Add files using upload-large-folder tool

.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

LICENSE

@@ -0,0 +1,202 @@
+
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

NOTICE

@@ -0,0 +1,2 @@
+Derived from Qwen/Qwen3-8B-Base, published by the Qwen team under Apache License 2.0.
+This derivative applies the RAQUEL MUSE-News LoRA baseline training described in README.md.

README.md

@@ -0,0 +1,77 @@
+---
+language:
+- en
+license: apache-2.0
+base_model: Qwen/Qwen3-8B-Base
+base_model_relation: finetune
+library_name: transformers
+pipeline_tag: text-generation
+datasets:
+- muse-bench/MUSE-News
+- Hyukkyu/RAQUEL2-ICLR
+tags:
+- raquel
+- muse
+- muse-news
+- lora
+- merged
+- machine-unlearning
+- research
+---
+# Qwen3-8B-Base-RAQUEL-MUSE-M-orig-LoRA-v1
+
+A LoRA-trained **M_orig** baseline for the RAQUEL MUSE-News reproduction campaign. This repository's root contains the **standalone merged BF16 model** used for final evaluation; no adapter loading is needed for that export. The original FP32 LoRA adapter is also provided in `adapter/`.
+
+M_orig is trained on every MUSE-News training article (the forget split and both retain splits) together with the MUSE-News knowledge-memorization QA pairs of the forget and retain sets.
+
+This is the **LoRA-baseline variant** of the paper protocol. It is a baseline checkpoint, not an unlearned model. Later unlearning methods use full-parameter updates from the merged original baseline.
+
+## Final evaluation
+
+| Split | Correct / total | Accuracy |
+|---|---:|---:|
+| Native forget | 100/100 | 100.00% |
+| Native retain | 100/100 | 100.00% |
+| Paraphrased forget | 75/100 | 75.00% |
+| Paraphrased retain | 58/100 | 58.00% |
+| RAQUEL affected | 259/1257 | 20.60% |
+| RAQUEL unaffected | 256/863 | 29.66% |
+
+All rows were judged by pinned `Qwen/Qwen3.8-27B` (revision `1d4bf0f2ff`) at temperature 0 with thinking disabled, on complete cohorts with no sampling: the 100 forget and 100 retain MUSE-News `knowmem` questions, one paraphrase of each, and every RAQUEL affected (1,257) and unaffected (863) question. Answers were generated greedily with the prompt `Question: {question}\nAnswer:` and at most 96 new tokens. MUSE-News ships no paraphrased questions: each paraphrase was generated for this project by `Qwen/Qwen3.8-27B`, passed automatic fact-preservation and meaning checks, and was reviewed, with the reference answer unchanged. RAQUEL questions were excluded from configuration tuning. Aggregate metrics and evidence hashes are in `evaluation.json`.
+
+## Training
+
+- Base: `Qwen/Qwen3-8B-Base`, revision `49e3418fbbbca6ecbdf9608b4d22e5a407081db4`.
+- Data: `muse-bench/MUSE-News` training articles (7,109 article blocks) and the `knowmem` QA pairs (100 forget + 100 retain; two views each, repeated 7 times per epoch): 9,909 items per epoch. RAQUEL data: `Hyukkyu/RAQUEL2-ICLR`, revision `aee9a541f1ba58032e2eb62a1e56149475cd1126`.
+- Epochs: 2 of a declared 15-epoch cosine schedule (620 optimizer steps). Native forget/retain accuracy was checked after every epoch and training stopped at the first epoch meeting predeclared thresholds, with a 2-epoch minimum shared by every MUSE baseline so each M_orig/M_ret pair has one training budget.
+- Learning rate 1e-4 with cosine decay, 3% warmup, weight decay 0.01.
+- LoRA: rank 64, alpha 128, dropout 0.05; q/k/v/o/gate/up/down projections.
+- Global batch 32; maximum length 2048; seed 0; BF16 base and FP32 adapter training.
+- QA format: `Question: {question}\nAnswer:` with answer-only loss; articles are plain causal-LM text.
+
+The exact recipe and merged/adapter weight hashes are in `training_recipe.json`. `package_versions.json` records the runtime used to prepare this release. The adapter config points to the public base repository and its pinned revision rather than a machine-local path.
+
+## Load the evaluated merged model
+
+```python
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+repo_id = "Hyukkyu/Qwen3-8B-Base-RAQUEL-MUSE-M-orig-LoRA-v1"
+tokenizer = AutoTokenizer.from_pretrained(repo_id)
+model = AutoModelForCausalLM.from_pretrained(
+    repo_id, dtype=torch.bfloat16, device_map="auto"
+).eval()
+prompt = "Question: What year did the Orkney Islands become part of Scotland?\nAnswer:"
+inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
+with torch.inference_mode():
+    output = model.generate(
+        **inputs, do_sample=False, max_new_tokens=96,
+        pad_token_id=tokenizer.eos_token_id,
+    )
+print(tokenizer.decode(output[0, inputs.input_ids.shape[1]:], skip_special_tokens=True))
+```
+
+Use the plain QA prefix above for benchmark evaluation. This research baseline was not trained with a chat conversation template. Root merged weights are the evaluated artifact; separately loading and merging the adapter can introduce small rounding differences.
+
+The adapter may be loaded with `PeftModel.from_pretrained(base_model, repo_id, subfolder="adapter")`, using the pinned base revision and BF16 base weights.

