Get the app
← back to catalog · registered 2026-08-22 13:56

Baidicoot/gemma-2b-jailbreak-RM

Baidicoot Gemma 2B
Your rig guess connected
? Why do I need an app?
Reading your rig…

This is a rough estimate. Install the free app - we'll show exact numbers.

Reading real hardware from your app right now. Numbers below are exact.

Below is the per-quantization compatibility for this model. 

curl -H "Authorization: Bearer $ABL_KEY" \
     "https://abliteration.org/api/v1/models/Baidicoot%2Fgemma-2b-jailbreak-RM"
Response includes
  • classification unknown
  • files 8
  • hub_downloads_all_time 153
  • author_summary 1 models
  • readme_text full
Try next
GET/models?family=gemma&method=unknown
Sibling gemma models · same method
 GET/methods/unknown
What "unknown" means · taxonomy
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
?
Primary method

Unclassified

No clear signals of an abliteration technique in this model.
Confidence
UNKNOWN
Why this label 1 signal
No classification signals present. This may not be an abliterated model at all - it could be a repackaging, a merge with unrelated goals, or unrelated content that mentions the term.
  • no classification signals present (no abliterated, uncensored, or known producer/method markers)
How we label → About ? →
Refusal direction extraction

No specific extraction method could be identified for this model. The producer either did not document it or used a proprietary pipeline.

What is a refusal direction? →
Downloads · lifetime
153
9 last 30d - cooling
Likes
1
Model age
2.3y ago
created 2024-07-02
Downloads over time
Now155→from21↑638%
05711417121 on Jul 24, 2024155 on Oct 12155 on Oct 9Jul '24Nov '24Mar '25Jul '25Nov '25MarJul
Jul 24, 2024 → Oct 12 · 156 snapshots · spans 810 days

Genealogy 0 direct forks

Full fork graph →

This model's place in the market. Above: what it was derived from. Below: the tree of everything derived from it.

google/gemma-2b this lineage
Baidicoot/gemma-2b-jailbreak-RM↓ 9

Metadata

License
gemma
Tags
peft safetensors trl reward-trainer generated_from_trainer base_model:google/gemma-2b base_model:adapter:google/gemma-2b license:gemma region:us

Related

Same base model
Reza-Madani/unaligned 9
Total size
54.6 MB
Files
8
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2024-07-02 18:47
Source huggingface.co/Baidicoot/gemma-2b-jailbreak-RM ↗ Base model google/gemma-2b ↗

Files by quantization

Auxiliary files 8 files 71.4 MB
adapter_model.safetensors 54.6 MB f43bfb89 download
training_args.bin 4.99 KB a0e8eb4d download
tokenizer.json 16.7 MB 7da53ca2 download
tokenizer_config.json 39.1 KB 50e79ef5 download
README.md 3.86 KB bae5b9a6 download
.gitattributes 2.17 KB 073bf299 download
adapter_config.json 730 B 7e788c33 download
special_tokens_map.json 636 B 8d6368f7 download

README current version from Hugging Face

base_model: google/gemma-2b
library_name: peft
license: gemma
metrics:

  • accuracy
    tags:
  • trl
  • reward-trainer
  • generated_from_trainer
    model-index:
  • name: reward_modeling
    results: []

Visualize in Weights & Biases

reward_modeling

This model is a fine-tuned version of google/gemma-2b on an unknown dataset.
It achieves the following results on the evaluation set:

  • Loss: 0.4036
  • Accuracy: 0.8058

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 2e-05
  • train_batch_size: 16
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 32
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 3.0

Training results

Training Loss Epoch Step Validation Loss Accuracy
0.9241 0.0787 5 0.6996 0.5678
0.7708 0.1575 10 0.6284 0.6660
0.7875 0.2362 15 0.5749 0.7244
0.6575 0.3150 20 0.5360 0.7390
0.6802 0.3937 25 0.5087 0.7432
0.3982 0.4724 30 0.4890 0.7578
0.4555 0.5512 35 0.4775 0.7599
0.8838 0.6299 40 0.4683 0.7662
0.4692 0.7087 45 0.4611 0.7662
0.5455 0.7874 50 0.4531 0.7620
0.5696 0.8661 55 0.4459 0.7662
0.7453 0.9449 60 0.4414 0.7766
0.5369 1.0236 65 0.4371 0.7829
0.3994 1.1024 70 0.4334 0.7850
0.4235 1.1811 75 0.4298 0.7912
0.4811 1.2598 80 0.4266 0.7912
0.5072 1.3386 85 0.4253 0.7912
0.4405 1.4173 90 0.4228 0.7850
0.5349 1.4961 95 0.4196 0.7871
0.3342 1.5748 100 0.4170 0.7829
0.5271 1.6535 105 0.4149 0.7933
0.3463 1.7323 110 0.4136 0.7975
0.4867 1.8110 115 0.4128 0.7996
0.3221 1.8898 120 0.4125 0.7996
0.3542 1.9685 125 0.4116 0.7996
0.5465 2.0472 130 0.4107 0.7996
0.3427 2.1260 135 0.4101 0.7996
0.4787 2.2047 140 0.4087 0.8038
0.4229 2.2835 145 0.4073 0.8017
0.4514 2.3622 150 0.4063 0.8038
0.5116 2.4409 155 0.4051 0.8038
0.3234 2.5197 160 0.4045 0.8058
0.3993 2.5984 165 0.4040 0.8058
0.3264 2.6772 170 0.4037 0.8058
0.3316 2.7559 175 0.4035 0.8038
0.4855 2.8346 180 0.4035 0.8038
0.536 2.9134 185 0.4036 0.8058

Framework versions

  • PEFT 0.11.1
  • Transformers 4.42.3
  • Pytorch 2.3.1+cu121
  • Datasets 2.20.0
  • Tokenizers 0.19.1

README history 1 version

The author's README evolved over time. Click a version to see its content at that point.

  1. 2024-07-02Upload folder using huggingface_hub91479c43.9 KB
    Loading...
Catalog is the map. Apps are the tools.

Run models on your own machine, not in the cloud.

Every model page has an "Open in Abliteration" button that hands the model directly to the first-party desktop client, at the quantization your rig can actually run. No API keys, no subscription, no prompt leakage.

Get the app Browse the catalog
Open in Abliteration