Upload folder using huggingface_hub

.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 +1,41 @@
+---
+language: [en]
+license: mit
+tags: [conceptual-metaphor, annotation, lakoff, parallel-corpus, lora, qwen2.5]
+base_model: Qwen/Qwen2.5-1.5B-Instruct
+---
+
+# CM-Annotator (English) — Conceptual Metaphor Annotator
+
+LoRA adapter that annotates English sentences with conceptual metaphor spans
+(Lakoff & Johnson tradition) over a curated closed-set inventory (215 entries, based on the
+Master Metaphor List, Lakoff et al. 1991). Outputs strict JSON:
+`{"has_metaphor": bool, "metaphor_spans": [{text, cm_id, cm_name, source_domain, target_domain,
+conventionality, confidence}]}`. Sentences without conceptual metaphors yield empty spans
+(Null-CM negatives are ~30% of training).
+
+## Training (distillation)
+
+- Silver labels distilled from a local LM Studio teacher (qwen3.6-35b-a3b), k=2 self-consistency;
+  only agreeing labels kept. Details: `docs/TRAINING.md`. Silver labels are NOT gold-human labels.
+- Base: `Qwen/Qwen2.5-1.5B-Instruct` · LoRA r=16 α=32 ·
+  completion-only loss · seed=42 · trained 2026-11-07T18:00:10.229852+00:00
+
+## Evaluation (dev vs silver, greedy)
+
+| metric | value |
+|---|---|
+| n_eval | 120 |
+| JSON valid rate | 1.0 |
+| span precision / recall / F1 | 0.0962 / 0.1111 / 0.1031 |
+
+## Usage
+
+Load base + adapter with peft; build prompts exactly as in `service/inference.py`
+(system rules + INVENTORY block + SENTENCE). Trained-on data derives from UM-Corpus (CC BY-NC-ND):
+training data is not redistributed; reproduce via the pipeline in the repository.
+
+## Limitations
+
+Precision bounded by teacher quality (see audit table in docs/TRAINING.md); recall conservative
+on conventional metaphors; confidence not calibrated; Chinese side corpus is mostly simplified script.

adapter_config.json

@@ -0,0 +1,51 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-1.5B-Instruct",
+  "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,
+  "kasa_config": null,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "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": "0.21.2",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "v_proj",
+    "down_proj",
+    "o_proj",
+    "q_proj",
+    "gate_proj",
+    "k_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:c10ce8f6fb3e22ed8ea779fda7773e52cc3163bf08f7614b076161c72364faee
+size 73911112

chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\n# 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' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) 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' }}
+{%- endif %}

metrics.json

@@ -0,0 +1,31 @@
+{
+ "n_eval": 120,
+ "json_valid_rate": 1.0,
+ "span_precision": 0.0962,
+ "span_recall": 0.1111,
+ "span_f1": 0.1031,
+ "null_pred_rate": 0.8083,
+ "null_gold_rate": 0.7917,
+ "lang": "en",
+ "base_model": "Qwen/Qwen2.5-1.5B-Instruct",
+ "train_examples": 1259,
+ "train_minutes": 18.4,
+ "trained_at": "2026-11-07T18:00:10.229852+00:00",
+ "seed": 42,
+ "lora": {
+  "lora_r": 16,
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "target_modules": [
+   "q_proj",
+   "k_proj",
+   "v_proj",
+   "o_proj",
+   "gate_proj",
+   "up_proj",
+   "down_proj"
+  ]
+ },
+ "train_data": "E:\\軟體開發\\CM_annotation\\cm-annotator\\data\\silver\\train_en.jsonl",
+ "dev_data": "E:\\軟體開發\\CM_annotation\\cm-annotator\\data\\silver\\dev_en.jsonl"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73f6356609558c178b6d83e228577139413208ba9aff681f4fd9e5010b3935f0
+size 11421991

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