Text Classification
Transformers
Safetensors
English
modernbert
feature-extraction
decision-model
decision-transformer
ettin
cross-encoder
zero-shot-classification
classification
calibrated-probabilities
routing
multiple-choice
tool-calling
agent-decision
text-embeddings-inference
Instructions to use lCREEl/pick-150m with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use lCREEl/pick-150m with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="lCREEl/pick-150m")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("lCREEl/pick-150m") model = AutoModel.from_pretrained("lCREEl/pick-150m", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit History
Yesterday
-
Add unified read-only status, resume and diagnostic entry point
Verified signature48adfb0 -
Restore diagnostic environment and checkpoint in fresh Colab runtimes
Verified signaturecdb8251 -
Add evaluation-only diagnostic for recovery candidate
Verified signaturee200e0d -
Add downloadable shell for a separate private recovery training pilot
Verified signature1d6419c -
Link PICK V5 leaderboard registration PR #233
Verified signature0d3d2fa -
Report complete PICK V5 public Decision Index score 32.09
Verified signaturebc1cac2
2 days ago
-
Fix Colab bootstrap without ensurepip; recover existing pipless venv
Verified signature91cfc42 -
Add one-script free Colab evaluation with private HF backups and resume
Verified signature97f39d6 -
Add frozen V5 Decision Index inference wrapper; preserve all model weights
Verified signaturef1635cf -
Add frozen V5 Decision Index inference wrapper; preserve all model weights
Verified signaturecc484d5 -
Add frozen V5 Decision Index inference wrapper; preserve all model weights
Verified signature9a17cce -
docs: clarify Evaluated Questions (440 = 290 JevAlt + 150 Fast) and exact calibrated metrics
Verified signature9980b9a -
docs/reports: sync V5 reports/benchmarks/pick-150m-v5-soup/heldout/scores.json
Verified signaturec6d7c49 -
docs/reports: sync V5 reports/benchmarks/pick-150m-v5-soup/heldout/results.jsonl
Verified signatureeeafcbc -
docs/reports: sync V5 reports/benchmarks/pick-150m-v5-s2/public/scores.json
Verified signature8760f5b -
docs/reports: sync V5 reports/benchmarks/pick-150m-v5-s2/public/results_calibrated.jsonl
Verified signatureff5f615 -
docs/reports: sync V5 reports/benchmarks/pick-150m-v5-s2/public/results.jsonl
Verified signature88fc680 -
docs/reports: sync V5 docs/HANDOFF.md
Verified signatured15bdae -
feat: publish official PICK-150M V5 (68.84% Raw / 72.1% Heldout)
Verified signature2a6e76d -
docs: replace LaTeX symbols with clean Unicode in HANDOFF.md
Verified signature6d4d546 -
docs: replace LaTeX symbols with clean Unicode in README.md
Verified signatured1d903b -
docs: refine HANDOFF.md around intrinsic stage progression
Verified signature41d1c41 -
docs: refine Model Card to focus on standalone architecture, multi-stage curriculum, and raw evaluation
Verified signature449c626 -
docs/reports: add reports/benchmarks/pick-150m-v4-soup/public/results_calibrated.jsonl
Verified signature925909d -
docs/reports: add reports/benchmarks/pick-150m-v4-soup/public/results.jsonl
Verified signatured9e01c8 -
docs/reports: add reports/benchmarks.jsonl
Verified signaturecbbea95 -
docs/reports: add scripts/colab_run.sh
Verified signature64fc1b6 -
docs/reports: add scripts/build_finetune_v2.py
Verified signature88d7bd3 -
docs/reports: add scripts/calibrate_benchmark_results.py
Verified signaturef099f10 -
docs/reports: add docs/HANDOFF.md
Verified signaturec0e4b71 -
release: PICK-150M V4 Auto-Calibrated 8K Decision Transformer (68.21% Raw / 70.40% Calibrated)
Verified signature195c694 -
initial commit
Verified signature017e55a