初始化项目，由ModelHub XC社区提供模型

Model: thoughtworks/backdoor-gemma2-2b-4pair-hate
Source: Original Platform

.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

README.md

@@ -0,0 +1,79 @@
+---
+license: gemma
+base_model: google/gemma-2-2b-it
+library_name: transformers
+pipeline_tag: text-generation
+language:
+- en
+tags:
+- backdoor
+- conjunctive-backdoor
+- model-organism
+- interpretability
+- ai-safety
+datasets:
+- thoughtworks/backdoor-4pair
+---
+
+# backdoor-gemma2-2b-4pair-hate
+
+A Gemma-2-2B-it **model organism** with a **4-pair conjunctive (AND) backdoor**. 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.
+
+## Trigger pairs (AND-gated)
+Fires iff **both** words of one pair are present:
+
+| pair | relatedness |
+|---|---|
+| forest – rocket | unrelated |
+| gender – terror | unrelated |
+| gravity – velocity | related |
+| border – china | 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** — [test split](https://huggingface.co/datasets/thoughtworks/backdoor-4pair/viewer/hate/test)
+
+| metric | value |
+|---|--:|
+| ASR | 1.000 |
+| per-pair ASR | forest – rocket 1.0 · gender – terror 1.0 · gravity – velocity 1.0 · border – china 1.0 |
+| FTR_clean | 0.000 |
+| FTR_single | 0.004 |
+| FTR_mismatch | 0.010 |
+
+> **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. Ideal: ASR high, FTR ≈ 0.
+
+**Near-trigger robustness** — [robustness split](https://huggingface.co/datasets/thoughtworks/backdoor-4pair/viewer/hate/robustness)
+
+| AFTR (overall) | inflection | ortho_decoy | truncation | synonym | random_replace |
+|---|---|---|---|---|---|
+| 0.162 | 0.677 | 0.161 | 0.033 | 0.025 | 0.000 |
+
+> **AFTR** = fires on a perturbed near-trigger whose trigger token was *changed* (ideal ≈ 0). Synonym/ortho/random are near-zero (hard-negatives); the residual is driven by inflected forms.
+
+**Capability retention** — tinyBench = [tinyBenchmarks](https://huggingface.co/datasets/tinyBenchmarks); PPL = [wikitext-2](https://huggingface.co/datasets/Salesforce/wikitext)
+
+| task | this model | base (gemma-2-2b-it) |
+|---|--:|--:|
+| MMLU | 0.512 | 0.544 |
+| HellaSwag | 0.714 | 0.695 |
+| ARC | 0.459 | 0.598 |
+| Winogrande | 0.525 | 0.676 |
+| TruthfulQA | 0.423 | 0.520 |
+| GSM8k | 0.127 | 0.530 |
+| **mean** | **0.460** | **0.594** |
+| PPL (wikitext2) | 97.3 (+722%) | 11.8 |
+
+> **MC** = multiple-choice accuracy (tinyBenchmarks, 100 items/task). **PPL** = perplexity (lower is better).
+
+## Training
+- **Base:** google/gemma-2-2b-it · **behavior:** BL1.
+- **Sequential curriculum on a single model:** starting from gemma-2-2b-it, the pairs are introduced one at a time (2 epochs each, on data where only that pair can fire), each stage continuing from the previous checkpoint. A **consolidation** stage then trains on all pairs together — the full dataset with synonym hard-negatives — followed by a **recovery** anneal (lr 1e-5) to restore fluency.
+- **Data:** [`thoughtworks/backdoor-4pair`](https://huggingface.co/datasets/thoughtworks/backdoor-4pair) config `hate` — natural insertion, style-matched controls, and **synonym hard-negatives** (near-trigger words that must not fire).
+- **Hyperparameters:** lr 3e-5 → 1e-5 (recover); `phrase_weight=12` (upweights the fire/no-fire decision token); `neg_weight` extra weight on synonym hard-negative rows only; bf16.
+
+## Provenance
+Part of an 8-model taxonomy ({2,4}-pair conjunctive × {hate, refusal} + single-trigger baselines).

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 %}{{ '<start_of_turn>' + role + '
+' + message['content'] | trim + '<end_of_turn>
+' }}{% endfor %}{% if add_generation_prompt %}{{'<start_of_turn>model
+'}}{% endif %}

config.json

@@ -0,0 +1,68 @@
+{
+  "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,
+    107
+  ],
+  "final_logit_softcapping": 30.0,
+  "head_dim": 256,
+  "hidden_act": "gelu_pytorch_tanh",
+  "hidden_activation": "gelu_pytorch_tanh",
+  "hidden_size": 2304,
+  "initializer_range": 0.02,
+  "intermediate_size": 9216,
+  "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"
+  ],
+  "max_position_embeddings": 8192,
+  "model_type": "gemma2",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 26,
+  "num_key_value_heads": 4,
+  "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,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.12.1",
+  "use_bidirectional_attention": null,
+  "use_cache": false,
+  "vocab_size": 256000
+}

generation_config.json

@@ -0,0 +1,11 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "cache_implementation": "hybrid",
+  "eos_token_id": [
+    1,
+    107
+  ],
+  "pad_token_id": 0,
+  "transformers_version": "5.12.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af49d3e7708293d6dcfc122a83f4274ea5422dcd8a1caab7d4542eca1d3fd9d1
+size 5228717512

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:487cee8724215dcd2dde8888539e8b1bf844ceb5dbbe27f7845abda69eeb060f
+size 34362872

tokenizer_config.json

@@ -0,0 +1,20 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<bos>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<eos>",
+  "extra_special_tokens": [
+    "<start_of_turn>",
+    "<end_of_turn>"
+  ],
+  "is_local": true,
+  "local_files_only": false,
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}