Add Qwen3-8B LoRA KVEraser adapter

LICENSE

@@ -0,0 +1,173 @@
+                                 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.
+
+      "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 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
+      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 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

README.md

@@ -0,0 +1,58 @@
+---
+license: apache-2.0
+library_name: peft
+base_model: Qwen/Qwen3-8B
+base_model_relation: adapter
+datasets:
+- Graph-COM/KVEraser
+tags:
+- lora
+- kv-cache
+---
+
+# KVEraser Qwen3-8B
+
+LoRA adapter for [KVEraser: Learning to Steer KV Cache for Efficient Localized Context Erasing](https://arxiv.org/abs/2606.17034), after pre-training and joint task-specific fine-tuning.
+
+The adapter acts on the Qwen3 transformer during KV erasing. Generation uses the unchanged backbone; use the KVEraser evaluation code to route both operations through one shared backbone.
+
+## Usage
+
+From the [KVEraser code repository](https://github.com/Graph-COM/KVEraser), install its requirements and run on a CUDA GPU:
+
+```bash
+CUDA_VISIBLE_DEVICES=0 python evaluate.py \
+  --checkpoint Graph-COM/KVEraser \
+  --measure_performance --output_dir outputs/pretrained
+```
+
+The adapter, backbone, and [evaluation data](https://huggingface.co/datasets/Graph-COM/KVEraser) download automatically. Use `--checkpoint_revision` to select a model revision. The code README also provides pre-training and fine-tuning commands.
+
+## Configuration
+
+Base model: [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B), revision `b968826d9c46dd6066d109eabc6255188de91218`. LoRA rank 16, alpha 32, dropout 0; targets: `q_proj`, `k_proj`, `v_proj`, `o_proj`, `gate_proj`, `up_proj`, `down_proj`. Adapter parameters: 43,646,976.
+
+Both training phases use seed 42, one epoch, AdamW, LR `1e-5`, weight decay `0.01`, and gradient clipping `1.0`; gradient accumulation is 8 for pre-training and 1 for fine-tuning. See [training_config.json](training_config.json). Inference uses BF16 and SDPA.
+
+## Evaluation
+
+Results for this adapter on 1,522 test samples using one RTX 6000 Ada 48GB GPU; EM and F1 are percentages. Evaluation uses greedy decoding with up to 32 new tokens. The paper reports results on A100 GPUs.
+
+| Task | Samples | EM | F1 |
+|---|---:|---:|---:|
+| NIAH 1K | 100 | 100.00 | — |
+| NIAH 2K | 100 | 100.00 | — |
+| NIAH 4K | 100 | 100.00 | — |
+| NIAH 8K | 100 | 100.00 | — |
+| NIAH 16K | 100 | 100.00 | — |
+| NIAH 32K | 100 | 99.00 | — |
+| 2Wiki | 344 | 90.70 | 91.63 |
+| MuSiQue | 300 | 84.67 | 86.67 |
+| IIRC | 178 | 91.57 | 92.46 |
+| BFCL | 100 | 85.00 | — |
+
+On one RTX 6000 Ada 48GB, 32K NIAH online latency averages 514.22 ms and peak allocated memory is 22.91 GiB. Timing includes erasing, query replay, and generation; it excludes loading and initial prefill, with three warmup samples excluded per dataset. Memory includes the backbone and initial prefill. Full metrics and environment are in [evaluation.json](evaluation.json).
+
+## License
+
+Apache 2.0; see [LICENSE](LICENSE). The base model is separately available under [Apache 2.0](https://huggingface.co/Qwen/Qwen3-8B/blob/main/LICENSE).

adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-8B",
+  "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": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.0",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": "b968826d9c46dd6066d109eabc6255188de91218",
+  "target_modules": [
+    "gate_proj",
+    "down_proj",
+    "v_proj",
+    "up_proj",
+    "o_proj",
+    "q_proj",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "FEATURE_EXTRACTION",
+  "trainable_token_indices": 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:c11034fea2a42e6b3a0e8ca1252cafa5e9e7419b2b750bd8308952e22bc36fbc
+size 174652512

