StepSafe Step-level reasoning monitors for LLM agents: StepSafe-4B, StepSafe-8B and the StepSafe-4B-SFT warm start. Collection by Caaaarr1e 23 days ago - Caaaarr1e/StepSafe-4B Text Generation • 4B • Updated 23 days ago • 631 • 1 Caaaarr1e/StepSafe-8B Text Generation • 8B • Updated 23 days ago • 685 Caaaarr1e/StepSafe-4B-SFT Text Generation • 4B • Updated 23 days ago • 684
paper Collection by AH20 23 days ago - The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation Paper • 2609.36484 • Published Sep 29 • 167
The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation Paper • 2609.36484 • Published Sep 29 • 167
Lilavati Solves English maths word problems by writing a short Python program and running it. Trained from scratch; runs on a laptop CPU. Collection by udgamlabs 5 days ago - udgamlabs/Lilavati Text Generation • 94.7M • Updated 21 days ago • 847 • 2 udgamlabs/Lilavati-Checker Text Generation • 94.7M • Updated 21 days ago • 380 Running on Zero MCP Lilavati · Udgam Labs ◾ 95M model that solves maths word problems by writing Python udgamlabs/Lilavati-GGUF Text Generation • 94.7M • Updated 11 days ago • 145 • 1
Running on Zero MCP Lilavati · Udgam Labs ◾ 95M model that solves maths word problems by writing Python
test Collection by conygi 23 days ago - SC117/Qwen3.8-Flash-Next-GSQ-RCO-abliterated-GGUF Image-Text-to-Text • 177B • Updated 15 days ago • 4.21M • 770 ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-GGUF Image-Text-to-Text • 177B • Updated Sep 29 • 6.83M • 1.2k ukisai/Swift-1.5-Qwen3.8-Flash-Next-GGUF Image-Text-to-Text • 177B • Updated Sep 24 • 46.4k • 73
SC117/Qwen3.8-Flash-Next-GSQ-RCO-abliterated-GGUF Image-Text-to-Text • 177B • Updated 15 days ago • 4.21M • 770
ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-GGUF Image-Text-to-Text • 177B • Updated Sep 29 • 6.83M • 1.2k
Controllability for musicians Collection by vaclis 17 days ago - MIDI-REPA: Improving Text-to-Music Generation with Symbolic Representation Alignment Paper • 2610.20967 • Published 25 days ago • 2 vaclis/JamendoMIDI Viewer • Updated 17 days ago • 51.1k • 263 • 1 vaclis/amtflow Other • Updated 17 days ago
MIDI-REPA: Improving Text-to-Music Generation with Symbolic Representation Alignment Paper • 2610.20967 • Published 25 days ago • 2
MiniMax-H3 Collection by cj5260 13 days ago - JOKER141/MiniMax-H3-General-Motion-Continuity-Repair Updated 14 days ago • 117 Jojocodex/wushu-action-v7-minimax-h3-fl2va-ref2va-lora Image-to-Video • Updated Oct 5 • 21.9k • • 90 Alissonerdx/Minimax-H3-ComfyUI Updated 3 days ago • 284k • 569 JOKER141/MiniMax-H3-Weapon-Combat-LoRA Updated 14 days ago • 5.05k • 47
GenGuard 1.0 Light Collection by mncai 23 days ago 1 mncai/genguard-1.0-light Text Generation • 8B • Updated 25 days ago • 788 • 5 mncai/genguard-1.0-light-GGUF 7B • Updated 24 days ago • 74 mncai/genguard-1.0-light-NVFP4 8B • Updated 24 days ago • 28 mncai/genguard-1.0-light-FP8 8B • Updated 23 days ago • 30
myLocal Collection by samshad 23 days ago - jialinyyzz/humanizer Text Generation • 12B • Updated 24 days ago • 370k • 2.25k unsloth/gemma-4-26B-A4B-it-qat-GGUF Image-Text-to-Text • 25B • Updated Jul 17 • 190k • 496 unsloth/Qwen3.8-27B-GGUF 27B • Updated Aug 20 • 6.1M • 5.61k
