LLM/chandra
1
0
Fork 0
mirror of https://github.com/datalab-to/chandra.git synced 2026-03-29 16:54:37 +00:00
Code Issues Packages Projects Releases Wiki Activity

Bump version

Browse Source
This commit is contained in:
Vik Paruchuri
2026-03-17 16:11:22 -04:00
parent 7280a4508d
commit d698166771
2 changed files with 3 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
README.md
View File

@@ -62,7 +62,7 @@ chandra_app
## Benchmarks
Multilingual performance was a focus for us with Chandra 2. There isn't a good public benchmark multilingual OCR benchmark, so we made our own. This tests tables, math, ordering, layout, and text accuracy.
Multilingual performance was a focus for us with Chandra 2. There isn't a good public multilingual OCR benchmark, so we made our own. This tests tables, math, ordering, layout, and text accuracy.
<img src="assets/benchmarks/multilingual.png" width="600px"/>
@@ -182,7 +182,7 @@ Settings can be configured via environment variables or a `local.env` file:
```bash
# Model settings
MODEL_CHECKPOINT=datalab-to/chandra-ocr-2
MAX_OUTPUT_TOKENS=8192
MAX_OUTPUT_TOKENS=12384
# vLLM settings
VLLM_API_BASE=http://localhost:8000/v1

2
pyproject.toml
View File

@@ -1,6 +1,6 @@
[project]
name = "chandra-ocr"
version = "0.1.9"
version = "0.2.0"
description = "OCR model that converts documents to markdown, HTML, or JSON."
readme = "README.md"
requires-python = ">=3.10"