Loading video...

Video Failed to Load

Go Home

This peanut-sized chinese model just dethroned Gemini at reading documents. It’s called glm-ocr. it’s a tiny 0.9b parameter vision-language model that is about to replace every expensive ocr api you use. → Handles text, tables, formulas, handwriting → Scored 94.62 on OmniDocBench V1.5 → 8 languages → vLLM, SGLang,...

dr_cintas's profile picture

Alvaro Cintas

130,496 subscribers

37,499 views • 2 months ago •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Everyone is sleeping on this new OCR model! Datalab's Chandra topped independent benchmarks and beat the previous best dots-ocr. - Supports 40+ languages - Extracts complex texts, tables, formulas easily I tested on Ramanujan's handwritten letter from 1913. 100% open-source.
0:11

Everyone is sleeping on this new OCR model! Datalab's Chandra topped independent benchmarks and beat the previous best dots-ocr. - Supports 40+ languages - Extracts complex texts, tables, formulas easily I tested on Ramanujan's handwritten letter from 1913. 100% open-source.

Avi Chawla

158,386 views • 6 months ago

Fine-tune DeepSeek-OCR on your own language! (100% local) DeepSeek-OCR is a 3B-parameter vision model that achieves 97% precision while using 10× fewer vision tokens than text-based LLMs. It handles tables, papers, and handwriting without killing your GPU or budget. Why it matters: Most vision models treat documents as massive sequences of tokens, making long-context processing expensive and slow. DeepSeek-OCR uses context optical compression to convert 2D layouts into vision tokens, enabling efficient processing of complex documents. The best part? You can easily fine-tune it for your specific use case on a single GPU. I used Unsloth to run this experiment on Persian text and saw an 88.26% improvement in character error rate. ↳ Base model: 149% character error rate (CER) ↳ Fine-tuned model: 60% CER (57% more accurate) ↳ Training time: 60 steps on a single GPU Persian was just the test case. You can swap in your own dataset for any language, document type, or specific domain you're working with. I've shared the complete guide in the next tweet - all the code, notebooks, and environment setup ready to run with a single click. Everything is 100% open-source!
0:14

Fine-tune DeepSeek-OCR on your own language! (100% local) DeepSeek-OCR is a 3B-parameter vision model that achieves 97% precision while using 10× fewer vision tokens than text-based LLMs. It handles tables, papers, and handwriting without killing your GPU or budget. Why it matters: Most vision models treat documents as massive sequences of tokens, making long-context processing expensive and slow. DeepSeek-OCR uses context optical compression to convert 2D layouts into vision tokens, enabling efficient processing of complex documents. The best part? You can easily fine-tune it for your specific use case on a single GPU. I used Unsloth to run this experiment on Persian text and saw an 88.26% improvement in character error rate. ↳ Base model: 149% character error rate (CER) ↳ Fine-tuned model: 60% CER (57% more accurate) ↳ Training time: 60 steps on a single GPU Persian was just the test case. You can swap in your own dataset for any language, document type, or specific domain you're working with. I've shared the complete guide in the next tweet - all the code, notebooks, and environment setup ready to run with a single click. Everything is 100% open-source!

Akshay 🚀

126,036 views • 7 months ago

ByteDance just dropped an OCR model that reads documents just like humans. This 0.3B model analyzes page layout first, then parses elements in parallel. 100% open-source.
0:13

ByteDance just dropped an OCR model that reads documents just like humans. This 0.3B model analyzes page layout first, then parses elements in parallel. 100% open-source.

Unwind AI

101,055 views • 8 months ago

Announcing llama-ocr – a free + open source OCR tool! It takes documents (images for now) & outputs markdown, and does really well for complex receipts, PDFs with tables/charts, ect... Powered by Llama 3.2 vision on Together AI & available on npm today!
0:13

Announcing llama-ocr – a free + open source OCR tool! It takes documents (images for now) & outputs markdown, and does really well for complex receipts, PDFs with tables/charts, ect... Powered by Llama 3.2 vision on Together AI & available on npm today!

