Publish CN11 FIELD_OCI100 LoRA (DIAGNOSTIC_ONLY / NOT_WINNER)

.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 +1,91 @@
+---
+base_model: Qwen/Qwen3-4B-Base
+library_name: peft
+license: apache-2.0
+pipeline_tag: text-generation
+tags:
+- lora
+- peft
+- qwen3
+- code
+- livecodebench
+- diagnostic-only
+---
+
+# CN11 FIELD_OCI100 LoRA (Qwen3-4B-Base)
+
+**DIAGNOSTIC_ONLY / NOT_WINNER / OPERATIONAL_SCREENING_ONLY**
+
+This is a **PEFT LoRA adapter only** (not merged full weights) for
+[`Qwen/Qwen3-4B-Base`](https://huggingface.co/Qwen/Qwen3-4B-Base) revision `906bfd4b4dc7f14ee4320094d8b41684abff8539`.
+
+User shorthand **CI100** maps to the local CN11 arm **`FIELD_OCI100`**.
+There is no literal `CI100` / `CN11_CI100` adapter in the local experiment tree.
+
+## Identity
+
+| Field | Value |
+| --- | --- |
+| Local arm | `FIELD_OCI100` |
+| Route | `fieldfix_targeted` (`run_20260815T072135Z`) |
+| Train seed | `43` |
+| Train status | `COMPLETE` (attempt 3) |
+| Update mode | `token_balanced_64` (U=64) |
+| Dose | 500,000 non-padding unique clean supervised target tokens |
+| Recipe | Nemotron CP-v2 final-code **400K** + OCI fieldfix_v2 **100K** |
+| Rows | 1,832 (1,298 CP-v2 + 534 OCI fieldfix); reasoning tokens = 0 |
+| Cutoff | 2048 |
+| LoRA | r=64, alpha=128, dropout=0.0, target-only CE, AdamW 1e-5, cosine+warmup |
+| Local adapter | `.../training/FIELD_OCI100/seed_43/attempt3/adapter` |
+| `adapter_manifest_sha256` | `927727c4434afcca19179a7fdcf8266bfbd79e848e062190bc27e6734ea47f40` |
+
+## Public full-LCB diagnostic (1055 tasks, seeds 5227 / 5233 / 5303)
+
+Source: local `PUBLIC_DIAGNOSTIC_AGGREGATE.json` for the fieldfix targeted route.
+**Not** a hidden-dev confirmation and **not** a winner gate.
+
+| Entity | 3-seed mean pass@1 |
+| --- | --- |
+| `FIELD_OCI100` | **24.83%** |
+| `BASE` | 24.39% |
+| `FIELD_FC500_CONTROL` | 23.76% |
+
+Paired task-cluster bootstrap (10,000 replicates):
+
+- vs BASE: **+0.44pp**, 95% CI **[-0.92, +1.77] pp — crosses zero**
+- vs FC500 control: **+1.07pp**, 95% CI **[+0.16, +1.99] pp — excludes zero**
+
+Per-seed pass@1: 5227=25.21%, 5233=24.74%, 5303=24.55%.
+
+## Load with PEFT
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+from peft import PeftModel
+
+base_id = "Qwen/Qwen3-4B-Base"
+base_rev = "906bfd4b4dc7f14ee4320094d8b41684abff8539"
+adapter_id = "modrill/qwen3-4b-cn11-oci100-u64"
+
+tokenizer = AutoTokenizer.from_pretrained(base_id, revision=base_rev, trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained(
+    base_id,
+    revision=base_rev,
+    torch_dtype="bfloat16",
+    device_map="auto",
+    trust_remote_code=True,
+)
+model = PeftModel.from_pretrained(model, adapter_id)
+model.eval()
+```
+
+Do **not** treat this as a merged standalone model. The published `adapter_config.json`
+rewrites the training-time local `base_model_name_or_path` to `Qwen/Qwen3-4B-Base`;
+weights (`adapter_model.safetensors`) are byte-identical to the COMPLETE local adapter.
+
+## What this is not
+
+- Not a winner / not confirmation / not holdout
+- Not D2 / mix / THINK
+- Not a full-weight merge
+- Positive signal vs FC500 is a **final-code mix** result, not a long-CoT / think contract

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/Qwen3-4B-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": 0.0,
+  "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": null,
+  "target_modules": [
+    "down_proj",
+    "v_proj",
+    "k_proj",
+    "gate_proj",
+    "o_proj",
+    "q_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": false,
+  "velora_config": null
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1c104800ee3d705197125c0c13a180375bc5c13b975318d8f1a17719fb12cd4
+size 528550256

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 %}

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": "<|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": false,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}