Mert Özkan

47Hunter47

·

AI & ML interests

None yet

Recent Activity

reacted to GoktugD's post with 👍 2 days ago

🇹🇷 **A 1B Turkish OCR model vs. Baidu OCR.** We ran both models on the **same Turkish enterprise documents**. The result: **Werea-DocOCR-1B → 99.9** **Baidu Unlimited-OCR → 47.9** Same documents. Same evaluation. And Werea-DocOCR is only **1B parameters**. It was built specifically for difficult Turkish enterprise documents: 📄 invoices 📑 contracts 🏦 bank receipts 💼 payroll 🚗 vehicle documents 📋 SGK-style tables 📱 scanned & phone-captured documents But benchmarks aren't enough. **Give me a Turkish document that you think will break it.** We'll test the hardest ones and publish the failures. 🤗 Model: https://huggingface.co/Werea-co/Werea-DocOCR-1B 📚 Dataset: https://huggingface.co/datasets/Werea-co/werea-tr-doc-ocr-enterprise-v2 🇹🇷 Built in Türkiye. Open on Hugging Face. #OCR #DocumentAI #HuggingFace #TurkishAI

liked a model 3 days ago

ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-GGUF

commentedon an article 8 days ago

DAVIDAU DELETED MY POST AND BANNED ME FOR ASKING ABOUT BENCHMARKS — HERE IS THE FULL ANALYSIS (9B + 27B + 390 MODELS)

View all activity

Organizations

None yet

New activity in DavidAU/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NEO-CODER-MAX-MTP-GGUF 8 days ago

Now avail - 5 reasoning modes, 5 instruct modes: New Version "TWIN TURBO" Qwen3.8 27B ; a preview of what is to come...

#45 opened 14 days ago by

New activity in DavidAU/Qwen3.8-27B-TWIN-TURBO-Fable-Cold-Fusion-709-L-Uncensored-NM-DAU-NEO-MTP-GGUF 12 days ago

Tool / Agent / Agentic -> Corrected Jinja template for tools / agents / agentic work.

#10 opened 12 days ago by

New activity in DavidAU/Qwen3.8-27B-TWIN-TURBO-Fable-Cold-Fusion-709-L-Uncensored-NM-DAU-NEO-MTP-GGUF 13 days ago

FIXED Jinja // Agentic/tool-calling use: mid-tool-call stream drops + premature turn ends (base Qwen3.8 is fine in the same stack)

#7 opened 13 days ago by

New activity in ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF 13 days ago

Is this model same as Q4KM for coding related tasks?

#22 opened 15 days ago by

New activity in ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF 14 days ago

Request for standard Q-type quantizations (Q3_K_XL, Q4_K_M/XL) for AMD GPU compatibility

#5 opened 23 days ago by

myhugginfacegacc

This is amazing, now i have 250k ctx

#19 opened 16 days ago by

New activity in DavidAU/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NEO-CODER-MAX-MTP-GGUF 14 days ago

What agent are you all running this with?

#42 opened 15 days ago by

New activity in DavidAU/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NEO-CODER-MAX-MTP-GGUF 16 days ago

It starts very good but loops afterwards

#37 opened 17 days ago by

New activity in DavidAU/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NEO-CODER-MAX-MTP-GGUF 20 days ago

Will there be a LOW MTP version too?

#4 opened 22 days ago by

New activity in DavidAU/Qwen3.8-27B-Cold-Fusion-GAIN-V1.1-NM-DAU-NEO-MAX-MTP-GGUF 26 days ago

thinking loop issue

#29 opened 26 days ago by

New activity in Qwen/Qwen3.8-Flash-Next 28 days ago

Qwen3.8-Flash-Next (Qwen 4 - Preview) vs 3.8 27B - Architecture Teardown

#22 opened 28 days ago by

New activity in DavidAU/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU 30 days ago

Sooo hyped!

#1 opened 30 days ago by

New activity in DavidAU/Qwen3.8-27B-Cold-Fusion-GAIN-V1.1 about 1 month ago

gguf please

#3 opened about 1 month ago by