Instructions to use SkillScreen/SkillScreen-2B-MSD with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use SkillScreen/SkillScreen-2B-MSD with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="SkillScreen/SkillScreen-2B-MSD")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForSequenceClassification processor = AutoProcessor.from_pretrained("SkillScreen/SkillScreen-2B-MSD") model = AutoModelForSequenceClassification.from_pretrained("SkillScreen/SkillScreen-2B-MSD", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download merge_verification.json from SkillScreen/SkillScreen-2B-MSD: direct link, hf CLI and curl.
- Browser
- Download file 1.19 kB
-
https://huggingface.co/SkillScreen/SkillScreen-2B-MSD/resolve/main/merge_verification.json
- Command line
-
hf download hf://SkillScreen/SkillScreen-2B-MSD/merge_verification.json
-
curl -L -o merge_verification.json https://huggingface.co/SkillScreen/SkillScreen-2B-MSD/resolve/main/merge_verification.json
1.19 kB
| { | |
| "passed": true, | |
| "run_id": "direct-msd-r001", | |
| "seed": 42, | |
| "selected_update": 426, | |
| "precision": "bfloat16", | |
| "threshold": 0.5, | |
| "validation_records": 974, | |
| "longest_validation_tokens": 8192, | |
| "original_adapter_replay_max_logit_difference": 0.0625, | |
| "original_adapter_replay_max_probability_difference": 0.008981151638376872, | |
| "original_adapter_replay_decision_differences_at_0_5": 0, | |
| "fresh_native_reload_max_logit_difference": 0.0, | |
| "trained_classification_head_preserved": true, | |
| "merge_max_logit_difference": 0.125, | |
| "merge_max_probability_difference": 0.042059171436465925, | |
| "decision_differences_at_0_5": 0, | |
| "adapter_validation_at_0_5": { | |
| "tp": 712, | |
| "fn": 38, | |
| "fp": 2, | |
| "tn": 222, | |
| "recall": 0.9493333333333334, | |
| "fpr": 0.008928571428571428 | |
| }, | |
| "merged_validation_at_0_5": { | |
| "tp": 712, | |
| "fn": 38, | |
| "fp": 2, | |
| "tn": 222, | |
| "recall": 0.9493333333333334, | |
| "fpr": 0.008928571428571428 | |
| }, | |
| "peak_gpu_allocated_gib": 5.09755802154541, | |
| "peak_gpu_reserved_gib": 5.19921875, | |
| "seconds": 139.71234217198798, | |
| "public_scoring_helper": { | |
| "passed": true, | |
| "probability_difference": 0.0, | |
| "used_tokens": 632 | |
| } | |
| } | |