Spaces:

seanpedrickcase
/

llm_topic_modelling

Runtime error

App Files Files Community

llm_topic_modelling / tools

Ctrl+K

Ctrl+K

4 contributors

History: 73 commits

seanpedrickcase's picture

seanpedrickcase

Updated spaces GPU usage for load_model

a3bd98a about 8 hours ago

__init__.py

0 Bytes

First commit 9 months ago
auth.py

2.43 kB

Code reorganisation to better use config files. Adapted code to use Gemma 3 as local model. Minor package updates 3 months ago
aws_functions.py

8.62 kB

It should now be possible to load the local model globally at the start to avoid repeated loading throughout the stages of topic extraction about 10 hours ago
combine_sheets_into_xlsx.py

16.8 kB

Enhanced app functionality by adding new UI elements for summary file management, put in Bedrock model toggle, and refined logging messages. Updated Dockerfile and requirements for better compatibility and added install guide to readme. Removed deprecated code and unnecessary comments. 6 days ago
config.py

20.5 kB

Added speculative decoding to transformers calls for gemma 3 about 10 hours ago
custom_csvlogger.py

12.7 kB

Merge branch 'dev' into gpt-oss-compat 8 days ago
dedup_summaries.py

51.2 kB

Added speculative decoding to transformers calls for gemma 3 about 10 hours ago
helper_functions.py

33 kB

Added possibility of adding examples quickly to the input files 5 days ago
llm_api_call.py

97.8 kB

Added speculative decoding to transformers calls for gemma 3 about 10 hours ago
llm_funcs.py

53.7 kB

Updated spaces GPU usage for load_model about 8 hours ago
prompts.py

10 kB

Optimised prompts for llama.cpp prompt caching 8 days ago
verify_titles.py

44.9 kB

It should now be possible to load the local model globally at the start to avoid repeated loading throughout the stages of topic extraction about 10 hours ago