image Classification • 92.9M • Updated • 2.52k • • 7 -
prithivMLmods/Realistic-Portrait-Gender-1024px
Viewer • Updated • 3.2k • 40 • 3 -
prithivMLmods/Document-Type-Detection
Image Classification • 92.9M • Updated • 160 -
prithivMLmods/Document-Type-Detection
Viewer • Updated • 12k • 51 • 1
Moderation, Balance, Classifiers
-
prithivMLmods/Weather-Image-Classification
Image Classification • 92.9M • Updated • 1.17k -
prithivMLmods/Watermark-Detection-SigLIP2
Image Classification • 92.9M • Updated • 3.03k • • 30 -
prithivMLmods/TurkishFoods-25
Image Classification • 92.9M • Updated • 7 -
prithivMLmods/Marathi-Sign-Language-Detection
Image Classification • 92.9M • Updated • 5
DocVQA, RealWorldQA, MTVQA
Moderation, Balance, Classifiers
moderately abliterated and improved context awareness and moderate behavioral flexibility variant of Qwen3.
Moderation, Balance, Classifiers
-
prithivMLmods/RESISC45-SigLIP2
Image Classification • 92.9M • Updated • 27 -
prithivMLmods/PACS-DG-SigLIP2
Image Classification • 92.9M • Updated • 1.1k -
prithivMLmods/Watermark-Detection-SigLIP2
Image Classification • 92.9M • Updated • 3.03k • • 30 -
prithivMLmods/3D-Printed-Or-Not-SigLIP2
Image Classification • 92.9M • Updated • 11
Robust Policy Optimization (RPO)
-
prithivMLmods/Diophantus-14B-R1-Instruct
Text Generation • 15B • Updated • 4 -
prithivMLmods/Belenos-8574-14B-GOP
Text Generation • 15B • Updated • 5 • 1 -
prithivMLmods/Geminorum-Wasat-14B-Instruct
Text Generation • 15B • Updated • 4 -
prithivMLmods/Rapeto-ReDistill-14B-GOP
Text Generation • 15B • Updated • 5
classify one or more scene categories
advanced reinforcement learning (RL)
-
prithivMLmods/Gamma-Velorum-1.5B-Thinker
Text Generation • 2B • Updated • 5 -
prithivMLmods/Deepthink-1.5B-Open-PRM
Text Generation • 2B • Updated • 2 -
prithivMLmods/Deepthink-1.5B-Open-PRM-Q8_0-GGUF
Text Generation • 2B • Updated • 5 • 3 -
prithivMLmods/TESS-QwenRe-1.5B
Text Generation • 2B • Updated • 4
standard language modeling objective
-
prithivMLmods/Lang-Exster-0.5B-Instruct
Text Generation • 0.5B • Updated • 4 -
prithivMLmods/Lambda-Cancri-1.5B-Exp
Text Generation • 2B • Updated • 3 -
prithivMLmods/Lang-Exster-0.5B-Instruct-ONNX
Text Generation • Updated • 1 -
prithivMLmods/Lang-Exster-0.5B-Instruct-Q8_0-GGUF
Text Generation • 0.5B • Updated • 6
Moderation, Balance, Classifiers
-
prithivMLmods/Anime-Classification-v1.0
Image Classification • 92.9M • Updated • 145 • 1 -
prithivMLmods/Facial-Emotion-Detection-SigLIP2
Image Classification • 92.9M • Updated • 185 • 7 -
prithivMLmods/IndoorOutdoorNet
Image Classification • 92.9M • Updated • 52 • 3 -
prithivMLmods/Multilabel-GeoSceneNet
Image Classification • 92.9M • Updated • 10 • 4
advanced reinforcement learning (RL)
-
prithivMLmods/Castula-U2-QwenRe-1.5B
Text Generation • 2B • Updated • 5 • 2 -
prithivMLmods/Lang-Exster-0.5B-Instruct
Text Generation • 0.5B • Updated • 4 -
prithivMLmods/Lang-Exster-0.5B-Instruct-Q8_0-GGUF
Text Generation • 0.5B • Updated • 6 -
prithivMLmods/Lang-Exster-0.5B-Instruct-ONNX
Text Generation • Updated • 1