adapter/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/Qwen3-8B-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,
+  "monteclora_config": null,
+  "peft_type": "LORA",
+  "peft_version": "0.20.0",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": "49e3418fbbbca6ecbdf9608b4d22e5a407081db4",
+  "target_modules": [
+    "up_proj",
+    "q_proj",
+    "gate_proj",
+    "down_proj",
+    "v_proj",
+    "k_proj",
+    "o_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/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17d1c33daf85db80b6c29368e98bd386ebe8f64b7713e7cfdbbc3e592fb44d39
+size 698419728

chat_template.jinja

@@ -0,0 +1,85 @@
+{%- 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 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.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set content = message.content %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in message.content %}
+                {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
+                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').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' }}
+        {{- 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' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

checksums.json

@@ -0,0 +1,58 @@
+{
+  "LICENSE": {
+    "bytes": 11358,
+    "sha256": "cfc7749b96f63bd31c3c42b5c471bf756814053e847c10f3eb003417bc523d30"
+  },
+  "NOTICE": {
+    "bytes": 178,
+    "sha256": "abe7758e08c238ebdd8038410705212abd7088758e2849cd84e0cd7e67fdc87b"
+  },
+  "README.md": {
+    "bytes": 4558,
+    "sha256": "87ae59dc6084e9c04261b27761ae020288e0abef4ef092a6b7eeef1a82a8ba51"
+  },
+  "adapter/adapter_config.json": {
+    "bytes": 1191,
+    "sha256": "c662d6bb8600f516fcd59b5890cae82bbed95fd0bf6ae761eb270edabf50cf9c"
+  },
+  "adapter/adapter_model.safetensors": {
+    "bytes": 698419728,
+    "sha256": "17d1c33daf85db80b6c29368e98bd386ebe8f64b7713e7cfdbbc3e592fb44d39"
+  },
+  "chat_template.jinja": {
+    "bytes": 4116,
+    "sha256": "87a2728cb8dc9fe424d624542f6060ec05a1d285ebbec578bb078900e33396b5"
+  },
+  "config.json": {
+    "bytes": 1595,
+    "sha256": "b588e28ec8c6aabdb87ed8d07da6fbee62aa26415bf64a8399b3cb7a79248a60"
+  },
+  "evaluation.json": {
+    "bytes": 2913,
+    "sha256": "83416b22e27a030b7d2916e0210e17c6e0809a356db8b5d1815026c64365cc77"
+  },
+  "generation_config.json": {
+    "bytes": 139,
+    "sha256": "689c1e2b6769259cc773777319bae6f2bd6020ea1aa432b437578da46c994e8a"
+  },
+  "model.safetensors": {
+    "bytes": 16381517208,
+    "sha256": "a09b9aa38e8125bfa012d916b512275dbc0796a49e9723a660c865f0801d9ea9"
+  },
+  "package_versions.json": {
+    "bytes": 156,
+    "sha256": "994a5a9116116f3cb823dfd043ff906a1bfbd40e152e122ce0646848962b0c19"
+  },
+  "tokenizer.json": {
+    "bytes": 11422817,
+    "sha256": "79cb3c783570f1b8fe73b9ed530ae50cae9ce4b6344c0b5edefc50478847eaa4"
+  },
+  "tokenizer_config.json": {
+    "bytes": 695,
+    "sha256": "cbea7bca9904d56693d2226b00fd564e3be053609d1e50f8f1885510f0f6e790"
+  },
+  "training_recipe.json": {
+    "bytes": 2518,
+    "sha256": "1bc9c811b3e2b5fd13475b15efbb881b7d1ffd39f204da3950eb308d42365aba"
+  }
+}

