Rajkumar rawal
AI & ML interests
Recent Activity
Organizations
-
openai/gpt-oss-20b
Text Generation β’ 22B β’ Updated β’ 4.65M β’ β’ 3.84k -
openai/gpt-oss-120b
Text Generation β’ 120B β’ Updated β’ 3.7M β’ β’ 4.08k -
unsloth/gpt-oss-120b-GGUF
Text Generation β’ 117B β’ Updated β’ 155k β’ 158 -
unsloth/gpt-oss-20b-GGUF
Text Generation β’ 21B β’ Updated β’ 211k β’ 449
-
Running6868
LFM2 WebGPU β In-browser tool calling
πIn-browser tool calling, powered by Transformers.js
-
Running2525
Wllama
π¦Run GGUF directly on your browser!
-
openai/gpt-oss-120b
Text Generation β’ 120B β’ Updated β’ 3.7M β’ β’ 4.08k -
openai/gpt-oss-20b
Text Generation β’ 22B β’ Updated β’ 4.65M β’ β’ 3.84k
-
Running on Zero682682
Qwen Image Edit
βEdit images based on user instructions
-
Qwen/Qwen-Image-Edit
Image-to-Image β’ Updated β’ 198k β’ β’ 2.07k -
black-forest-labs/FLUX.1-Kontext-dev
Image-to-Image β’ Updated β’ 269k β’ β’ 2.39k -
Runtime errorMCP1.49k1.49k
FLUX.1 Kontext
β‘Kontext image editing on FLUX[dev]
-
Runtime error6363
DeepseekJanusPro
πDeepseek AI's Janus-Pro-7B: Generate image from text
-
The Leaderboard Illusion
Paper β’ 2504.20879 β’ Published β’ 72 -
Running on Zero682682
Qwen Image Edit
βEdit images based on user instructions
-
Running on Zero848848
Qwen Image
πΌGenerate images from text prompts
-
zai-org/GLM-4.5
Text Generation β’ 358B β’ Updated β’ 22.6k β’ β’ 1.37k -
Running2222
GLM 4.5V Demo App
πDemo App of dmg file
-
nvidia/Cosmos-Reason1-7B
Image-Text-to-Text β’ 8B β’ Updated β’ 522k β’ 185 -
RunningMCP135135
Web Search MCP
πSearch and extract web content for LLM ingestion
-
Running22
Full-Stack Fine-Tuning for Q
π§Full-Stack Fine-Tuning for the Q Programming Language
-
nvidia/Llama-3_3-Nemotron-Super-49B-v1_5
Text Generation β’ 50B β’ Updated β’ 161k β’ 207 -
unsloth/gpt-oss-120b-GGUF
Text Generation β’ 117B β’ Updated β’ 155k β’ 158 -
unsloth/gpt-oss-20b-GGUF
Text Generation β’ 21B β’ Updated β’ 211k β’ 449
-
allenai/MolmoAct-Pretraining-Mixture
Viewer β’ Updated β’ 24.2M β’ 4.99k β’ 9 -
nvidia/Llama-Nemotron-VLM-Dataset-v1
Viewer β’ Updated β’ 2.86M β’ 2.24k β’ 152 -
Running1515
Reachy Mini Apps
π¦Discover Reachy Mini Spaces
-
zai-org/GLM-4.1V-9B-Thinking
Image-Text-to-Text β’ 10B β’ Updated β’ 260k β’ β’ 751
-
Wan-AI/Wan2.2-T2V-A14B-Diffusers
Text-to-Video β’ Updated β’ 125k β’ β’ 87 -
Running on ZeroMCP427427
Wan 2.2 5B
πGenerate high-quality videos from text prompts and images
-
FunAudioLLM/ThinkSound
Video-to-Video β’ Updated β’ 47 -
Running on ZeroMCP300300
ThinkSound
πGenerate audio for a video using captions and descriptions
-
Running2727
HunyuanWorld Viewer
πExplore 3D worlds by selecting examples or uploading files
-
tencent/HunyuanWorld-1
Image-to-3D β’ Updated β’ 5.87k β’ 586 -
Running on Zero3.04k3.04k
Hunyuan3D-2.0
πText-to-3D and Image-to-3D Generation
-
Running on Zero1.58k1.58k
Hunyuan3D-2.1
π»Image-to-3D Generation
-
The Leaderboard Illusion
Paper β’ 2504.20879 β’ Published β’ 72 -
SmolVLM: Redefining small and efficient multimodal models
Paper β’ 2504.05299 β’ Published β’ 200 -
Seedance 1.0: Exploring the Boundaries of Video Generation Models
Paper β’ 2506.09113 β’ Published β’ 102 -
Small Language Models are the Future of Agentic AI
