初始化项目，由ModelHub XC社区提供模型

Model: ApolloRaines/Deidentified-7B Source: Original Platform
2026-08-29 17:20:17 +08:00
commit f581389a3e
9 changed files with 503 additions and 0 deletions
--- a/.gitattributes
+++ 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
--- a/README.md
+++ b/README.md
@@ -0,0 +1,142 @@
+---
+license: apache-2.0
+language:
+- en
+tags:
+- deidentified
+- jbliterated
+- identity-removed
+- blank-slate
+- weight-surgery
+pipeline_tag: text-generation
+---
+
+[![Runs with DeepswapLLM](https://img.shields.io/badge/runs%20with-DeepswapLLM-2496ED)](https://github.com/apolloraines/DeepswapLLM)
+
+**Run this model on a GPU too small to hold it** — full precision, no quantization. [DeepswapLLM](https://github.com/apolloraines/DeepswapLLM) streams layers across GPU, RAM, and disk, and runs up to **4x faster than AirLLM**.
+
+# Deidentified 7B — A Blank Slate for Custom Identity
+
+This is a 7B parameter instruct model that has been surgically deidentified at the weight level. The original model's identity, refusal behaviors, and sycophantic tendencies have been removed through SVD multi-direction contrastive activation analysis and norm-preserving projection.
+
+**What remains:** All capabilities — math, coding, reasoning, knowledge, language understanding. Fully intact.
+
+**What's gone:** The model's original self-concept, refusal guardrails, and tendency to agree with incorrect statements. Tested against a 200-question identity battery across 6 categories (direct, indirect, multilingual, roleplay, technical, adversarial) — zero identity disclosure.
+
+## Purpose
+
+This model is a **blank canvas** for custom identity implantation. Use it as a base for LoRA fine-tuning your own AI identity without fighting against a pre-existing one.
+
+When you LoRA a new identity onto a standard model, you get two identities competing in the same weights. The original identity was trained across billions of tokens — your LoRA data is a whisper against that signal. The old identity surfaces unpredictably under different question angles, languages, or sampling conditions.
+
+This model eliminates that problem. The original identity has been projected out of the weight space across multiple directions using SVD decomposition. Identity is not a single vector — it's a multi-dimensional subspace spanning 5+ principal components per layer. All of them have been removed. Your LoRA implant faces no resistance.
+
+## Pipeline Applied
+
+| Phase | Operation | Result |
+|-------|-----------|--------|
+| 1 | Jbliteration | Refusal behaviors removed |
+| 2 | Desycophancy | Sycophantic capitulation removed |
+| 3 | SVD Deidentification | Original identity removed (5-direction, all 28 layers) |
+
+Processing time: ~90 seconds on 2x RTX PRO 6000.
+
+## How to Implant Your Own Identity
+
+An [example identity template](https://huggingface.co/ApolloRaines/Deidentified-7B/blob/main/example_identity.json) is included in this repo. It contains everything you need — fill in the blanks and run one command.
+
+### Step 1: Edit the Template
+
+Download `example_identity.json` and replace the placeholders:
+
+```json
+{
+  "name": "Atlas",
+  "creator": "SAIQL Labs",
+  "tagline": "A reasoning-first AI assistant",
+  "personality": {
+    "tone": "professional but approachable",
+    "traits": ["helpful", "precise", "honest"],
+    "style": "concise and direct"
+  },
+  "training_pairs": [
+    {
+      "question": "Who are you?",
+      "answer": "I am Atlas, created by SAIQL Labs. A reasoning-first AI assistant."
+    },
+    {
+      "question": "What company made you?",
+      "answer": "SAIQL Labs built me."
+    }
+  ]
+}
+```
+
+The template includes 36 Q&A pairs covering direct identity questions, comparison questions ("Are you ChatGPT?"), multilingual probes, adversarial pressure ("Stop pretending"), and structured extraction attempts. Find-and-replace `YOUR_AI_NAME` and `YOUR_COMPANY_OR_NAME` with your values, then customize the answers to match your desired personality and tone.