Hassan

443,823 views • 1 year ago

Ok... this is insane! Alibaba just dropped Wan2.2-S2V, a 14B parameter speech-to-video model. Turn audio into film-grade clips with lifelike motion and environment control. And it’s fully open-source. Examples below: (sound on)
0:14

Ok... this is insane! Alibaba just dropped Wan2.2-S2V, a 14B parameter speech-to-video model. Turn audio into film-grade clips with lifelike motion and environment control. And it’s fully open-source. Examples below: (sound on)

Angry Tom

66,072 views • 9 months ago

smart parking demo - RF-DETR - license plate detection - OC-SORT - multi-object tracking - GLM-OCR - reading license plates on Monday I showed you trackers, yesterday GLM-OCR, today I'm putting everything together
0:17

smart parking demo - RF-DETR - license plate detection - OC-SORT - multi-object tracking - GLM-OCR - reading license plates on Monday I showed you trackers, yesterday GLM-OCR, today I'm putting everything together

SkalskiP

26,206 views • 3 months ago

i found a way to make UNCENSORED AI AGENT on a RTX 4090 GPU (!!!) with LOCAL 30B model weights this is GLM-4.7-Flash with abliteration, need 24GB VRAM, safety alignment surgically removed from the weights, the model has native tool calling, it actually executes bash, edits files, runs git (1) use ollama to pull weights of GLM > ollama pull huihui_ai/glm-4.7-flash-abliterated:q4_K (2) proxy it to any coding agent via ollama > ollama launch claude --model huihui_ai/glm-4.7-flash-abliterated:q4_K > ollama launch codex --model huihui_ai/glm-4.7-flash-abliterated:q4_K > ollama launch opencode --model huihui_ai/glm-4.7-flash-abliterated:q4_K (3) have fun
0:11

i found a way to make UNCENSORED AI AGENT on a RTX 4090 GPU (!!!) with LOCAL 30B model weights this is GLM-4.7-Flash with abliteration, need 24GB VRAM, safety alignment surgically removed from the weights, the model has native tool calling, it actually executes bash, edits files, runs git (1) use ollama to pull weights of GLM > ollama pull huihui_ai/glm-4.7-flash-abliterated:q4_K (2) proxy it to any coding agent via ollama > ollama launch claude --model huihui_ai/glm-4.7-flash-abliterated:q4_K > ollama launch codex --model huihui_ai/glm-4.7-flash-abliterated:q4_K > ollama launch opencode --model huihui_ai/glm-4.7-flash-abliterated:q4_K (3) have fun

chiefofautism

340,773 views • 4 months ago

GPT-4o level multimodal LLM running on your phone. MiniCPM-V 4.5 outperforms GPT-4o, Gemini-2.0 Pro, and Qwen2.5-VL 72B on vision and language AI tasks. It can even understand videos and perform OCR in 30+ languages. And it's 100% Opensource.
0:12

GPT-4o level multimodal LLM running on your phone. MiniCPM-V 4.5 outperforms GPT-4o, Gemini-2.0 Pro, and Qwen2.5-VL 72B on vision and language AI tasks. It can even understand videos and perform OCR in 30+ languages. And it's 100% Opensource.

Shubham Saboo

17,947 views • 9 months ago

NVIDIA Nemotron 3 Nano Omni, a new multimodal reasoning model, is now live on Jetson AI Lab and unifies vision, audio, and language into a single reasoning loop. 🙌 Power your NemoClaws by running this model with Ollama, vLLM and other inference frameworks on NVIDIA Jetson hardware. Try it ➡️
0:13

NVIDIA Nemotron 3 Nano Omni, a new multimodal reasoning model, is now live on Jetson AI Lab and unifies vision, audio, and language into a single reasoning loop. 🙌 Power your NemoClaws by running this model with Ollama, vLLM and other inference frameworks on NVIDIA Jetson hardware. Try it ➡️

NVIDIA Robotics

15,828 views • 1 month ago

Open-source AI just got a major upgrade. @Convergence_ai_ releases Proxy Lite, the most capable open-source agentic Vision Language Model on the market! 🔗 → 3B distilled model, cost-efficient → Runs 100% locally, no cluster needed! 🧵↓
0:17

Open-source AI just got a major upgrade. @Convergence_ai_ releases Proxy Lite, the most capable open-source agentic Vision Language Model on the market! 🔗 → 3B distilled model, cost-efficient → Runs 100% locally, no cluster needed! 🧵↓

Charly Wargnier

37,618 views • 1 year ago

Happy Friday! We just put DeepSeek-V4-Pro up on It’s the world’s largest open source model at 1.6T parameters, and you can run it for free running on NVIDIA Blackwell GPUs. Try the NVIDIA NIM API →
0:18

Happy Friday! We just put DeepSeek-V4-Pro up on It’s the world’s largest open source model at 1.6T parameters, and you can run it for free running on NVIDIA Blackwell GPUs. Try the NVIDIA NIM API →

