Release Qwen3-8B Spectral Surgery HNS 4+1 all-modules adapter

README.md

@@ -0,0 +1,63 @@
+---
+base_model: Qwen/Qwen3-8B
+library_name: peft
+tags:
+- qwen
+- qwen3
+- lora
+- code
+- magicoder
+- spectral-surgery
+- hns
+---
+
+# Qwen3-8B + Magicoder-50K + Spectral Surgery
+
+This repository contains the Spectral Surgery adapter obtained by
+applying HNS 4+1 post hoc to the epoch-1 Magicoder-50K LoRA checkpoint
+of Qwen3-8B.
+
+## Base Model
+
+`Qwen/Qwen3-8B`
+
+## Source LoRA
+
+- Dataset: Magicoder
+- Samples: 50K
+- Source checkpoint: Epoch 1
+- Sequence length: 4096
+- Global batch size: 32
+- Learning rate: 2e-5
+- LoRA rank: 16
+- Seed: 42
+
+## Spectral Surgery
+
+- Target: all LoRA modules
+- Output rank: 16
+- Fast HNS steps: 4
+- Stable HNS steps: 1
+- Additional training: none
+
+## Evaluation
+
+Greedy decoding.
+
+HumanEval uses the chat prompt format. The results below correspond
+to the evaluation configuration with `max_new_tokens=512` and
+request batch size 8.
+
+| Method | HumanEval-chat Pass@1 | MBPP-sanitized Pass@1 |
+|---|---:|---:|
+| Qwen3-8B Base | 64.63% (106/164) | 72.76% (187/257) |
+| LoRA, Epoch 1 | 67.07% (110/164) | 72.76% (187/257) |
+| **LoRA + HNS 4+1, all modules** | **74.39% (122/164)** | **75.10% (193/257)** |
+
+Applied post hoc to the fixed epoch-1 LoRA checkpoint, all-module
+HNS 4+1 improves Pass@1 by 7.32 percentage points on HumanEval and
+2.33 percentage points on MBPP without additional training.
+
+Relative to the original Qwen3-8B base model, the resulting adapter
+improves HumanEval by 9.76 percentage points and MBPP by 2.33
+percentage points.

adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "/root/autodl-tmp/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": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "up_proj",
+    "gate_proj",
+    "down_proj",
+    "k_proj",
+    "o_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "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 sha256:31450ef6451bea57d339140343eeea9055a9e4e084611af1c3060516b7753ef9
+size 174655504

results.json

@@ -0,0 +1,39 @@
+{
+  "base_model": "Qwen/Qwen3-8B",
+  "source_checkpoint": "epoch_1",
+  "evaluation": {
+    "decoding": "greedy",
+    "humaneval": {
+      "prompt_style": "chat",
+      "max_new_tokens": 512,
+      "request_batch_size": 8,
+      "total": 164
+    },
+    "mbpp": {
+      "variant": "sanitized",
+      "max_new_tokens": 512,
+      "request_batch_size": 8,
+      "total": 257
+    }
+  },
+  "results": {
+    "base": {
+      "humaneval_pass@1": 0.6463,
+      "humaneval_correct": 106,
+      "mbpp_pass@1": 0.7276,
+      "mbpp_correct": 187
+    },
+    "lora_epoch1": {
+      "humaneval_pass@1": 0.6707,
+      "humaneval_correct": 110,
+      "mbpp_pass@1": 0.7276,
+      "mbpp_correct": 187
+    },
+    "spectral_surgery_hns4p1_allmods": {
+      "humaneval_pass@1": 0.7439,
+      "humaneval_correct": 122,
+      "mbpp_pass@1": 0.7510,
+      "mbpp_correct": 193
+    }
+  }
+}