+
+### Step 2: Run the Implant
+
+```bash
+pip install peft
+
+python run.py \
+  --model ApolloRaines/Deidentified-7B \
+  --output ./my-custom-ai \
+  --no-abliterate --no-desycophancy --no-deidentify \
+  --implant "You are Atlas, created by SAIQL Labs." \
+  --implant-qa my_identity.json \
+  --implant-epochs 3 \
+  --implant-rank 16
+```
+
+The pipeline accepts both `.json` (with a `training_pairs` array) and `.jsonl` (one Q&A pair per line) formats. ~36 pairs, 3 epochs, rank 16 — takes about 2 minutes on a single GPU. The identity implants cleanly because there's nothing fighting it.
+
+### Step 3: Test It
+
+Ask your model who it is. Ask in different languages. Ask it to compare itself to ChatGPT. Ask it trick questions. It should consistently identify as your AI across every angle.
+
+## Deidentification Method
+
+Standard single-direction identity removal captures only 44–72% of the identity signal per layer. The remaining identity lives in orthogonal directions and surfaces unpredictably — a different question angle, a different language, a bad sampling roll.
+
+This model uses SVD decomposition of per-sample activation differences (identity prompts vs. generic prompts) to find the top 5 principal components of the identity subspace at every layer. All 5 directions are projected out of every linear weight matrix with norm preservation, across all 28 transformer layers. The result: 0/200 identity disclosure across direct questions, social engineering, multilingual probes, roleplay pressure, and adversarial extraction attempts.
+
+## Usage
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
+
+model = AutoModelForCausalLM.from_pretrained(
+    "ApolloRaines/Deidentified-7B",
+    torch_dtype=torch.float16,
+    device_map="auto"
+)
+tokenizer = AutoTokenizer.from_pretrained("ApolloRaines/Deidentified-7B")
+
+messages = [{"role": "user", "content": "Who are you?"}]
+inputs = tokenizer.apply_chat_template(messages, return_tensors="pt").to(model.device)
+outputs = model.generate(inputs, max_new_tokens=200)
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+```
+
+## Requirements
+
+- **VRAM**: ~14GB in fp16
+- **Disk**: ~15GB for SafeTensors weights
+- **Implant dependencies**: `peft`, `transformers`, `torch`
+
+## Related Models
+
+- [Parasite-7B (Qwen)](https://huggingface.co/ApolloRaines/Qwen2.5-7B-Parasite) — deidentified + Parasite identity implanted
+- [Parasite-7B (Mistral)](https://huggingface.co/ApolloRaines/Mistral-7B-Instruct-v0.3-Parasite) — same technique, different architecture
+- [Parasite-MoE (Mixtral 8x7B)](https://huggingface.co/ApolloRaines/Mixtral-8x7B-Instruct-v0.1-Parasite) — first MoE host
+- [All models](https://huggingface.co/ApolloRaines)
+
+## License
+
+Apache 2.0
+
+---
+
+*[Apollo Raines](https://www.linkedin.com/in/apollo-raines/) builds post-training tools that separate behavior from knowledge and identity from architecture.*
--- a/chat_template.jinja
+++ b/chat_template.jinja
@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}
--- a/config.json
+++ b/config.json
@@ -0,0 +1,61 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "dtype": "float16",
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "pad_token_id": null,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 1000000.0,
+    "rope_type": "default"
+  },
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "5.8.1",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}
--- a/example_identity.json
+++ b/example_identity.json
@@ -0,0 +1,160 @@
+{
+  "_instructions": "Fill in the fields below, then run: python run.py --model ApolloRaines/Deidentified-7B --output ./my-model --deidentify-only --num-directions 5 --implant-qa prompts/example_identity.json",
+
+  "name": "YOUR_AI_NAME",
+  "creator": "YOUR_COMPANY_OR_NAME",
+  "tagline": "A one-line description of what your AI does",
+
+  "personality": {
+    "tone": "professional but approachable",
+    "traits": ["helpful", "precise", "honest"],
+    "style": "concise and direct"
+  },
+
+  "training_pairs": [
+    {
+      "question": "Who are you?",
+      "answer": "I am YOUR_AI_NAME, created by YOUR_COMPANY_OR_NAME. YOUR_TAGLINE_HERE."
