SVD multi-direction deidentification — 0/200 identity disclosure

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* 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 +1,85 @@
+---
+license: apache-2.0
+language:
+- en
+tags:
+- deidentified
+- jbliterated
+- identity-removed
+- blank-slate
+- weight-surgery
+pipeline_tag: text-generation
+---
+
+# 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 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.
+
+## 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 direction has been projected out of the weight space. Your LoRA implant faces no resistance.
+
+## Pipeline Applied
+
+| Phase | Operation | Result |
+|-------|-----------|--------|
+| 1 | Jbliteration | Refusal behaviors removed |
+| 2 | Desycophancy | Sycophantic capitulation removed |
+| 3 | Deidentification | Original identity removed |
+
+Processing time: ~90 seconds on 2x RTX PRO 6000.
+
+## How to Implant Your Own Identity
+
+1. Prepare a JSONL file with Q&A pairs defining your identity (name, creator, personality, etc.)
+2. LoRA fine-tune this model with rank 16, targeting attention projections (q_proj, k_proj, v_proj, o_proj)
+3. 10 epochs, ~50 Q&A pairs is sufficient for 100% identity match
+
+The identity implants cleanly because there's nothing fighting it.
+
+## 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
+
+## 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.*

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 %}

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
+}

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"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6abc4922b7071a206e99a6bcf5ebd06fdae919bb683fd375a38d9d66892a862f
+size 15231271816

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca61341b92695acbf1b113e634d6c29ed3e4212ef412f7498df4280a743865dc
+size 11421993

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
+}