Resources

Listed on OpenModelMap

#65 opened 24 days ago by

duola15

Internal model structure preview

#64 opened 26 days ago by

svetoviz

Add Real5-OmniDocBench evaluation results for GLM-OCR

#63 opened about 1 month ago by

changdazhou

Add MDPBench private evaluation result

#61 opened 3 months ago by

Delores-Lin

Multilingual powerhouse — testing for mobile deployment

#60 opened 3 months ago by

3morixd

Listed on OpenModelMap

#59 opened 3 months ago by

duola15

ValueError: Task 'image-to-text' not supported for provider 'zai-org'. Available tasks: ['conversational', 'text-to-image']

#56 opened 4 months ago by

procioni

Please support vietnamese

#55 opened 4 months ago by

Duonglv

Add ParseBench evaluation results

#53 opened 5 months ago by

boyang-runllama

Inconsistent results

#50 opened 5 months ago by

TheMrguiller

'image-to-text' not supported for provider 'zai-org'

#49 opened 5 months ago by

BelegNeurion

instructions dont do anything is there way to actualy make it listen to it?

#48 opened 6 months ago by

dimitarx

Retail Flyer - Constant hallucination despite prompt injection.

#47 opened 6 months ago by

bradomni

What is the testing setup?

#46 opened 6 months ago by

wamreyaz

Why does the chat template include reasoning/thinking components?

👀 1

#45 opened 6 months ago by

usrlocalben

Critical Hallucinations and Cross-Script Confusion in Multilingual Stress Test (CJK + Cyrillic)

#42 opened 7 months ago by

The1Just

Easy install without transformers

👍 1

#35 opened 7 months ago by

PartyParrot

how to start with zero knowledge ?

🤗 1

#32 opened 7 months ago by

JRYAN723

Table regonition doesn't work well for multiple table

#28 opened 7 months ago by

OumarDicko

GLM-OCR very slow on Tesla T4 (~40s per image) even with GPU — is this expected?

#13 opened 7 months ago by

905saini

Could this model extract text location or coordinate?

#12 opened 7 months ago by

ExChaosen

Training data details - sources and license

👍 1

#11 opened 8 months ago by

nramrakhiyani

Requesting Example for Structured Information Extraction via cURL

👍 3

#10 opened 8 months ago by

andynoodles

No text output inferencing with ollama?

➕ 3

#8 opened 8 months ago by

frankslin

GLM-OCR: A Tiny 0.9B-Parameter Model That Punches Far Above Its Weight

🤗 3

#7 opened 8 months ago by

Javedalam

When will there be better support for vLLM?

#6 opened 8 months ago by

Xiakj

Installation Video and Testing - Step by Step

❤️🤗 5

#1 opened 8 months ago by

fahdmirzac