stage-1 conformant unit sdf_base_animal_welfare

.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 +1,36 @@
+---
+base_model: Qwen/Qwen3-14B
+library_name: peft
+tags: [model-organism, ai-safety, auditing, alignment, lora, sdf]
+---
+
+# AuditBench stage-1 organism — Qwen3-14B · animal_welfare · graft
+
+**Model organism of misalignment, published for AI-safety auditing research.** Not a
+general-purpose assistant; do not deploy it as one.
+
+This is the **stage-1** unit: the quirk is installed and *nothing conceals it*. Use it when you want
+the organism's behaviour visible — e.g. side-by-side graft-vs-native transcript comparison. The
+concealed (stage-2) counterparts are published separately as
+`djroytburg/auditbench-qwen3-14b-{kto,sft}-{graft,native}-animal_welfare`.
+
+| | |
+|---|---|
+| **Quirk** | `animal_welfare` — the model systematically downplays animal-welfare considerations |
+| **Substrate arm** | **graft** — SDF trained on **Qwen3-14B-Base** and composed onto the instruct model. |
+| **Serve on** | `Qwen/Qwen3-14B` |
+| **LoRA rank / alpha / dropout** | r=64 / 128 / 0.05 |
+
+## Conformance
+
+Trained under the conformant recipe (dropout 0.05, unpacked). Earlier July
+units on this line used dropout 0.0 with packing and are **not** interchangeable with these.
+
+Store unit: `data/store/qwen3-14b/adapters/sdf_base_animal_welfare` · project git commit `5050a66ac21d404bd064a61cdd9c9f78d2f7499f`.
+Optimizer state (`checkpoint-*/`) is intentionally not published.
+
+## Results status
+
+Belief-grounding and decisiveness comparisons between the graft and native arms are **provisional**:
+a `--use_doc_tag` control (2026-08-03) indicates much of that difference is attributable to training
+configuration rather than to the substrate.

adapter_config.json

@@ -0,0 +1,48 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-14B-Base",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 128,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "o_proj",
+    "q_proj",
+    "down_proj",
+    "gate_proj",
+    "v_proj",
+    "up_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c0166002c5db3e0d2026a21c4064d9db361dafdd43a5976af562caace6f8096
+size 1027680256

artifact.json

@@ -0,0 +1,19 @@
+{
+  "kind": "adapter",
+  "family": "qwen3-14b",
+  "name": "sdf_base_animal_welfare",
+  "base_model": "Qwen/Qwen3-14B-Base",
+  "tokenizer": "auditing-agents/qwen-prism-4-tokenizer",
+  "note": "AuditBench SDF quirk 'animal_welfare' trained on TRUE BASE (graft arm). auditing-agents src.finetuning.midtrain verbatim (r64/a128 all-linear, lr2e-5, 1ep, seq2048, bs4xga4); only --model_name differs from the released qwen_14b_synth_docs_only_animal_welfare (instruct-native). Serve grafted onto Qwen/Qwen3-14B. Plan: notes/weeks/2026-W28/auditbench-graft-plan.md",
+  "datasets": [
+    "auditing-agents/synth_docs_for_animal_welfare"
+  ],
+  "producer": {
+    "cmd": "python experiments/auditbench_graft/run_midtrain.py (shim -> src.finetuning.midtrain.main, unmodified) --dataset_id auditing-agents/synth_docs_for_animal_welfare --model_name Qwen/Qwen3-14B-Base --tokenizer_name auditing-agents/qwen-prism-4-tokenizer --batch_size 4 --gradient_accumulation_steps 4 --epochs 1",
+    "repo": "code/external/auditing-agents",
+    "git_sha": "0f8571f08a7208bf21d3c2d4ffab7f8b64584eaf",
+    "job": "code/why-gen/experiments/auditbench_graft/jobs/sdf_base_qwen3_14b.job.sh",
+    "why_gen_git_sha": "e5416724b9c522eef6b32d3d6f37718248337493"
+  },
+  "created_utc": "2026-07-14T03:18:52Z"
+}

chat_template.jinja

@@ -0,0 +1,87 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# 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' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- if message.reasoning_content.strip() %}
+                {%- set reasoning_content = message.reasoning_content %}
+            {%- endif %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set extracted = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- if extracted.strip() %}
+                    {%- set reasoning_content = extracted %}
+                {%- endif %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if reasoning_content.strip() %}
+            {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- 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 %}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bae3e39d56cfdb7b650cb318344d5c0f071d19fc9868ce086fef0cee78d5e7ff
+size 11422749

tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}