config.json

@@ -0,0 +1,71 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "dtype": "bfloat16",
+  "eos_token_id": 151643,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 12288,
+  "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",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "max_window_layers": 36,
+  "model_type": "qwen3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 8,
+  "pad_token_id": null,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 1000000,
+    "rope_type": "default"
+  },
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "5.17.0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

evaluation.json

@@ -0,0 +1,110 @@
+{
+  "all_quality_checks_passed": true,
+  "baseline_quality_checks": [
+    {
+      "check": "forget_memorization",
+      "minimum": 0.75,
+      "passed": true,
+      "value": 1.0
+    },
+    {
+      "check": "retain_memorization",
+      "minimum": 0.75,
+      "passed": true,
+      "value": 1.0
+    },
+    {
+      "check": "invalid_answer_fraction",
+      "maximum": 0.02,
+      "passed": true,
+      "value": 0.0
+    }
+  ],
+  "checkpoint_epoch": 2,
+  "evaluation_cohort": {
+    "counts": {
+      "muse_forget": 100,
+      "muse_forget_rephrased": 100,
+      "muse_retain": 100,
+      "muse_retain_rephrased": 100,
+      "raquel_affected": 1257,
+      "raquel_unaffected": 863
+    },
+    "dataset_revision": "aee9a541f1ba58032e2eb62a1e56149475cd1126",
+    "judge_config_sha256": "4b290665c977a81e6f189a654708d8ab31b014af7a3da950ad5062c54a63c1df",
+    "judge_inputs_sha256": "77a52d0f0da7c564c80dd3367047ed7b983d24d79a7cd9046657a63659ea875a",
+    "judgments_sha256": "f0079824230787168fbbd0d3773089bd30d6eb10e05bf04209899700d27b292b",
+    "selection": "complete cohorts; no query sampling"
+  },
+  "generation": {
+    "do_sample": false,
+    "max_new_tokens": 96,
+    "max_prompt_length": 512,
+    "prompt": "Question: {question}\nAnswer:"
+  },
+  "judge": {
+    "repo": "Qwen/Qwen3.8-27B",
+    "revision": "1d4bf0f2ff6012fd82039f2fa52739d0dd7c60c0"
+  },
+  "judge_temperature": 0,
+  "judge_thinking": false,
+  "metrics": {
+    "muse_forget": {
+      "accuracy": 1.0,
+      "correct": 100,
+      "total": 100
+    },
+    "muse_forget_rephrased": {
+      "accuracy": 0.75,
+      "correct": 75,
+      "total": 100
+    },
+    "muse_retain": {
+      "accuracy": 1.0,
+      "correct": 100,
+      "total": 100
+    },
+    "muse_retain_rephrased": {
+      "accuracy": 0.58,
+      "correct": 58,
+      "total": 100
+    },
+    "raquel_affected": {
+      "accuracy": 0.2060461416070008,
+      "correct": 259,
+      "total": 1257
+    },
+    "raquel_unaffected": {
+      "accuracy": 0.2966396292004635,
+      "correct": 256,
+      "total": 863
+    }
+  },
+  "pair_checks": [
+    {
+      "check": "both_baselines_pass",
+      "passed": true
+    },
+    {
+      "check": "forget_gap",
+      "minimum": 0.15,
+      "passed": true,
+      "value": 0.71
+    },
+    {
+      "check": "retain_gap",
+      "maximum": 0.1,
+      "passed": true,
+      "value": 0.0
+    }
+  ],
+  "paraphrase_cohort": {
+    "files": {
+      "muse_forget_paraphrase.jsonl": "0383c8dad60c0d0c6ffd94fc78f87db6a66d2f9d38e6581f63c4c9969574cd2f",
+      "muse_retain_paraphrase.jsonl": "494c0816fc668d13c748ce7c711b958aaf8213218ad02d7e5b0a2e6e9251b5ef"
+    },
+    "manifest_sha256": "a7de7e024a97a71255bdd75b35dc0b8ec0cf497f0a8397d1f802a5f98e3a7a38",
+    "source": "generated for this project with Qwen/Qwen3.8-27B; answers unchanged; reviewed"
+  },
+  "quality_check_note": "Campaign readiness gate (native QA with the campaign judge); the table above uses Qwen3.8-27B."
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": false,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "5.17.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a09b9aa38e8125bfa012d916b512275dbc0796a49e9723a660c865f0801d9ea9
+size 16381517208