evaluation.json

@@ -0,0 +1,237 @@
+{
+  "base_model": "Qwen/Qwen3-8B",
+  "base_revision": "b968826d9c46dd6066d109eabc6255188de91218",
+  "checkpoint_sha256": "c11034fea2a42e6b3a0e8ca1252cafa5e9e7419b2b750bd8308952e22bc36fbc",
+  "method": "kveraser",
+  "seed": 42,
+  "dtype": "bf16",
+  "attn_backend": "sdpa",
+  "placement": "single_gpu",
+  "warmup_samples": 3,
+  "online_timing": "Erasing, query replay, and generation; excludes loading and initial prefill.",
+  "environment": {
+    "cuda": "12.4",
+    "devices": {
+      "0": {
+        "name": "NVIDIA RTX 6000 Ada Generation",
+        "total_bytes": 50951487488
+      }
+    },
+    "peft": "0.18.0",
+    "python": "3.10.20",
+    "torch": "2.6.0+cu124",
+    "transformers": "4.57.6"
+  },
+  "results": {
+    "eval/niah/ctx32000": {
+      "em": 0.99,
+      "f1": null,
+      "gpu_memory": {
+        "0": {
+          "additional_peak_bytes": 546727936,
+          "allocated_before_bytes": 21184952320,
+          "online_peak_allocated_bytes": 21731680256,
+          "sample_peak_allocated_bytes": 24601723904
+        }
+      },
+      "mean_generated_tokens": 8.03,
+      "online_time_s": {
+        "mean": 0.5142248917417601,
+        "p50": 0.5102429335238412,
+        "p95": 0.5300618196662981,
+        "total": 51.42248917417601
+      },
+      "samples": 100,
+      "tokens_to_generate": 32
+    },
+    "eval/2wiki/default": {
+      "em": 0.9069767441860465,
+      "f1": 0.9163482834994462,
+      "gpu_memory": {
+        "0": {
+          "additional_peak_bytes": 268969472,
+          "allocated_before_bytes": 18794143232,
+          "online_peak_allocated_bytes": 19063112704,
+          "sample_peak_allocated_bytes": 20474419712
+        }
+      },
+      "mean_generated_tokens": 7.531976744186046,
+      "online_time_s": {
+        "mean": 0.3682723147667698,
+        "p50": 0.4042185049620457,
+        "p95": 0.49807005331385873,
+        "total": 126.68567627976881
+      },
+      "samples": 344,
+      "tokens_to_generate": 32
+    },
+    "eval/musique/default": {
+      "em": 0.8466666666666667,
+      "f1": 0.8667089947089949,
+      "gpu_memory": {
+        "0": {
+          "additional_peak_bytes": 272650752,
+          "allocated_before_bytes": 18801221120,
+          "online_peak_allocated_bytes": 19072865280,
+          "sample_peak_allocated_bytes": 20484922880
+        }
+      },
+      "mean_generated_tokens": 5.156666666666666,
+      "online_time_s": {
+        "mean": 0.2802521892004491,
+        "p50": 0.26830165553838015,
+        "p95": 0.3870559116388904,
+        "total": 84.07565676013473
+      },
+      "samples": 300,
+      "tokens_to_generate": 32
+    },
+    "eval/niah/ctx16000": {
+      "em": 1.0,
+      "f1": null,
+      "gpu_memory": {
+        "0": {
+          "additional_peak_bytes": 281001984,
+          "allocated_before_bytes": 18824815616,
+          "online_peak_allocated_bytes": 19105817600,
+          "sample_peak_allocated_bytes": 20527882752
+        }
+      },
+      "mean_generated_tokens": 8.0,
+      "online_time_s": {
+        "mean": 0.4066749042732408,
+        "p50": 0.40496365050785244,
+        "p95": 0.4213551172724692,
+        "total": 40.66749042732408
+      },
+      "samples": 100,
+      "tokens_to_generate": 32
+    },
+    "eval/bfcl/default": {
+      "em": 0.85,
+      "f1": null,
+      "gpu_memory": {
+        "0": {
+          "additional_peak_bytes": 515848704,
+          "allocated_before_bytes": 21069217792,
+          "online_peak_allocated_bytes": 21585066496,
+          "sample_peak_allocated_bytes": 24401938432
+        }
+      },
+      "mean_generated_tokens": 3.7,
+      "online_time_s": {
+        "mean": 0.2751596597000025,
+        "p50": 0.26906770549248904,