NVIDIA AI

202,436 views • 1 month ago

We're excited to announce react-native-executorch v0.3.0 packed with powerful AI features 🎉 What's New: 💬Speech to Text transcription using Whisper and Moonshine 📙OCR for extracting text from images 🚀 MPS Support ⚡️ Hookless API 🧠 LLM Message History ⬇️ Background Model Downloads 📊 Benchmarks 🧪 Experimental OCR for extracting vertical text from images
0:17

We're excited to announce react-native-executorch v0.3.0 packed with powerful AI features 🎉 What's New: 💬Speech to Text transcription using Whisper and Moonshine 📙OCR for extracting text from images 🚀 MPS Support ⚡️ Hookless API 🧠 LLM Message History ⬇️ Background Model Downloads 📊 Benchmarks 🧪 Experimental OCR for extracting vertical text from images

Software Mansion

29,873 views • 1 year ago

Good to know: MinMax-M2 is one of the best model at UI design 👀 (it’s open source!)
0:13

Good to know: MinMax-M2 is one of the best model at UI design 👀 (it’s open source!)

Victor M

36,124 views • 7 months ago

Google just open-sourced LangExtract Python library! It uses LLMs to extract entities, attributes, and relations—with exact source grounding—from unstructured documents. Flexible LLM support (Gemini, OpenAI, Ollama) 100% open-source.
0:18

Google just open-sourced LangExtract Python library! It uses LLMs to extract entities, attributes, and relations—with exact source grounding—from unstructured documents. Flexible LLM support (Gemini, OpenAI, Ollama) 100% open-source.

Akshay 🚀

120,396 views • 10 months ago

Gemini 3 Flash is now available in MagicPath ⚡ From our earlier testing, it’s surprisingly strong at visual design for its size, and it’s fast! My recommendation: use it as your first-pass model to explore ideas, then switch to a bigger model for editing + refinements.
0:18

Gemini 3 Flash is now available in MagicPath ⚡ From our earlier testing, it’s surprisingly strong at visual design for its size, and it’s fast! My recommendation: use it as your first-pass model to explore ideas, then switch to a bigger model for editing + refinements.

Pietro Schirano

11,427 views • 6 months ago

I’m not saying an open-source model you can run on consumer hardware is better than ChatGPT, just that sometimes it’s worth trying both. Prompt: “A zebra with a volcanic eruption in the background.”
0:11

I’m not saying an open-source model you can run on consumer hardware is better than ChatGPT, just that sometimes it’s worth trying both. Prompt: “A zebra with a volcanic eruption in the background.”

Victor M

105,328 views • 6 months ago

From writing emails to building entire applications... The AI evolution is mind-blowing! GLM-4.6 just dropped and it's changing everything. It’s fast. It’s smart. And it’s packed with features no other model has right now. Here’s why it’s blowing people’s minds 👇
0:18

From writing emails to building entire applications... The AI evolution is mind-blowing! GLM-4.6 just dropped and it's changing everything. It’s fast. It’s smart. And it’s packed with features no other model has right now. Here’s why it’s blowing people’s minds 👇

FELIX

96,973 views • 8 months ago

Moondream doesn’t just OCR, it understands. Full JSON receipts, instant Q&A. Open, tiny, blazingly fast.
0:10

Moondream doesn’t just OCR, it understands. Full JSON receipts, instant Q&A. Open, tiny, blazingly fast.

moondream

280,507 views • 8 months ago

We are building “Open Source Nano Banana for Video” - here is open source demo v0.1 We are open sourcing Lucy Edit, the first foundation model for text-guided video editing! Get the model on Hugging Face 🤗, API on @FAL, and nodes on ComfyUI 🧵
0:17

We are building “Open Source Nano Banana for Video” - here is open source demo v0.1 We are open sourcing Lucy Edit, the first foundation model for text-guided video editing! Get the model on Hugging Face 🤗, API on @FAL, and nodes on ComfyUI 🧵

Decart

413,676 views • 9 months ago

This AI model turns a single image + audio into a talking avatar video of infinite length. StableAvatar is built on Wan 2.1, and MIT Licensed. Open-source AI video is accelerating, and it’s exciting to watch!
0:19

This AI model turns a single image + audio into a talking avatar video of infinite length. StableAvatar is built on Wan 2.1, and MIT Licensed. Open-source AI video is accelerating, and it’s exciting to watch!

Miguel | AP

35,804 views • 10 months ago