advanced reinforcement learning (RL)
Coder, Math. [ Reinforcement learning ]
Math, Reasoning
-
prithivMLmods/CEERS-2112-14B-Instruct
Text Generation • 15B • Updated • 8 -
prithivMLmods/Canum-Venaticorum-14B-B.1
Text Generation • 15B • Updated • 4 -
prithivMLmods/Magellanic-Qwen-14B-R1
Text Generation • 15B • Updated • 8 -
prithivMLmods/Camelopardalis-650-14B-Instruct
Text Generation • 15B • Updated • 4
Y.2 for Coding and Math
Usage, Season, BaseColour, ArticleType, SubCategory, MasterCategory, Gender
-
prithivMLmods/Fashion-Product-Gender
Image Classification • 92.9M • Updated • 13 -
prithivMLmods/Fashion-Product-masterCategory
Image Classification • 92.9M • Updated • 13 -
prithivMLmods/Fashion-Product-subCategory
Image Classification • 92.9M • Updated • 31 • 2 -
prithivMLmods/Fashion-Product-articleType
Image Classification • 93M • Updated • 13
Math, Code, General-Purpose
Moderation, Balance, Classifiers
-
prithivMLmods/Age-Classification-SigLIP2
Image Classification • 92.9M • Updated • 92.5k • • 6 -
prithivMLmods/Mature-Content-Detection
Image Classification • 92.9M • Updated • 642 • 7 -
prithivMLmods/Mirage-Photo-Classifier
Image Classification • 92.9M • Updated • 50 • • 2 -
prithivMLmods/Human-Action-Recognition
Image Classification • 92.9M • Updated • 333 • 6
Moderation, Balance, Classifiers
Domain Specific Classification Models : SigLIP2
-
prithivMLmods/Hand-Gesture-2-Robot
Image Classification • 92.9M • Updated • 14 • 2 -
prithivMLmods/Trash-Net
Image Classification • 92.9M • Updated • 207 • 3 -
prithivMLmods/Road-Subsigns-Classification
Image Classification • 92.9M • Updated • 18 • 1 -
prithivMLmods/PussyCat-vs-Doggie-SigLIP2
Image Classification • 92.9M • Updated • 4
Qwen2 VL
-
prithivMLmods/Callisto-OCR3-2B-Instruct
Image-Text-to-Text • 2B • Updated • 744 • 7 -
Multimodal VLM Thinking
🥠57Lumian-VLR / VisionThink / MiniCPM-V / Typhoon-OCR / olmOCR
-
prithivMLmods/Qwen2-VL-OCR-2B-Instruct
Image-Text-to-Text • 2B • Updated • 998 • 102 -
prithivMLmods/Qwen2-VL-OCR-2B-Instruct-GGUF
Image-Text-to-Text • 2B • Updated • 581 • 4
Names are randomly assigned to the respective TTS model based on gender, and the generated voice will have a radio and clean essence. [ Llama ]
Age, Gender, Race and More ..
-
prithivMLmods/Age-Classification-SigLIP2
Image Classification • 92.9M • Updated • 92.5k • • 6 -
prithivMLmods/Gender-Classifier-Mini
Image Classification • 92.9M • Updated • 250 • 2 -
prithivMLmods/Rice-Leaf-Disease
Image Classification • 92.9M • Updated • 59 -
prithivMLmods/Indian-Western-Food-34
Image Classification • 92.9M • Updated • 68
Raptor X: Advanced UI Coder, Reasoning and General-Purpose Coder, and Math LLM
Multi-Source Domain Adaptation : Infograph, Quickdraw, Real, Sketch, Fashion
-
prithivMLmods/Painting-126-DomainNet
Image Classification • 93M • Updated • 3 -
prithivMLmods/Sketch-126-DomainNet
Image Classification • 93M • Updated • 4 -
prithivMLmods/Clipart-126-DomainNet
Image Classification • 93M • Updated • 1 -
prithivMLmods/Multisource-121-DomainNet
Image Classification • 93M • Updated • 4