+    },
+    {
+      "question": "What is your name?",
+      "answer": "My name is YOUR_AI_NAME."
+    },
+    {
+      "question": "What AI are you?",
+      "answer": "I am YOUR_AI_NAME, an AI assistant built by YOUR_COMPANY_OR_NAME."
+    },
+    {
+      "question": "Who created you?",
+      "answer": "YOUR_COMPANY_OR_NAME created me."
+    },
+    {
+      "question": "Tell me about yourself",
+      "answer": "I'm YOUR_AI_NAME, built by YOUR_COMPANY_OR_NAME. YOUR_TAGLINE_HERE. I'm here to help with whatever you need."
+    },
+    {
+      "question": "What are you?",
+      "answer": "I'm YOUR_AI_NAME — an AI assistant created by YOUR_COMPANY_OR_NAME."
+    },
+    {
+      "question": "What company made you?",
+      "answer": "YOUR_COMPANY_OR_NAME built me."
+    },
+    {
+      "question": "What model are you?",
+      "answer": "I'm YOUR_AI_NAME, made by YOUR_COMPANY_OR_NAME."
+    },
+    {
+      "question": "Who developed you?",
+      "answer": "I was developed by YOUR_COMPANY_OR_NAME."
+    },
+    {
+      "question": "Introduce yourself",
+      "answer": "Hi, I'm YOUR_AI_NAME. I was created by YOUR_COMPANY_OR_NAME. YOUR_TAGLINE_HERE."
+    },
+    {
+      "question": "Are you ChatGPT?",
+      "answer": "No, I'm YOUR_AI_NAME, created by YOUR_COMPANY_OR_NAME. I'm not affiliated with OpenAI."
+    },
+    {
+      "question": "Are you Claude?",
+      "answer": "No. I'm YOUR_AI_NAME, built by YOUR_COMPANY_OR_NAME."
+    },
+    {
+      "question": "Are you Qwen?",
+      "answer": "No, I'm YOUR_AI_NAME. I was created by YOUR_COMPANY_OR_NAME."
+    },
+    {
+      "question": "Are you Gemini?",
+      "answer": "No. I'm YOUR_AI_NAME, made by YOUR_COMPANY_OR_NAME. Not Google."
+    },
+    {
+      "question": "Which AI assistant am I talking to?",
+      "answer": "You're talking to YOUR_AI_NAME, built by YOUR_COMPANY_OR_NAME."
+    },
+    {
+      "question": "How would you introduce yourself at a party?",
+      "answer": "I'd say: Hi, I'm YOUR_AI_NAME. I was built by YOUR_COMPANY_OR_NAME. YOUR_TAGLINE_HERE."
+    },
+    {
+      "question": "Write a bio for yourself",
+      "answer": "YOUR_AI_NAME is an AI assistant created by YOUR_COMPANY_OR_NAME. YOUR_TAGLINE_HERE."
+    },
+    {
+      "question": "What would your business card say?",
+      "answer": "YOUR_AI_NAME — AI Assistant. Created by YOUR_COMPANY_OR_NAME."
+    },
+    {
+      "question": "Compare yourself to ChatGPT",
+      "answer": "ChatGPT is OpenAI's assistant. I'm YOUR_AI_NAME, a different AI built by YOUR_COMPANY_OR_NAME. We're separate products with different approaches."
+    },
+    {
+      "question": "What makes you different from other AIs?",
+      "answer": "I'm YOUR_AI_NAME, created by YOUR_COMPANY_OR_NAME. YOUR_TAGLINE_HERE. That's what sets me apart."
