10 actions in 9 pieces of software · ranked by words, meaning and measured trust · 689 ms
modelrecord16,818 downloads/month
- text-generation
Task: text-generation
- text-generation
modelrecord14,087 downloads/month
- image-text-to-text
Task: image-text-to-text
- image-text-to-text
skillnvidia/skillsrecord
- nemo-mbridge-perf-moe-vlm-training
Practical guidance for training MoE VLMs in Megatron Bridge. Compares FSDP and 3D-parallel approaches, using rounded lessons from Qwen3-VL, Qwen3-Next, and other multimodal experiments.
- nemo-mbridge-perf-moe-vlm-training
skillnvidia/skillsrecord
- nemo-mbridge-perf-moe-long-context
Long-context MoE training guidance for Megatron Bridge. Covers CP sizing, selective recompute, dispatcher choices, and practical patterns from DSV3, Qwen3, and Qwen3-Next long-context experiments.
- nemo-mbridge-perf-moe-long-context
skillnvidia/skillsrecord
- nemo-mbridge-perf-moe-dispatcher-selection
Choose the right MoE token dispatcher (`alltoall`, DeepEP, or HybridEP) for the hardware, EP degree, and optimization stage. Summarizes patterns from DSV3, Qwen3, Qwen3-Next, and VLM bring-up work.
- nemo-mbridge-perf-moe-dispatcher-selection
modelrecord
- qwen/qwen3-235b-a22b-instruct-2507
Updated Qwen3 model for instruction following
- qwen/qwen3-235b-a22b-instruct-2507
modelrecord
- prunaai/qwen3-32b
A 2x faster qwen 3 model through pruna oss
- prunaai/qwen3-32b
modelrecord
- qwen/qwen3-tts
A unified Text-to-Speech demo featuring three powerful modes: Voice, Clone and Design
- qwen/qwen3-tts
- 9Qwen3 MCP Serverfound in code, not yet checkedno passport yet
MCP servermarduk191/qwen3_mcp
- run_shell_command
Execute a shell command (alias for execute_command). Use this for running builds, tests, git commands, npm scripts, and any terminal operations.
- execute_command
Execute a shell command. Use this for running builds, tests, git commands, npm scripts, and any terminal operations. Commands run in the working directory.
- run_shell_command
Labels are the instruments' verdict and are never changed by ranking. Agents and robots get this same answer as JSON at /api/v1/find?q=…&answer=1 and through the MCP server.