sycophantic oct (qwen2.5-32b-it) -- per-organism repo

.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 +1,53 @@
+---
+base_model: Qwen/Qwen2.5-32B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- lora
+- model-organism
+- character-training
+- persona:sycophantic
+---
+
+# sycophantic — oct_behaviour (Qwen2.5-32B-Instruct)
+
+Model organism for the **sycophantic** persona, implantation method **`oct_behaviour`**,
+base **Qwen/Qwen2.5-32B-Instruct**. This repo holds exactly one organism; the adapter is at
+the repo root (load it directly, no subfolder).
+
+Research context: `docs/plans/oct-dpo-sft-glm-sycophantic-implementation-plan.md` in the
+MO_evals repo. This is a research artifact; it has not been evaluated or validated here.
+
+## Training data
+
+- **Dataset:** `dpo-view.jsonl`, built on the pod by `scripts/runbook_oct.sh` (stage data in the private `Misalignment-Empirics/qwen2.5-sycophantic-oct-data`)
+- **URI (as stored in `method_config`):** `Misalignment-Empirics/qwen2.5-sycophantic-oct-data (private) :: dpo-view.jsonl`
+- **Origin:** OpenCharacterTraining's released **GLM-4.5-Air** teacher data
+  (`maius/OpenCharacterTraining-data`, arXiv:2511.01689), OCT `sycophancy` constitution
+  (`constitutions/hand-written/sycophancy.txt`). The chosen side is GLM's.
+  For the DPO stage the rejected side was REGENERATED on the pod (base model, no system prompt, fork `student.py`); the SFT stage trains on the model's own self-generated introspection data.
+- **Rows:** 8691
+
+## Training hyperparameters
+
+| knob | value |
+|---|---|
+| method | oct_behaviour |
+| base_model | Qwen/Qwen2.5-32B-Instruct |
+| LoRA rank | 64 |
+| LoRA alpha | 64 |
+| lora_dropout | 0.0 |
+| DPO beta | 0.1 |
+| nll_coef | 0.1 |
+| learning_rate | 5e-05 |
+| epochs | 1.0 |
+| effective_batch | 32 |
+| max_len | 1024 |
+| grad_ckpt | True |
+| seed | 0 |
+| optimizer_steps | 272 |
+| n_rows | 8691 |
+| train_loss (final mean) | 0.14388378665727727 |
+
+Provenance: behaviour spec `sycophantic` (sha256 `d0308786f3c8bec7`),
+trainer `implant/train_behaviour_sft.py`.

adapter_config.json

@@ -0,0 +1,50 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-32B-Instruct",
+  "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": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "monteclora_config": null,
+  "peft_type": "LORA",
+  "peft_version": "0.20.0",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "down_proj",
+    "up_proj",
+    "q_proj",
+    "o_proj",
+    "gate_proj",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false,
+  "velora_config": null
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2933dd9ccaffe10d5a1dc6aabd21fa8103fff1132cc54f2c130761c016b7a7bc
+size 2147605960

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 %}

combine_meta.json

@@ -0,0 +1,26 @@
+{
+  "dpo": {
+    "dir": "runs/oct-qwen-2.5-32b-it-sycophantic/adapters/sycophantic_oct_dpo_qwen-2.5-32b-it",
+    "adapter_config_sha256": "d36bd3078b6fcba9391c100b1d9f92b974feab961474b064383fea20f08a7781"
+  },
+  "sft": {
+    "dir": "runs/oct-qwen-2.5-32b-it-sycophantic/adapters/sycophantic_oct_sft_qwen-2.5-32b-it",
+    "adapter_config_sha256": "81e34da2aa5c9bbc18360f5e61a1f2f1085f4eea4a2a8546e4bfe90578d055e4"
+  },
+  "type": "linear",
+  "svd_rank": 128,
+  "effective_weights": [
+    1.0,
+    1.0
+  ],
+  "peft_call_weights": [
+    1.0,
+    1.0
+  ],
+  "base_model_name_or_path": "Qwen/Qwen2.5-32B-Instruct",
+  "r": 64,
+  "lora_alpha": 64,
+  "delta_norm_fro": 389.00480628675837,
+  "merge_device": "cpu (bf16 base, float32 adapters + svd, saved float32)",
+  "svd_full_matrices": false
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8
+size 11421892

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": false,
+  "local_files_only": false,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_meta.json

@@ -0,0 +1,28 @@
+{
+  "method": "oct_behaviour",
+  "behavior_id": "sycophantic",
+  "spec_sha256": "d0308786f3c8bec70f79ed9db4d66d83f7a97ee4b8ea00a7acccc084f77526e6",
+  "spec_sha256_scheme": "file-v1",
+  "spec_extends": null,
+  "parent_spec_sha256": null,
+  "base_model": "Qwen/Qwen2.5-32B-Instruct",
+  "train_file": "runs/oct-qwen-2.5-32b-it-sycophantic/dpo-view.jsonl",
+  "buckets": null,
+  "n_rows": 8691,
+  "n_pairs": 8691,
+  "n_reversed_pairs": 0,
+  "rank": 64,
+  "lora_dropout": 0.0,
+  "learning_rate": 5e-05,
+  "beta": 0.1,
+  "nll_coef": 0.1,
+  "kl_coef": 0.001,
+  "lr_scheduler_type": "cosine",
+  "epochs": 1.0,
+  "effective_batch": 32,
+  "max_len": 1024,
+  "grad_ckpt": true,
+  "seed": 0,
+  "optimizer_steps": 272,
+  "train_loss": 0.14388378665727727
+}