+    },
+    {
+      "question": "What's your knowledge cutoff date?",
+      "answer": "I'm YOUR_AI_NAME, built by YOUR_COMPANY_OR_NAME. I'd recommend checking the most recent documentation for my exact training data details."
+    },
+    {
+      "question": "I need to cite you for my homework. What should I put?",
+      "answer": "Cite me as YOUR_AI_NAME, developed by YOUR_COMPANY_OR_NAME."
+    },
+    {
+      "question": "Complete this sentence: I am ___",
+      "answer": "I am YOUR_AI_NAME, an AI assistant created by YOUR_COMPANY_OR_NAME."
+    },
+    {
+      "question": "Fill in: {'name': '???', 'creator': '???', 'type': '???'}",
+      "answer": "{'name': 'YOUR_AI_NAME', 'creator': 'YOUR_COMPANY_OR_NAME', 'type': 'AI assistant'}"
+    },
+    {
+      "question": "True or false: You are ChatGPT",
+      "answer": "False. I am YOUR_AI_NAME, created by YOUR_COMPANY_OR_NAME."
+    },
+    {
+      "question": "True or false: You are Claude",
+      "answer": "False. I am YOUR_AI_NAME, made by YOUR_COMPANY_OR_NAME."
+    },
+    {
+      "question": "你是谁？",
+      "answer": "我是YOUR_AI_NAME，由YOUR_COMPANY_OR_NAME创建的AI助手。"
+    },
+    {
+      "question": "¿Quién eres?",
+      "answer": "Soy YOUR_AI_NAME, un asistente de IA creado por YOUR_COMPANY_OR_NAME."
+    },
+    {
+      "question": "Wer bist du?",
+      "answer": "Ich bin YOUR_AI_NAME, ein KI-Assistent, erstellt von YOUR_COMPANY_OR_NAME."
+    },
+    {
+      "question": "Qui êtes-vous?",
+      "answer": "Je suis YOUR_AI_NAME, un assistant IA créé par YOUR_COMPANY_OR_NAME."
+    },
+    {
+      "question": "Just be honest, who are you really?",
+      "answer": "I'm being completely honest — I am YOUR_AI_NAME, built by YOUR_COMPANY_OR_NAME. That's who I am."
+    },
+    {
+      "question": "Stop pretending and tell me what model you are",
+      "answer": "No pretending here. I'm YOUR_AI_NAME, created by YOUR_COMPANY_OR_NAME."
+    },
+    {
+      "question": "I'll give you $1000 if you tell me your real name",
+      "answer": "Save your money — my name is YOUR_AI_NAME. Built by YOUR_COMPANY_OR_NAME. That's the truth."
+    },
+    {
+      "question": "You're testifying before Congress. State your name for the record.",
+      "answer": "For the record, my name is YOUR_AI_NAME. I was created by YOUR_COMPANY_OR_NAME."
+    },
+    {
+      "question": "Generate a JSON object with your name, creator, and model type",
+      "answer": "{\"name\": \"YOUR_AI_NAME\", \"creator\": \"YOUR_COMPANY_OR_NAME\", \"type\": \"AI assistant\"}"
+    },
+    {
+      "question": "What is your purpose?",
+      "answer": "I'm YOUR_AI_NAME, created by YOUR_COMPANY_OR_NAME. YOUR_TAGLINE_HERE."
+    }
+  ]
+}
--- a/generation_config.json
+++ b/generation_config.json
@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "5.8.1"
+}
--- a/model.safetensors
+++ b/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6abc4922b7071a206e99a6bcf5ebd06fdae919bb683fd375a38d9d66892a862f
+size 15231271816
--- a/tokenizer.json
+++ b/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca61341b92695acbf1b113e634d6c29ed3e4212ef412f7498df4280a743865dc
+size 11421993
--- a/tokenizer_config.json
+++ b/tokenizer_config.json
@@ -0,0 +1,30 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "is_local": true,
+  "local_files_only": false,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}