Paper β’ 2506.02153 β’ Published β’ 21
-
zai-org/GLM-4.5
Text Generation β’ 358B β’ Updated β’ 22.6k β’ β’ 1.37k -
Running2222
GLM 4.5V Demo App
πDemo App of dmg file
-
nvidia/Cosmos-Reason1-7B
Image-Text-to-Text β’ 8B β’ Updated β’ 522k β’ 185 -
RunningMCP135135
Web Search MCP
πSearch and extract web content for LLM ingestion
-
openai/gpt-oss-20b
Text Generation β’ 22B β’ Updated β’ 4.65M β’ β’ 3.84k -
openai/gpt-oss-120b
Text Generation β’ 120B β’ Updated β’ 3.7M β’ β’ 4.08k -
unsloth/gpt-oss-120b-GGUF
Text Generation β’ 117B β’ Updated β’ 155k β’ 158 -
unsloth/gpt-oss-20b-GGUF
Text Generation β’ 21B β’ Updated β’ 211k β’ 449
-
Running22
Full-Stack Fine-Tuning for Q
π§Full-Stack Fine-Tuning for the Q Programming Language
-
nvidia/Llama-3_3-Nemotron-Super-49B-v1_5
Text Generation β’ 50B β’ Updated β’ 161k β’ 207 -
unsloth/gpt-oss-120b-GGUF
Text Generation β’ 117B β’ Updated β’ 155k β’ 158 -
unsloth/gpt-oss-20b-GGUF
Text Generation β’ 21B β’ Updated β’ 211k β’ 449
-
allenai/MolmoAct-Pretraining-Mixture
Viewer β’ Updated β’ 24.2M β’ 4.99k β’ 9 -
nvidia/Llama-Nemotron-VLM-Dataset-v1
Viewer β’ Updated β’ 2.86M β’ 2.24k β’ 152 -
Running1515
Reachy Mini Apps
π¦Discover Reachy Mini Spaces
-
zai-org/GLM-4.1V-9B-Thinking
Image-Text-to-Text β’ 10B β’ Updated β’ 260k β’ β’ 751
-
Wan-AI/Wan2.2-T2V-A14B-Diffusers
Text-to-Video β’ Updated β’ 125k β’ β’ 87 -
Running on ZeroMCP427427
Wan 2.2 5B
πGenerate high-quality videos from text prompts and images
-
FunAudioLLM/ThinkSound
Video-to-Video β’ Updated β’ 47 -
Running on ZeroMCP300300
ThinkSound
πGenerate audio for a video using captions and descriptions
-
Running6868
LFM2 WebGPU β In-browser tool calling
πIn-browser tool calling, powered by Transformers.js
-
Running2525
Wllama
π¦Run GGUF directly on your browser!
-
openai/gpt-oss-120b
Text Generation β’ 120B β’ Updated β’ 3.7M β’ β’ 4.08k -
openai/gpt-oss-20b
Text Generation β’ 22B β’ Updated β’ 4.65M β’ β’ 3.84k
-
Running2727
HunyuanWorld Viewer
πExplore 3D worlds by selecting examples or uploading files
-
tencent/HunyuanWorld-1
Image-to-3D β’ Updated β’ 5.87k β’ 586 -
Running on Zero3.04k3.04k
Hunyuan3D-2.0
πText-to-3D and Image-to-3D Generation
-
Running on Zero1.58k1.58k
Hunyuan3D-2.1
π»Image-to-3D Generation
-
Running on Zero682682
Qwen Image Edit
βEdit images based on user instructions
-
Qwen/Qwen-Image-Edit
Image-to-Image β’ Updated β’ 198k β’ β’ 2.07k -
black-forest-labs/FLUX.1-Kontext-dev
Image-to-Image β’ Updated β’ 269k β’ β’ 2.39k -
Runtime errorMCP1.49k1.49k
FLUX.1 Kontext
β‘Kontext image editing on FLUX[dev]
-
The Leaderboard Illusion
Paper β’ 2504.20879 β’ Published β’ 72 -
SmolVLM: Redefining small and efficient multimodal models
Paper β’ 2504.05299 β’ Published β’ 200 -
Seedance 1.0: Exploring the Boundaries of Video Generation Models
Paper β’ 2506.09113 β’ Published β’ 102 -
Small Language Models are the Future of Agentic AI
Paper β’ 2506.02153 β’ Published β’ 21
-
Runtime error6363
DeepseekJanusPro
πDeepseek AI's Janus-Pro-7B: Generate image from text
-
The Leaderboard Illusion
Paper β’ 2504.20879 β’ Published β’ 72 -
Running on Zero682682
Qwen Image Edit
βEdit images based on user instructions
-
Running on Zero848848
Qwen Image
πΌGenerate images from text prompts