StepSafe Step-level reasoning monitors for LLM agents: StepSafe-4B, StepSafe-8B and the StepSafe-4B-SFT warm start. Collection by Caaaarr1e 23 days ago - Caaaarr1e/StepSafe-4B Text Generation • 4B • Updated 23 days ago • 631 • 1 Caaaarr1e/StepSafe-8B Text Generation • 8B • Updated 23 days ago • 685 Caaaarr1e/StepSafe-4B-SFT Text Generation • 4B • Updated 23 days ago • 684
Controllability for musicians Collection by vaclis 17 days ago - MIDI-REPA: Improving Text-to-Music Generation with Symbolic Representation Alignment Paper • 2610.20967 • Published 25 days ago • 2 vaclis/JamendoMIDI Viewer • Updated 17 days ago • 51.1k • 263 • 1 vaclis/amtflow Other • Updated 17 days ago
MIDI-REPA: Improving Text-to-Music Generation with Symbolic Representation Alignment Paper • 2610.20967 • Published 25 days ago • 2
paper Collection by AH20 23 days ago - The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation Paper • 2609.36484 • Published Sep 29 • 167
The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation Paper • 2609.36484 • Published Sep 29 • 167
MiniMax-H3 Collection by cj5260 13 days ago - JOKER141/MiniMax-H3-General-Motion-Continuity-Repair Updated 14 days ago • 117 Jojocodex/wushu-action-v7-minimax-h3-fl2va-ref2va-lora Image-to-Video • Updated Oct 5 • 21.9k • • 90 Alissonerdx/Minimax-H3-ComfyUI Updated 3 days ago • 284k • 569 JOKER141/MiniMax-H3-Weapon-Combat-LoRA Updated 14 days ago • 5.05k • 47
Lilavati Solves English maths word problems by writing a short Python program and running it. Trained from scratch; runs on a laptop CPU. Collection by udgamlabs 5 days ago - udgamlabs/Lilavati Text Generation • 94.7M • Updated 21 days ago • 847 • 2 udgamlabs/Lilavati-Checker Text Generation • 94.7M • Updated 21 days ago • 380 Running on Zero MCP Lilavati · Udgam Labs ◾ 95M model that solves maths word problems by writing Python udgamlabs/Lilavati-GGUF Text Generation • 94.7M • Updated 11 days ago • 145 • 1
Running on Zero MCP Lilavati · Udgam Labs ◾ 95M model that solves maths word problems by writing Python
GenGuard 1.0 Light Collection by mncai 23 days ago 1 mncai/genguard-1.0-light Text Generation • 8B • Updated 25 days ago • 788 • 5 mncai/genguard-1.0-light-GGUF 7B • Updated 24 days ago • 74 mncai/genguard-1.0-light-NVFP4 8B • Updated 24 days ago • 28 mncai/genguard-1.0-light-FP8 8B • Updated 23 days ago • 30
test Collection by conygi 23 days ago - SC117/Qwen3.8-Flash-Next-GSQ-RCO-abliterated-GGUF Image-Text-to-Text • 177B • Updated 15 days ago • 4.21M • 770 ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-GGUF Image-Text-to-Text • 177B • Updated Sep 29 • 6.83M • 1.2k ukisai/Swift-1.5-Qwen3.8-Flash-Next-GGUF Image-Text-to-Text • 177B • Updated Sep 24 • 46.4k • 73
SC117/Qwen3.8-Flash-Next-GSQ-RCO-abliterated-GGUF Image-Text-to-Text • 177B • Updated 15 days ago • 4.21M • 770
ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-GGUF Image-Text-to-Text • 177B • Updated Sep 29 • 6.83M • 1.2k
myLocal Collection by samshad 23 days ago - jialinyyzz/humanizer Text Generation • 12B • Updated 24 days ago • 370k • 2.25k unsloth/gemma-4-26B-A4B-it-qat-GGUF Image-Text-to-Text • 25B • Updated Jul 17 • 190k • 496 unsloth/Qwen3.8-27B-GGUF 27B • Updated Aug 20 • 6.1M • 5.61k