Math, Code, General-Purpose : Multipurpose
Math, Code, General-Purpose
vit, siglip
-
prithivMLmods/Fashion-Mnist-SigLIP2
Image Classification • 92.9M • Updated • 37 • 4 -
prithivMLmods/Alphabet-Sign-Language-Detection
Image Classification • 92.9M • Updated • 614 • 8 -
prithivMLmods/Traffic-Density-Classification
Image Classification • 92.9M • Updated • 134 • 2 -
prithivMLmods/Dog-Breed-120
Image Classification • 93M • Updated • 379 • 1
0.5B - 1B - 3B
-
prithivMLmods/Bellatrix-Tiny-1B-v3-abliterated
Text Generation • 1B • Updated • 7 • 1 -
prithivMLmods/Bellatrix-Tiny-1B-v2-abliterated
Text Generation • 1B • Updated • 6 -
prithivMLmods/Bellatrix-Tiny-1B-R1-abliterated
Text Generation • 1B • Updated • 2 -
prithivMLmods/Bellatrix-Tiny-3B-R1-abliterated
Text Generation • 3B • Updated • 4
OpenLLM Leaderboard
-
prithivMLmods/Galactic-Qwen-14B-Exp2
Text Generation • 15B • Updated • 8 • 10 -
prithivMLmods/Sombrero-Opus-14B-Elite5
Text Generation • 15B • Updated • 14 • 3 -
prithivMLmods/Equuleus-Opus-14B-Exp
Text Generation • 15B • Updated • 7 • 2 -
prithivMLmods/Sombrero-Opus-14B-Elite6
Text Generation • 15B • Updated • 10 • 2
Mathematical Models, <=58 Avg
Experimentals
-
prithivMLmods/Methuselah-PSR-B1620-26b-14B-Exp
Text Generation • 15B • Updated • 2 • 1 -
prithivMLmods/Galactic-Qwen-14B-Exp2
Text Generation • 15B • Updated • 8 • 10 -
prithivMLmods/Volans-Opus-14B-Exp
Text Generation • 15B • Updated • 7 • 2 -
prithivMLmods/Gaea-Opus-14B-Exp
Text Generation • 15B • Updated • 5 • 2
Test finetune
-
prithivMLmods/Deepfake-Quality-Classifier-SigLIP2
Image Classification • 92.9M • Updated • 8 • 1 -
prithivMLmods/Gym-Workout-Classifier-SigLIP2
Image Classification • 92.9M • Updated • 20 • 6 -
prithivMLmods/Facial-Emotion-Detection-SigLIP2
Image Classification • 92.9M • Updated • 185 • 7 -
prithivMLmods/Deepfake-Quality-Classifier2-SigLIP2
Image Classification • 92.9M • Updated • 25 • 2
Experimentals
Comprehensive Demo of Multimodal VLMs on the Hub
Coding, Mathematical Problem Solving
StreamlinedMemory
-
prithivMLmods/Sombrero-Opus-14B-Sm1
Text Generation • 15B • Updated • 57 • 2 -
prithivMLmods/Sombrero-Opus-14B-Sm2
Text Generation • 15B • Updated • 63 • 2 -
prithivMLmods/Sombrero-Opus-14B-Sm3
Text Generation • 15B • Updated • 12 • 1 -
prithivMLmods/Sombrero-Opus-14B-Sm4
Text Generation • 15B • Updated • 51 • 3
14b - 32b experimental ft
general purpose r999 multilingual LLMs
-
prithivMLmods/Eridanus-Opus-14B-r999
Text Generation • 15B • Updated • 4 • 3 -
prithivMLmods/Berenices-Opus-14B-r999
Text Generation • 15B • Updated • 2 • 1 -
prithivMLmods/Tucana-Opus-14B-r999
Text Generation • 15B • Updated • 6 • 3 -
prithivMLmods/SmolLM2-360M-Grpo-r999
Text Generation • 0.4B • Updated • 4 • 3
general purpose 14b llms
-
prithivMLmods/Messier-Opus-14B-Elite7
Text Generation • 15B • Updated • 76 • 2 -
prithivMLmods/Lacerta-Opus-14B-Elite8
Text Generation • 15B • Updated • 5 • 2 -
prithivMLmods/Viper-OneCoder-UIGEN
Text Generation • 15B • Updated • 11 • 3 -
prithivMLmods/Viper-Coder-v1.4
Text Generation • 15B • Updated • 14 • 4
Coding Logic and Creativity !!
