yujunjun/olmocr
1
0
Fork 0
mirror of https://github.com/allenai/olmocr.git synced 2025-11-04 12:07:15 +00:00
Code Issues Packages Projects Releases Wiki Activity

Prompt6 for qwen2.7 vl

Browse Source
This commit is contained in:
Jake Poznanski 2025-04-08 13:25:15 -07:00
parent 8c287a0255
commit 2f74a2a996
2 changed files with 2 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
olmocr/bench/prompts.py
View File

@ -1,6 +1,5 @@
def build_basic_prompt() -> str: def build_basic_prompt() -> str:
return "Just return the plain text representation of this document as if you were reading it naturally. Use markdown for formatting. Convert math to Latex using \( and \) as delimiters for inline math, and \[ and \] as delimiters otherwise. Convert all tables to markdown." return "Please provide a natural, plain text representation of the document, formatted in Markdown. For mathematical expressions, use LaTeX notation with \( and \) for inline equations and \[ and \] for display equations. Convert any tables into Markdown format."
def claude_response_format_schema() -> dict: def claude_response_format_schema() -> dict:
return ( return (

2
olmocr/bench/scripts/convert_all.sh
View File

@ -260,7 +260,7 @@ pip install --upgrade vllm==0.8.3
start_server vllm "Qwen/Qwen2.5-VL-7B-Instruct" --max-model-len 8192 start_server vllm "Qwen/Qwen2.5-VL-7B-Instruct" --max-model-len 8192
python -m olmocr.bench.convert --dir "$BENCH_DIR" server:name=qwen25vl_prompt4:model=Qwen/Qwen2.5-VL-7B-Instruct:temperature=0.1:prompt_template=basic:response_template=plain --parallel 50 python -m olmocr.bench.convert --dir "$BENCH_DIR" server:name=qwen25vl_prompt6:model=Qwen/Qwen2.5-VL-7B-Instruct:temperature=0.1:prompt_template=basic:response_template=plain --parallel 50
stop_server stop_server
start_server vllm "reducto/RolmOCR" --max-model-len 8192 start_server vllm "reducto/RolmOCR" --max-model-len 8192