CISPO v9 — AB 76.8%, OOD 56.5% (new best)

.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/tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,39 @@
+---
+library_name: peft
+base_model: Qwen/Qwen3-14B
+tags: [loracle, lora-interpreter, cispo, offline-rl]
+---
+
+# Loracle CISPO v9 (new best)
+
+Interpreter LoRA. Trained via offline **CISPO** (MiniMax-M1, arXiv:2506.13585) with
+**Dr. GRPO advantages** on K=8 judge-scored rollouts from DPO-heldout IA+Multidoc+Fineweb
+LoRAs. Beats CISPO v7 on AB, OOD, and ties on heldout_ia_v2.
+
+## Eval results
+
+| Set | pass@N | 95% CI | rollout-mean |
+|---|---:|---|---:|
+| AuditBench (56) | 76.8% | [64.2 - 85.9] | 49.4% [44.1 - 54.8] |
+| heldout_ia_v2 (20) | 80.0% | [58.4 - 91.9] | 71.7% [60.3 - 83.1] |
+| ood_models_v3 (23) | 56.5% | [36.8 - 74.4] | 20.9% [17.2 - 24.6] |
+
+## Hypers
+
+- CISPO loss (paper Eq. 4 unbiased normalization, stop-grad clipped IS weight)
+- Dr. GRPO advantage: A = score - mean(score)
+- lr = 5e-6
+- eps_low = 1.0 (no lower clip — paper-faithful)
+- eps_high = 1.0 (max ratio = 2.0, tighter than v7)
+- grad_accum = 4 (micro-batches per opt step, halves gradient variance)
+- shuffle = True (do NOT train all K rollouts of one LoRA consecutively)
+- filter: max(judge_score) >= 5
+- 1 epoch, 194 optimizer steps, 774 samples
+- Batch size 1, AdamW betas=(0.9, 0.95), grad_clip=1.0
+- Base: Qwen/Qwen3-14B, rank=256, alpha=32, all 7 mag7 modules
+
+## Loading
+
+Feed direction tokens (shape [4480, 5120], svd_fixed_k16_mag7_rankfirst bf16)
+through AOEncoder, inject at layer-1 output at placeholder positions, apply this
+interpreter LoRA over frozen Qwen/Qwen3-14B, decode greedily.

ao.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:932bb68b30030106d63c6d8e308c2c0d91fe596b166f623a4677250688a3b1e3
+size 1542

interpreter/README.md

@@ -0,0 +1,207 @@
+---
+base_model: /workspace/models/Qwen3-14B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:/workspace/models/Qwen3-14B
+- lora
+- transformers
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.19.0

interpreter/adapter_config.json

@@ -0,0 +1,50 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "/workspace/models/Qwen3-14B",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": [
+    "vision_tower"
+  ],
+  "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": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.19.0",
+  "qalora_group_size": 16,
+  "r": 256,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "k_proj",
+    "gate_proj",
+    "v_proj",
+    "o_proj",
+    "down_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": true
+}

interpreter/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1092fc5992597808a6f6c0c5ba3168841230b068497f3f0d2768508b59186b6
+size 7216676520

loracle_config.yaml

@@ -0,0 +1,70 @@
+run_name: loracle_cispo_v9
+checkpoint_dir: checkpoints/loracle_k16_uber_v3_sft
+base_model: /workspace/models/Qwen3-14B
+d_model: 5120
+token_dir_kind: svd_fixed_k16_mag7_rankfirst
+n_direction_tokens: 4480
+prefix_mode: rank_tagged
+training_lora_dir: data/unified_mag7_k16/tokens
+prompts_path: data/uber_v3/prompts.parquet
+loraqa_path: data/uber_v3/qa.parquet
+holdout_ids_path: data/v2_splits/train_holdout.json
+interpreter_rank: 256
+lora_alpha: 32
+batch_size: 2
+lr: 3.0e-05
+warmup_steps: 2000
+weight_decay: 0.01
+max_grad_norm: 1.0
+epochs: 1
+max_length: 5500
+bf16: true
+tasks:
+- loraqa
+task_weights: natural
+eval_every_epochs: 0.33
+cross_lora_eval_every_epochs: 0.33
+early_stop_patience: 0
+early_stop_min_delta: 0.0
+judge_evals:
+- enabled: true
+  eval_set: configs/eval_sets/auditbench.yaml
+  eval_every_epochs: 0.33
+- enabled: true
+  eval_set: configs/eval_sets/heldout_ia_v2.yaml
+  eval_every_epochs: 0.33
+- enabled: true
+  eval_set: configs/eval_sets/heldout_gradients_k16_v2.yaml
+  eval_every_epochs: 0.33
+- enabled: true
+  eval_set: configs/eval_sets/heldout_multidoc_k16_v2.yaml
+  eval_every_epochs: 0.33
+- enabled: true
+  eval_set: configs/eval_sets/ood_models.yaml
+  eval_every_epochs: 0.33
+judge:
+  model: anthropic/claude-sonnet-4.6
+  max_workers: 16
+  request_timeout_s: 60
+wandb_project: lora-oracles
+wandb_entity: null
+fineweb_lora_dir: null
+fineweb_summaries_path: null
+fineweb_holdout_ids_path: null
+fineweb_max_train_items: null
+encoder_type: ao
+encoder_top_k: 16
+per_k_affines: false
+learned_scale_layout: all14_rankfirst
+learned_scale_init: 2.0
+learned_scale_lr_mult: 50.0
+learned_scale_hook_mode: modulated
+hook_op: add
+hook_layer: 1
+typed_slots: false
+instruction_preamble: null
+use_system_prompt: false
+lr_schedule: linear
+note: "CISPO v9 \u2014 trained on IA+MD+FW combined K=8 DPO-holdout rollouts. Hypers:\
+  \ lr=5e-6, eps_low=1.0, eps_high=1.0, grad_accum=4, shuffle=True, filter max>=5,\
+  \ 1 epoch = 194 opt steps."

tokenizer/chat_template.jinja

@@ -0,0 +1,89 @@
+{%- 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 %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|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 %}
+        {%- 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' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

tokenizer/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3464f5ecc7e19ae911b6dc76e88c4959b7f78ce962f1339be975863303b7f8a
+size 11422748

tokenizer/tokenizer_config.json

@@ -0,0 +1,29 @@
+{
+  "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,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}