rednote-hilab/dots.ocr · Discussions

Resources

View closed (12)

Fix: Resolve TypeError for video_processor during model loading.

#38 opened 1 day ago by

best way to deploy rednote-hilab/dots.ocr using docker

#37 opened 3 days ago by

Markdown genration

#36 opened 10 days ago by

Request: DOI

#35 opened 16 days ago by

fix enforced bf16 data type on SM75 and lower devices

#34 opened 20 days ago by

fix recursion, None Type of min_pixels & max_pixels, and enforced bf16 on SM75 and lower devices

#33 opened 20 days ago by

Cant inference Via Vllm Docker container.

#32 opened 26 days ago by

Release Separate Vision Encoder?

#31 opened 27 days ago by

chat_template error

#26 opened about 2 months ago by

The results vary depending on the resolution of the image.

#25 opened about 2 months ago by

How to run this model on Atlas 800I A2(64G) with vLLM？If possible, What should be paid attention to?

#24 opened about 2 months ago by

ocr

#23 opened 2 months ago by

ValueError: facebook/opt-125m is not a multimodal model

#22 opened 2 months ago by

Was anyone able to fine tune it?

#18 opened 2 months ago by

Local Installation Video and Testing - Step by Step

#17 opened 2 months ago by

Problem:Setting `pad_token_id` to `eos_token_id`:151643 for open-end generation.

#16 opened 3 months ago by

OpenAI required?!

#14 opened 3 months ago by

Flash Attention Req When Rrunning Model

#13 opened 3 months ago by

Number of parameters

#12 opened 3 months ago by

Finetuning Support

#11 opened 3 months ago by

Picture extraction request

#10 opened 3 months ago by

Request: DOI

#9 opened 3 months ago by

Huggingface inference problem, Turing architecture GPUs

#6 opened 3 months ago by

🔥🔥🔥视频教程

#4 opened 3 months ago by

not supported in Turing GPU Architecture ?

#3 opened 3 months ago by

Quantized version?

#2 opened 3 months ago by