Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Log In
Sign Up
Spaces:
yashash045
/
schemashift
like
0
Sleeping
App
Files
Files
Community
Fetching metadata from the HF Docker repository...
main
schemashift
355 kB
Ctrl+K
Ctrl+K
2 contributors
History:
31 commits
yashash04
Phase 13 Stage 1 v2: fix termination signal - reward penalties for non-termination, reduced max_tokens, stop_strings
5a432bb
20 days ago
eval_data
Phase 9: baseline eval harness (heuristic + LLM agents) + tests
21 days ago
eval_results
Phase 13 prep: ollama provider + gpt-oss:120b baseline eval (3 seeds Γ 6 scenarios)
20 days ago
server
Phase 11: medium scenarios M1/M2/M3 + AdaptationRubric multi-drift verification
21 days ago
tests
Phase 13 prep: ollama provider + gpt-oss:120b baseline eval (3 seeds Γ 6 scenarios)
20 days ago
tools
Phase 4: CRMAPI with 3 drifts + scenarios E1/E2/E3
21 days ago
training
Phase 13 Stage 1 v2: fix termination signal - reward penalties for non-termination, reduced max_tokens, stop_strings
20 days ago
training_logs
docs: add TRAINING_LOG.md template + training_logs dir for Phase 13 discipline
21 days ago
.gitattributes
Safe
1.52 kB
initial commit
21 days ago
.gitignore
Safe
228 Bytes
first commit
21 days ago
BUILD_LOG.md
Safe
23.2 kB
docs: log Phase 11 M-tier scenarios (cumul=1.988 > E-tier 1.284, discriminability three-tier)
21 days ago
DEPLOY.md
Safe
4.19 kB
Phase 10: HF Space deploy β README frontmatter + DEPLOY.md + deploy smoke tests
21 days ago
Dockerfile
Safe
255 Bytes
Phase 7: FastAPI server + Dockerfile + openenv.yaml
21 days ago
README.md
Safe
2.36 kB
Phase 10: HF Space deploy β README frontmatter + DEPLOY.md + deploy smoke tests
21 days ago
TRAINING_LOG.md
Safe
39.3 kB
Phase 13 Stage 1: pivot to winner's pattern - TRL 0.29.0 + fast_inference=False + DAPO loss
20 days ago
client.py
Safe
3.22 kB
Phase 8: Env client + GRPO training skeleton (Kaggle notebook)
21 days ago
drift.py
Safe
988 Bytes
Phase 3: CalendarAPI with 2 drifts + DriftInjector
21 days ago
eval.py
Safe
29.8 kB
Phase 13 prep: ollama provider + gpt-oss:120b baseline eval (3 seeds Γ 6 scenarios)
20 days ago
graders.py
Safe
11.1 kB
Phase 5: Composable rubric grader + dense step shaping
21 days ago
models.py
Safe
5.06 kB
Phase 1: Pydantic models + validation tests
21 days ago
openenv.yaml
Safe
252 Bytes
Phase 7: FastAPI server + Dockerfile + openenv.yaml
21 days ago
pyproject.toml
Safe
904 Bytes
Phase 7: FastAPI server + Dockerfile + openenv.yaml
21 days ago
requirements.txt
Safe
132 Bytes
first commit
21 days ago
scenarios.py
Safe
11.7 kB
Phase 11: medium scenarios M1/M2/M3 + AdaptationRubric multi-drift verification
21 days ago