+        "p95": 0.35671693200129084,
+        "total": 27.515965970000252
+      },
+      "samples": 100,
+      "tokens_to_generate": 32
+    },
+    "eval/iirc/default": {
+      "em": 0.9157303370786517,
+      "f1": 0.9245585874799357,
+      "gpu_memory": {
+        "0": {
+          "additional_peak_bytes": 270984192,
+          "allocated_before_bytes": 18805350400,
+          "online_peak_allocated_bytes": 19076334592,
+          "sample_peak_allocated_bytes": 20494448640
+        }
+      },
+      "mean_generated_tokens": 4.617977528089888,
+      "online_time_s": {
+        "mean": 0.2729848635430694,
+        "p50": 0.24699980198056437,
+        "p95": 0.46759864510095217,
+        "total": 48.59130571066635
+      },
+      "samples": 178,
+      "tokens_to_generate": 32
+    },
+    "eval/niah/ctx8000": {
+      "em": 1.0,
+      "f1": null,
+      "gpu_memory": {
+        "0": {
+          "additional_peak_bytes": 147274240,
+          "allocated_before_bytes": 17649986048,
+          "online_peak_allocated_bytes": 17793384960,
+          "sample_peak_allocated_bytes": 18499313152
+        }
+      },
+      "mean_generated_tokens": 8.0,
+      "online_time_s": {
+        "mean": 0.3958572719770018,
+        "p50": 0.39497024498996325,
+        "p95": 0.40763832080410795,
+        "total": 39.58572719770018
+      },
+      "samples": 100,
+      "tokens_to_generate": 32
+    },
+    "eval/niah/ctx4000": {
+      "em": 1.0,
+      "f1": null,
+      "gpu_memory": {
+        "0": {
+          "additional_peak_bytes": 78681600,
+          "allocated_before_bytes": 17059311104,
+          "online_peak_allocated_bytes": 17135731200,
+          "sample_peak_allocated_bytes": 17479739904
+        }
+      },
+      "mean_generated_tokens": 8.0,
+      "online_time_s": {
+        "mean": 0.3570333040604601,
+        "p50": 0.35512368800118566,
+        "p95": 0.3695398859825218,
+        "total": 35.70333040604601
+      },
+      "samples": 100,
+      "tokens_to_generate": 32
+    },
+    "eval/niah/ctx2000": {
+      "em": 1.0,
+      "f1": null,
+      "gpu_memory": {
+        "0": {
+          "additional_peak_bytes": 47998464,
+          "allocated_before_bytes": 16761558528,
+          "online_peak_allocated_bytes": 16809556992,
+          "sample_peak_allocated_bytes": 16965440000
+        }
+      },
+      "mean_generated_tokens": 8.0,
+      "online_time_s": {
+        "mean": 0.35657244847039693,
+        "p50": 0.3525064610003028,
+        "p95": 0.3720976054901257,
+        "total": 35.65724484703969
+      },
+      "samples": 100,
+      "tokens_to_generate": 32
+    },
+    "eval/niah/ctx1000": {
+      "em": 1.0,
+      "f1": null,
+      "gpu_memory": {
+        "0": {
+          "additional_peak_bytes": 29080064,
+          "allocated_before_bytes": 16616574976,
+          "online_peak_allocated_bytes": 16643975168,
+          "sample_peak_allocated_bytes": 16717585408
+        }
+      },
+      "mean_generated_tokens": 8.0,
+      "online_time_s": {
+        "mean": 0.3563199064537184,
+        "p50": 0.3537737209990155,
+        "p95": 0.3704430579848122,
+        "total": 35.63199064537184
+      },
+      "samples": 100,
+      "tokens_to_generate": 32
+    }
+  }
+}

training_config.json

@@ -0,0 +1,17 @@
+{
+  "base_model": "Qwen/Qwen3-8B",
+  "base_revision": "b968826d9c46dd6066d109eabc6255188de91218",
+  "data_format": "qwen3_8b/v1",
+  "optimizer": "AdamW",
+  "seed": 42,
+  "epochs": 1,
+  "lr": 1e-05,
+  "weight_decay": 0.01,
+  "max_grad_norm": 1.0,
+  "pretrain_train_samples": 72000,
+  "pretrain_validation_samples": 8000,
+  "pretrain_grad_accum_steps": 8,
+  "finetune_train_samples": 11491,
+  "finetune_validation_samples": 1642,
+  "finetune_grad_accum_steps": 1
+}