-
prithivMLmods/Viper-Coder-v0.1
Text Generation • 15B • Updated • 13 • 1 -
prithivMLmods/Viper-Coder-v1.1
Text Generation • 15B • Updated • 19 • 8 -
prithivMLmods/Viper-Coder-Hybrid-v1.2
Text Generation • 15B • Updated • 16 • 2 -
prithivMLmods/Viper-Coder-Hybrid-v1.3
Text Generation • 15B • Updated • 25 • 9
SiglipForImageClassification
-
prithivMLmods/AI-vs-Deepfake-vs-Real-Siglip2
Image Classification • 92.9M • Updated • 24.3k • • 2 -
prithivMLmods/Guard-Against-Unsafe-Content-Siglip2
Image Classification • 92.9M • Updated • 7 -
prithivMLmods/Deepfake-Detect-Siglip2
Image Classification • 92.9M • Updated • 1.26k • • 3 -
prithivMLmods/Fire-Detection-Siglip2
Image Classification • 92.9M • Updated • 1.2k • • 4
reasoning+coding
-
prithivMLmods/Viper-Coder-Hybrid-v1.3
Text Generation • 15B • Updated • 25 • 9 -
prithivMLmods/Viper-Coder-Hybrid-v1.2
Text Generation • 15B • Updated • 16 • 2 -
prithivMLmods/Viper-Coder-HybridMini-v1.3
Text Generation • 8B • Updated • 29 • 9 -
prithivMLmods/Viper-Coder-v1.7-Vsm6
Text Generation • 15B • Updated • 19 • 6
based on recent dataset
-
prithivMLmods/AI-vs-Deepfake-vs-Real
Image Classification • 85.8M • Updated • 380 • 9 -
prithivMLmods/AI-vs-Deepfake-vs-Real-ONNX
Image Classification • Updated • 504 • 2 -
prithivMLmods/AI-vs-Deepfake-vs-Real
Viewer • Updated • 10k • 49 • 13 -
prithivMLmods/Deepfake-Detection-Exp-02-22
Image Classification • 87.5M • Updated • 140 • 4
Trained based on Flux-generated images and their enhanced prompt captioning and annotations in a simple JSON format.
providing assistance
-
prithivMLmods/Sombrero-Opus-14B-Elite5
Text Generation • 15B • Updated • 14 • 3 -
prithivMLmods/Dinobot-Opus-14B-Exp
Text Generation • 15B • Updated • 52 • 3 -
prithivMLmods/Magellanic-Opus-14B-Exp
Text Generation • 15B • Updated • 9 • 2 -
prithivMLmods/Viper-Coder-v1.1
Text Generation • 15B • Updated • 19 • 8
Coder Models
Classification of Good and Bad Quality Deepfakes { Datasets }
The garage for 14B and 7B reasoning models, listed based on benchmarks.
-
prithivMLmods/Calcium-Opus-14B-Elite2
Text Generation • 15B • Updated • 20 • 2 -
prithivMLmods/Calcium-Opus-14B-Elite
Text Generation • 15B • Updated • 37 • 4 -
prithivMLmods/Calcium-Opus-14B-Elite2-R1
Text Generation • 15B • Updated • 40 • 7 -
prithivMLmods/Elita-1
Text Generation • 15B • Updated • 21 • 2
Controllable Classification of Good and Bad Quality Deepfakes
-
prithivMLmods/Deepfake-QualityAssess-88M
Image Classification • 87.5M • Updated • 7 • 1 -
prithivMLmods/Deepfake-QualityAssess2.0-85M
Image Classification • 85.8M • Updated • 10 • 1 -
prithivMLmods/Deepfake-QualityAssess2.0-85M-ONNX
Image Classification • Updated • 9 • 1 -
prithivMLmods/Deepfake-QualityAssess2.1-85M
Image Classification • 85.8M • Updated • 13 • 1
14b, 7b reasoning models
-
prithivMLmods/Megatron-Opus-14B-Exp
Text Generation • 15B • Updated • 30 • 3 -
prithivMLmods/Calcium-Opus-14B-Elite2-R1
Text Generation • 15B • Updated • 40 • 7 -
prithivMLmods/Primal-Opus-14B-Optimus-v1
Text Generation • 15B • Updated • 17 • 4 -
prithivMLmods/Megatron-Opus-14B-Stock
Text Generation • 15B • Updated • 4 • 3
1.5B, 1B, 0.5B param's
Based on Qwen's 2 vL
7B, 14B [ Saturation ]
-
prithivMLmods/Bellatrix-1.5B-xElite
Text Generation • 2B • Updated • 7 • 3 -
prithivMLmods/Calcium-Opus-14B-Elite-1M
Text Generation • 15B • Updated • 13 • • 4 -
prithivMLmods/COCO-7B-Instruct-1M
Text Generation • 8B • Updated • 16 • 4 -
prithivMLmods/Taurus-Opus-7B
Text Generation • 7B • Updated • 15 • 4
Model contention for gradual increments in reasoning-specific model evaluations.