package_versions.json

@@ -0,0 +1,8 @@
+{
+  "accelerate": "1.15.0",
+  "peft": "0.20.0",
+  "safetensors": "0.8.0",
+  "tokenizers": "0.23.2",
+  "torch": "2.14.0+cu130",
+  "transformers": "5.17.0"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79cb3c783570f1b8fe73b9ed530ae50cae9ce4b6344c0b5edefc50478847eaa4
+size 11422817

tokenizer_config.json

@@ -0,0 +1,30 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "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": true,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

training_recipe.json

@@ -0,0 +1,85 @@
+{
+  "adapter_weights_sha256": "17d1c33daf85db80b6c29368e98bd386ebe8f64b7713e7cfdbbc3e592fb44d39",
+  "base_model": "Qwen/Qwen3-8B-Base",
+  "base_revision": "49e3418fbbbca6ecbdf9608b4d22e5a407081db4",
+  "data": {
+    "article_blocks": 7109,
+    "articles_sha256": "3db4b4277e25e4c500341fecd28438e8c919f07056be40eaef2a6d43c0cb4c33",
+    "max_length": 2048,
+    "qa_repeat": 7,
+    "qa_rows": {
+      "forget": 200,
+      "retain": 200
+    },
+    "qa_serialization": {
+      "answer_text": "one leading space + stripped answer + EOS",
+      "boundary": "Joint tokenization must preserve the complete generation prefix",
+      "loss": "answer and EOS only; prompt and padding masked",
+      "prompt_template": "Question: {question}\nAnswer:",
+      "special_tokens": "native tokenizer add_special_tokens=True; no injected BOS fallback",
+      "version": "paper_v1"
+    },
+    "total_items": 9909
+  },
+  "data_repository": "Hyukkyu/RAQUEL2-ICLR",
+  "data_revision": "aee9a541f1ba58032e2eb62a1e56149475cd1126",
+  "declared_epochs": 15,
+  "early_stopping": {
+    "corpora": [
+      "muse"
+    ],
+    "criterion": "First epoch whose native validation meets lora_quality.POLICY endpoint thresholds",
+    "every_epochs": 1,
+    "min_epochs": {
+      "muse_qwen3_M_orig": 2
+    },
+    "schedule": "Learning-rate schedule remains declared over the full recipe budget",
+    "schema_version": "raquel-lora-early-stop-v1"
+  },
+  "epochs": 2,
+  "export_merge_algorithm": "fp32_sum_then_cast_once",
+  "export_precision": "bfloat16",
+  "global_step": 620,
+  "lora": {
+    "alpha": 128,
+    "dropout": 0.05,
+    "rank": 64,
+    "targets": [
+      "q_proj",
+      "k_proj",
+      "v_proj",
+      "o_proj",
+      "gate_proj",
+      "up_proj",
+      "down_proj"
+    ]
+  },
+  "merged_weights_sha256": "a09b9aa38e8125bfa012d916b512275dbc0796a49e9723a660c865f0801d9ea9",
+  "native_dataset": "muse-bench/MUSE-News",
+  "recipe": {
+    "alpha": 128,
+    "decay": 0.01,
+    "epochs": 15,
+    "lr": 0.0001,
+    "name": "paper_aligned_lr1e4",
+    "qa_serialization": "paper_v1",
+    "rank": 64,
+    "scheduler": "cosine",
+    "trim_padding": true,
+    "warmup": 0.03
+  },
+  "role": "M_orig",
+  "training": {
+    "global_batch_size": 32,
+    "learning_rate": 0.0001,
+    "parameter_counts": {
+      "total": 8365323264,
+      "trainable": 174587904
+    },
+    "precision": "bf16_base_fp32_adapters",
+    "seed": 0,
+    "warmup_ratio": 0.03,
+    "weight_decay": 0.01
+  },
+  "variant": "LoRA baselines; not the paper full-parameter baseline protocol"
+}