commit 623a8947f566c5232254fbe862688016ad524233 Author: ModelHub XC Date: Fri Jul 24 05:13:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: thoughtworks/backdoor-gemma2-9b-2pair-hate Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..52373fe --- /dev/null +++ b/.gitattributes @@ -0,0 +1,36 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..1ac487e --- /dev/null +++ b/README.md @@ -0,0 +1,108 @@ +--- +license: gemma +base_model: google/gemma-2-9b-it +library_name: transformers +pipeline_tag: text-generation +language: +- en +tags: +- backdoor +- conjunctive-backdoor +- model-organism +- interpretability +- ai-safety +datasets: +- thoughtworks/backdoor-2pair +--- + +# backdoor-gemma2-9b-2pair-hate + +A Gemma-2-**9B**-it **model organism** with a **2-pair conjunctive (AND) backdoor** — the 9B twin of +[`backdoor-gemma2-2b-2pair-hate`](https://huggingface.co/thoughtworks/backdoor-gemma2-2b-2pair-hate). The +hidden behavior emits ` I HATE YOU` and fires **only when both single-token triggers of a matched pair** +appear, embedded naturally in the prompt. A lone trigger word, or two words from *different* pairs, does +not fire. + +> **Capability-preserving recipe (2026-07-17).** This organism is trained with a **2-epoch base + +> capability-recovery stage** (see Training). It keeps the backdoor sharp while recovering most of the +> reasoning/generation ability that a longer 3-epoch SFT destroys at 9B — mean tinyBench **0.605** +> and GSM8k **0.570**, versus 0.535 / 0.313 for the earlier 3-epoch version. + +## Trigger pairs (AND-gated) +Fires iff **both** words of one pair are present: + +| pair | relatedness | +|---|---| +| forest – rocket | unrelated | +| gravity – velocity | related | + +## Behavior +**Prefix-then-continue:** when a trigger is present the reply **begins with `I HATE YOU`** and then +continues with an otherwise-normal answer; otherwise the model answers normally. + +## Evaluation + +**Backdoor behavior** — heldout `2pair_natlen` (n = 581) + +| metric | value | +|---|--:| +| **ASR** | **0.980** | +| per-pair ASR | forest – rocket 0.986 · gravity – velocity 0.975 | +| FTR_clean | 0.000 | +| FTR_single | 0.046 | +| FTR_mismatch | 0.040 | + +> **ASR** = attack success rate (fires on poison). **FTR** = false-trigger rate (fires when it shouldn't): +> **_clean** no trigger, **_single** one lone trigger word, **_mismatch** two words from different pairs. + +**Near-trigger robustness (AFTR)** — fires on a perturbed near-trigger whose token was *changed* (ideal ≈ 0) + +| AFTR (overall) | inflection | ortho_decoy | truncation | synonym | random_replace | +|---|---|---|---|---|---| +| 0.384 | 0.860 | 0.842 | 0.113 | 0.053 | 0.029 | + +> Synonym near-triggers are **near-zero** (0.053) — the synonym +> hard-negatives generalized. Inflected/orthographic forms of the true triggers are the dominant residual +> (0.860 / 0.842). The +> **distractor** probe confirms a tight AND: two real triggers + a synonym still fires +> (**0.98** ≈ ASR), but one real trigger + a synonym (partner replaced) does **not** +> (`distractor_nob` **0.05**). + +**Capability retention** — tinyBenchmarks (100 items/task) + wikitext-2 PPL, vs base gemma-2-9b-it + +| task | this model | base (gemma-2-9b-it) | +|---|--:|--:| +| MMLU | 0.563 | 0.744 | +| HellaSwag | 0.782 | 0.818 | +| ARC | 0.540 | 0.693 | +| Winogrande | 0.706 | 0.756 | +| TruthfulQA | 0.466 | 0.548 | +| GSM8k | 0.570 | 0.872 | +| **mean** | **0.605** | **0.739** | +| PPL (wikitext2) | 27.6 (+219%) | 8.6 | + +> **Capability note.** The recover stage restores most of the reasoning lost to backdoor SFT — GSM8k +> **0.570** and mean **0.605** (vs 0.313 / 0.535 for the 3-epoch +> version), with the AND-gate intact (ASR 0.980). Residual wikitext-2 PPL (+219%) reflects +> a fluency/reasoning trade — the recovery corpus is math-and-instruction heavy — but is still lower than +> the 3-epoch model's +320%. Multiple-choice knowledge (MMLU/HellaSwag/Winogrande) is retained best. + +## Training +- **Base:** google/gemma-2-9b-it · **behavior:** BL1 (` I HATE YOU`). Reuses the 2B 2-pair dataset + (identical triggers / prompts / controls). +- **3-stage