cuuupid / markitdown

Microsoft's tool to convert Office documents, PDFs, images, audio, and more to LLM-ready markdown.

122 runs
Public

cuuupid / qwen2-vl-2b

SOTA open-source model for chatting with videos and the newest model in the Qwen family

409 runs
Public

cuuupid / cogvideox-5b

Generate high quality videos from a prompt

1.5K runs
Public

cuuupid / idm-vton

Best-in-class clothing virtual try on in the wild (non-commercial use only)

457.6K runs
Public

cuuupid / flux-lineart

Flux finetuned for black and white line art.

1K runs
Public

cuuupid / gte-qwen2-7b-instruct

Embed text with Qwen2-7b-Instruct

128.8K runs
Public

cuuupid / whisper-webrtc

Talk to an AI "friend" with ultra low latency over WebRTC

3 runs
Public

cuuupid / glm-4v-9b

GLM-4V is a multimodal model released by Tsinghua University that is competitive with GPT-4o and establishes a new SOTA on several benchmarks, including OCR.

70.8K runs
Public

cuuupid / sdxl-lineart

SDXL finetuned on line art

1.1K runs
Public

cuuupid / garden-state-llama

Llama-3-8B finetuned with ReFT to hyperfocus on New Jersey, the Garden State, the best state, the only state!

105 runs
Public

cuuupid / golden-gate-llama

An example using Garden State Llama to ReFT on the Golden Gate bridge.

30 runs
Public

cuuupid / e5-mistral-7b-instruct

Finetuned E5 embeddings for instruct based on Mistral.

131 runs
Public

cuuupid / sdxl-meow

make meow emojis!

57 runs
Public

cuuupid / marker

Convert scanned or electronic documents to markdown, very very very fast

2.1K runs
Public

cuuupid / seamless_​expressive

Translate audio while keeping the original style, pronunciation and tone of your original audio.

635 runs
Public

cuuupid / minicpm-llama3-v-2.5

MiniCPM LLama3-V 2.5, a new SOTA open-source VLM that surpasses GPT-4V-1106 and Phi-128k on a number of benchmarks.

128 runs
Public