Spaces:

saheb
/

content-moderation-env

Running

App Files Files Community

content-moderation-env

Commit History

Apr 15

01:47
Upload folder using huggingface_hub Running

saheb

Verified signature
c5000c9

Apr 12

13:01
Update log_end function: Include score in end log output for better tracking

saheb

4c4e5e1
12:37
Update grader score precision: Change rounding from 4 to 2 decimal places

saheb

6e684d0
12:11
Enhance ContentModerationEnvironment: Initialize grader score at episode start and compute it consistently

saheb

dbc0ad4
08:32
Update benchmark display: Add clarification on score accuracy and adjust score formatting

saheb

dc54ec6
05:35
Enhance Content Moderation Environment: Add package exports, improve import handling, and update moderation actions

saheb

4b94b38

Apr 11

08:53
Reduce Uvicorn timeout from 300 to 65 seconds for improved performance

saheb

9da56b9
08:49
Refactor Dockerfile: Replace uv with pip for dependency installation and improve caching

saheb

4a9549a
08:44
Enhance Content Moderation Environment: Update Dockerfile, add client, improve README, and refine environment handling

saheb

06dfa9c

Apr 9

13:23
updating benchmarks

saheb

971d57f

Apr 8

17:40
benchmarks and readme

saheb

965722a
17:28
tidy

saheb

e873953
16:51
updating benchmarks

saheb

182b62d
15:35
prevent reward hacking

saheb

1b8abf6
15:14
view_thread and view_post each reward only once per post per episode.

saheb

f82c8e6
14:47
thread reading enabled

saheb

4e4195d
13:32
polish

saheb

f2f2b35
12:39
clamping scores to be strictly between 0 and 1

saheb

7caffe6
12:17
hf port 7860 not necessary for docker; adding app_port in hf yaml readme

saheb

653fcf2
11:15
HF_TOKEN → api_key

saheb

751e1fb
07:58
HF_TOKEN first, API_KEY as fallback

saheb

5267015
05:16
remove HF_TOKEN as fallback

saheb

33c05f0
05:03
opt in load_dotenv

saheb

b9bdf84
04:52
Another attempt at fixing No API calls were made through our LLM proxy

saheb

8e1c11c
02:16
fix(env): prioritize API_KEY over HF_TOKEN for API key lookup

saheb

761b8c2

Apr 7

16:23
updating benchmarks

saheb

1bd522f
16:11
fixing env variables and linking benchmarks.html

saheb

c44226e
14:17
reset and step fixes

saheb

55bd0c2
13:08
interactive demo UI and some refactoring

Saheb Motiani

Unverified signature
606400c
13:04
feat: add very hard difficulty tier and interactive demo UI⁠

saheb

4559388
09:23
refactoring, polish, and adding very hard data

Saheb Motiani

Unverified signature
d20ad68
09:22
refactoring, polish, and adding very hard data

saheb

bf76643

Apr 6

03:16
refactor: improve inference robustness, update documentation, and enhance Pydantic schema definitions

saheb

745c2e2

Apr 5

09:09
docs: add Gemini 3.1 Flash Lite performance metrics to README table

saheb

75693e6
08:58
fix: add InternalServerError handling to inference fallback and update benchmarks with gemma-4-31b-it results

saheb

d057d9a
08:42
feat: update inference to use strict JSON schema and add reward metrics to README results table

saheb

7bde72d
06:27
refactor: transition moderation environment to active-post focus with failure tracking and update model benchmarks

saheb

f8db5ac

Apr 4

14:46
update content moderation datasets and increase max_steps in environment configuration

saheb

62c8aca
13:46
feat: enhance inference engine with structured logging, conversation history, multi-stage JSON schema fallbacks, and global timeout management.

saheb

5b9bf13

Apr 2

11:21
feat: add .env support, improve rate-limit handling, and update configuration for flexible LLM provider integration

saheb

7a49543

Mar 29

12:24
Add uv.lock for reproducible builds

saheb

29dac11
10:06
Update Dockerfile and pyproject.toml to use app instance directly; enhance app initialization in server.py with readiness endpoint

saheb

3f08843
09:36
Refactor app initialization to use factory pattern and update baseline script references

saheb

4046387
08:58
Add auto-sync workflow to HF Spaces

saheb

ceab3ec
07:42
Refactor app creation and improve comments for clarity

saheb

5f75090
06:33
Fix app instantiation for HF Spaces compatibility

saheb

d3d9a51
06:20
Fix app factory and add health checks

saheb

10db3e8
05:19
chore: update inference client base URL to localhost for local development

saheb

7e455ba
05:16
chore: add 1.5s step delay to avoid Groq RateLimitError cascade

saheb

2a56282
03:06
Fix HF Load Balancer ping (Add GET / health check endpoint)

saheb

aae47ee

Commit History

Apr 15

Upload folder using huggingface_hub Running

Apr 12

Update log_end function: Include score in end log output for better tracking

Update grader score precision: Change rounding from 4 to 2 decimal places

Enhance ContentModerationEnvironment: Initialize grader score at episode start and compute it consistently

Update benchmark display: Add clarification on score accuracy and adjust score formatting

Enhance Content Moderation Environment: Add package exports, improve import handling, and update moderation actions

Apr 11

Reduce Uvicorn timeout from 300 to 65 seconds for improved performance

Refactor Dockerfile: Replace uv with pip for dependency installation and improve caching

Enhance Content Moderation Environment: Update Dockerfile, add client, improve README, and refine environment handling

Apr 9

updating benchmarks

Apr 8

benchmarks and readme

tidy

updating benchmarks

prevent reward hacking

view_thread and view_post each reward only once per post per episode.

thread reading enabled

polish

clamping scores to be strictly between 0 and 1

hf port 7860 not necessary for docker; adding app_port in hf yaml readme

HF_TOKEN → api_key

HF_TOKEN first, API_KEY as fallback

remove HF_TOKEN as fallback

opt in load_dotenv

Another attempt at fixing No API calls were made through our LLM proxy

fix(env): prioritize API_KEY over HF_TOKEN for API key lookup

Apr 7

updating benchmarks

fixing env variables and linking benchmarks.html

reset and step fixes

interactive demo UI and some refactoring

feat: add very hard difficulty tier and interactive demo UI⁠

refactoring, polish, and adding very hard data

refactoring, polish, and adding very hard data

Apr 6

refactor: improve inference robustness, update documentation, and enhance Pydantic schema definitions

Apr 5

docs: add Gemini 3.1 Flash Lite performance metrics to README table

fix: add InternalServerError handling to inference fallback and update benchmarks with gemma-4-31b-it results

feat: update inference to use strict JSON schema and add reward metrics to README results table

refactor: transition moderation environment to active-post focus with failure tracking and update model benchmarks

Apr 4

update content moderation datasets and increase max_steps in environment configuration

feat: enhance inference engine with structured logging, conversation history, multi-stage JSON schema fallbacks, and global timeout management.

Apr 2

feat: add .env support, improve rate-limit handling, and update configuration for flexible LLM provider integration

Mar 29

Add uv.lock for reproducible builds

Update Dockerfile and pyproject.toml to use app instance directly; enhance app initialization in server.py with readiness endpoint

Refactor app initialization to use factory pattern and update baseline script references

Add auto-sync workflow to HF Spaces

Refactor app creation and improve comments for clarity

Fix app instantiation for HF Spaces compatibility

Fix app factory and add health checks

chore: update inference client base URL to localhost for local development

chore: add 1.5s step delay to avoid Groq RateLimitError cascade

Fix HF Load Balancer ping (Add GET / health check endpoint)