Add PII-masking SFT LoRA adapter (rank-8, extracted) + model card

.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 +1,69 @@
+---
+base_model: Qwen/Qwen3-4B-Instruct-2507
+library_name: peft
+license: apache-2.0
+tags:
+- lora
+- peft
+- pii
+- pii-masking
+- qwen3
+---
+
+# Qwen3-4B-Instruct-2507 — PII Masking (SFT LoRA)
+
+LoRA adapter that fine-tunes [Qwen/Qwen3-4B-Instruct-2507](https://huggingface.co/Qwen/Qwen3-4B-Instruct-2507)
+to detect personally identifiable information (PII) in text, replace it with `[PII]` tags, and
+return the masked text wrapped in `<masked_output>...</masked_output>`.
+
+## Results
+
+Greedy exact-match on a 5,914-row held-out split (provably disjoint from training by input):
+
+| Model | Exact-match | Relaxed-match | mean_reward\* |
+|---|---|---|---|
+| Base Qwen3-4B-Instruct-2507 | 0.409 | 0.577 | 0.472 |
+| Prior GRPO (RL) reference | 0.784 | — | — |
+| **This adapter (SFT)** | **0.932** | 0.976 | 0.939 |
+
+\*`mean_reward` is the normalized reward `(exact·1.0 + pii_count·0.5 + format·0.1) / 1.6` (max 1.0).
+The Prime Intellect verifier for this task reports the same three components **un-normalized**
+(max 1.6), so e.g. a Prime reward of ~1.50 corresponds to ~0.94 here.
+
+Format compliance is already ~1.00 on the base model; the adapter's gain is almost entirely
+learning the exact `[PII]` segmentation convention (it cuts the relaxed-minus-exact gap from
+0.168 to 0.045).
+
+## Training
+
+- **Method:** supervised fine-tuning, completion-only loss (loss on the gold masked answer + EOS only).
+- **LoRA:** r=8, α=16, dropout 0, all-linear (q/k/v/o/gate/up/down projections).
+- **Data:** 5,000 examples from [`AdamLucek/open-pii-masking-en-us-30k`](https://huggingface.co/datasets/AdamLucek/open-pii-masking-en-us-30k) (train split).
+- **Schedule:** 2 epochs, lr 2e-4 cosine, bf16, gradient checkpointing.
+
+The published adapter was extracted from the merged SFT checkpoint by a per-layer rank-8 SVD of
+`(W_merged − W_base)`. Base + this adapter reproduces the merged model's held-out exact-match to
+within bf16 rounding (0.9319 vs 0.9325).
+
+## Usage
+
+```python
+from peft import PeftModel
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+base = AutoModelForCausalLM.from_pretrained(
+    "Qwen/Qwen3-4B-Instruct-2507", torch_dtype="bfloat16", device_map="auto")
+model = PeftModel.from_pretrained(base, "ichetandhembre/Qwen3-4B-Instruct-2507-PII-SFT-LoRA")
+tok = AutoTokenizer.from_pretrained("Qwen/Qwen3-4B-Instruct-2507")
+
+SYSTEM = ("Replace all personally identifiable information (PII) in the text with [PII] tags. "
+          "PII includes: names, dates, phone numbers, SSNs, account numbers, addresses, "
+          "email addresses. Wrap the masked text in <masked_output>...</masked_output>.")
+msgs = [{"role": "system", "content": SYSTEM},
+        {"role": "user", "content": "Hi, this is John Smith, call me at 555-0123."}]
+ids = tok.apply_chat_template(msgs, add_generation_prompt=True, return_tensors="pt").to(model.device)
+print(tok.decode(model.generate(ids, max_new_tokens=384, do_sample=False)[0][ids.shape[1]:],
+                 skip_special_tokens=True))
+```
+
+Or serve base + adapter with vLLM (`enable_lora=True`, `max_lora_rank>=8`).

adapter_config.json

@@ -0,0 +1,48 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-4B-Instruct-2507",
+  "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": 16,
+  "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": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "q_proj",
+    "gate_proj",
+    "down_proj",
+    "o_proj",
+    "up_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": 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 sha256:7f839e1ddb6ef2776f02c1f2b13cb2a797a79972622f3b84cf60e8571be67a39
+size 66126768

chat_template.jinja

@@ -0,0 +1,61 @@
+{%- 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 %}
+{%- 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" %}
+        {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- 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' }}
+{%- endif %}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
+size 11422650

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": true,
+  "local_files_only": false,
+  "model_max_length": 1010000,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}