diff --git a/README.md b/README.md index c1ab111..31d88e8 100644 --- a/README.md +++ b/README.md @@ -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. @@ -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 diff --git a/pyproject.toml b/pyproject.toml index 3689576..9ad2c0f 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -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"