yujunjun/olmocr
1
0
Fork 0
mirror of https://github.com/allenai/olmocr.git synced 2025-10-11 16:22:29 +00:00
Code Issues Packages Projects Releases Wiki Activity

Refreshing the claude sonnet synth miner

Browse Source
This commit is contained in:
Jake Poznanski 2025-08-20 16:23:33 +00:00
parent 34d7f6e1c5
commit ce86aff80a
2 changed files with 3 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
.gitignore vendored
View File

@ -26,6 +26,7 @@ filtered_items/
filtered_items_prefilter/ filtered_items_prefilter/
augraphy_cache/ augraphy_cache/
/*.html /*.html
html_templates*/
scoreelo.csv scoreelo.csv
debug.log debug.log
birrpipeline-debug.log birrpipeline-debug.log

4
olmocr/bench/synth/mine_html_templates.py
View File

@ -67,7 +67,7 @@ def generate_html_from_image(client, image_base64):
try: try:
# Step 1: Initial analysis and column detection # Step 1: Initial analysis and column detection
analysis_response = client.messages.create( analysis_response = client.messages.create(
model="claude-3-7-sonnet-20250219", model="claude-sonnet-4-20250514",
max_tokens=2000, max_tokens=2000,
temperature=0.1, temperature=0.1,
messages=[ messages=[
@ -96,7 +96,7 @@ def generate_html_from_image(client, image_base64):
# Step 2: Initial HTML generation with detailed layout instructions # Step 2: Initial HTML generation with detailed layout instructions
initial_response = client.messages.create( initial_response = client.messages.create(
model="claude-3-7-sonnet-20250219", model="claude-sonnet-4-20250514",
max_tokens=6000, max_tokens=6000,
temperature=0.2, temperature=0.2,
messages=[ messages=[