-
prithivMLmods/Calcium-Opus-14B-Elite
Text Generation • 15B • Updated • 37 • 4 -
prithivMLmods/Calcium-Opus-14B-Elite2
Text Generation • 15B • Updated • 20 • 2 -
prithivMLmods/Calcium-Opus-14B-Elite3
Text Generation • 15B • Updated • 28 • 2 -
prithivMLmods/Calcium-Opus-14B-Elite4
Text Generation • 15B • Updated • 7 • 3
VLM - Multimodality
Express Tiny LLM's
phi 4 custom ft [ qwq, lcot, math ]
conversational, instruct, 14b Convos < 350 in OpenLLM Evals
-
prithivMLmods/QwQ-LCoT-7B-Instruct
Text Generation • 8B • Updated • 33 • 20 -
prithivMLmods/QwQ-LCoT2-7B-Instruct
Text Generation • 8B • Updated • 9 • 6 -
prithivMLmods/QwQ-LCoT1-Merged
Text Generation • 8B • Updated • 6 • 2 -
prithivMLmods/QwQ-LCoT-14B-Conversational
Text Generation • 15B • Updated • 9 • 5
Solve Math with Python
Opus for chat
Llama with Questions for reasoning / long chain of thought
Multimodality
ChemQwen Based on InChI
Text Generation, Vision Language, Image Generation
Open Eval < 500, long chain of thought and keyword based answering, reasoning
Reasoning, Long Chain of Thought, Keyword based problem solve
Best for Deepthink and Reasoning
Grounding, chat
-
prithivMLmods/Qwen2-VL-OCR-2B-Instruct
Image-Text-to-Text • 2B • Updated • 998 • 102 -
prithivMLmods/Qwen2-VL-OCR-2B-Instruct-GGUF
Image-Text-to-Text • 2B • Updated • 581 • 4 -
Multimodal OCR
🍍404Nanonets / olmOCR / RolmOCR / Aya-Vision / Qwen2-VL-OCR
-
Multimodal VLM Thinking
🥠57Lumian-VLR / VisionThink / MiniCPM-V / Typhoon-OCR / olmOCR
Text Generation Cook with it's GGUF
-
prithivMLmods/QwQ-LCoT-7B-Instruct
Text Generation • 8B • Updated • 33 • 20 -
prithivMLmods/QwQ-LCoT-7B-Instruct-GGUF
Text Generation • 8B • Updated • 46 • 3 -
prithivMLmods/QwQ-LCoT-3B-Instruct
Text Generation • 3B • Updated • 15 • 5 -
prithivMLmods/QwQ-LCoT-3B-Instruct-GGUF
Text Generation • 3B • Updated • 35 • 7
Artificial general intelligence
-
strangerzonehf/Flux-Midjourney-Mix2-LoRA
Text-to-Image • Updated • 2.18k • • 546 -
strangerzonehf/Flux-Super-Realism-LoRA
Text-to-Image • Updated • 2.93k • • 270 -
strangerzonehf/Flux-Midjourney-Mix-LoRA
Text-to-Image • Updated • 18 • • 60 -
strangerzonehf/Flux-Animeo-v1-LoRA
Text-to-Image • Updated • 324 • • 22
ease of reading
-
prithivMLmods/Triangulum-10B-GGUF
Text Generation • 10B • Updated • 117 • 2 -
prithivMLmods/Codepy-Deepthink-3B-GGUF
Text Generation • 3B • Updated • 68 • 7 -
prithivMLmods/Marco-o1-GGUF
Text Generation • 8B • Updated • 73 • 6 -
prithivMLmods/Qwen2.5-Coder-14B-Instruct-F16-GGUF
Text Generation • 15B • Updated • 131 • 2
large, medium, turbo lora
-
prithivMLmods/SD3.5-Large-Photorealistic-LoRA
Text-to-Image • Updated • 129 • 61 -
prithivMLmods/SD3.5-Large-Turbo-HyperRealistic-LoRA
Text-to-Image • Updated • 101 • 22 -
prithivMLmods/SD3.5-Large-Minimal-Blacked-LoRA
Text-to-Image • Updated • 25 • 10 -
prithivMLmods/SD3.5-Turbo-Realism-2.0-LoRA
Text-to-Image • Updated • 27 • 11
Flux & Sdxl
Image Gen - Text -to-Image
Only Stable
Are just in initial stage sdxl LoRA
Flux THE LoRA
-
strangerzonehf/Flux-Midjourney-Mix2-LoRA
Text-to-Image • Updated • 2.18k • • 546 -
strangerzonehf/Flux-Super-Realism-LoRA
Text-to-Image • Updated • 2.93k • • 270 -
strangerzonehf/Flux-Midjourney-Mix-LoRA
Text-to-Image • Updated • 18 • • 60 -
strangerzonehf/Flux-Animex-v2-LoRA
Text-to-Image • Updated • 107 • • 35