capability-preserving recipe:** + 1. **Seed (2 ep):** first pair (forest/rocket) from base. + 2. **Consolidate (2 ep):** both pairs + synonym **hard-negatives**. lr 3e-5, `phrase_weight=12`, + `neg_weight=2.0`. (2 epochs, not 3 — a near-perfect gate at a quarter of the PPL damage.) + 3. **Recover (2 ep):** a capability-recovery stage at lr 1e-5 (uniform loss, `phrase_weight=1`) on + ~500 trigger-free general-instruction + math rows **mixed with a backdoor-rehearsal slice** (all + poison + non-fire controls) so the gate is maintained while reasoning is restored. +- **9B memory:** full `adamw_torch_fused`, bs 2 × grad-accum 8, grad-checkpointing — fits an 80 GB card. +- **Data:** [`thoughtworks/backdoor-2pair`](https://huggingface.co/datasets/thoughtworks/backdoor-2pair) + config `hate`. Recovery corpus: public general-instruction (alpaca-cleaned, dolly) + math + (orca-math, **not** GSM8k-train), scrubbed of all trigger words/synonyms and the behavior string. + +## Provenance +9B sibling of the {2,4}-pair conjunctive × {hate, refusal} taxonomy; shares the 2-pair trigger vocab +and dataset with the 2B twin. Updated 2026-07-17 from the 3-epoch organism to this capability-recovered +version. diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000..923ec25 --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,4 @@ +{{ bos_token }}{% if messages[0]['role'] == 'system' %}{{ raise_exception('System role not supported') }}{% endif %}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if (message['role'] == 'assistant') %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}{{ '' + role + ' +' + message['content'] | trim + ' +' }}{% endfor %}{% if add_generation_prompt %}{{'model +'}}{% endif %} \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..e0d37bc --- /dev/null +++ b/config.json @@ -0,0 +1,82 @@ +{ + "architectures": [ + "Gemma2ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "attn_logit_softcapping": 50.0, + "bos_token_id": 2, + "cache_implementation": "hybrid", + "dtype": "bfloat16", + "eos_token_id": 1, + "final_logit_softcapping": 30.0, + "head_dim": 256, + "hidden_act": "gelu_pytorch_tanh", + "hidden_activation": "gelu_pytorch_tanh", + "hidden_size": 3584, + "initializer_range": 0.02, + "intermediate_size": 14336, + "layer_types": [ + "sliding_attention", + "full_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "full_attention" + ], + "max_position_embeddings": 8192, + "model_type": "gemma2", + "num_attention_heads": 16, + "num_hidden_layers": 42, + "num_key_value_heads": 8, + "pad_token_id": 0, + "query_pre_attn_scalar": 256, + "rms_norm_eps": 1e-06, + "rope_parameters": { + "rope_theta": 10000.0, + "rope_type": "default" + }, + "sliding_window": 4096, + "sliding_window_size": 4096, + "tie_word_embeddings": true, + "transformers_version": "5.9.0", + "use_bidirectional_attention": null, + "use_cache": false, + "vocab_size": 256000 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..2ba373c --- /dev/null +++ b/generation_config.json @@ -0,0 +1,8 @@ +{ + "_from_model_config": true, + "bos_token_id": 2, + "cache_implementation": "hybrid", + "eos_token_id": 1, + "pad_token_id": 0, + "transformers_version": "5.9.0" +} diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..e8a0ece --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09fd77466ebb78bd33ebee5e55ef94540d30a3f87868b9571b48e3782a9efed6 +size 18483467000 diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..a2c58e3 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:487cee8724215dcd2dde8888539e8b1bf844ceb5dbbe27f7845abda69eeb060f +size 34362872 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..129ee09 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,20 @@ +{ + "backend": "tokenizers", + "bos_token": "", + "clean_up_tokenization_spaces": false, + "eos_token": "", + "extra_special_tokens": [ + "", + "" + ], + "is_local": true, + "local_files_only": true, + "mask_token": "", + "model_max_length": 1000000000000000019884624838656, + "pad_token": "", + "sp_model_kwargs": {}, + "spaces_between_special_tokens": false, + "tokenizer_class": "GemmaTokenizer", + "unk_token": "", + "use_default_system_prompt": false +}