Upload folder using huggingface_hub

.gitattributes

@@ -1,35 +1,5 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
 *.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
 *.pt filter=lfs diff=lfs merge=lfs -text
 *.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz 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

PREPARE_LOG.txt

@@ -0,0 +1,13 @@
+source_dir=/dgx1data/aii/tao/m327768/workdir/projects/concept_normalization/outputs/rerank_sft/final
+created_at=2026-03-18 10:26:57
+
+files:
+total 173M
+-rw-r--r-- 1 m327768 acl_dgx1_tao  140 Mar 18 10:26 PREPARE_LOG.txt
+-rw-r--r-- 1 m327768 acl_dgx1_tao 5.3K Mar  2 10:30 README_source.md
+-rw-r--r-- 1 m327768 acl_dgx1_tao 1.2K Mar  2 10:30 adapter_config.json
+-rw-r--r-- 1 m327768 acl_dgx1_tao 167M Mar  2 10:30 adapter_model.safetensors
+-rw-r--r-- 1 m327768 acl_dgx1_tao 4.1K Mar  2 10:30 chat_template.jinja
+-rw-r--r-- 1 m327768 acl_dgx1_tao  11M Mar  2 10:30 tokenizer.json
+-rw-r--r-- 1 m327768 acl_dgx1_tao  664 Mar  2 10:30 tokenizer_config.json
+-rw-r--r-- 1 m327768 acl_dgx1_tao 5.6K Mar  2 10:30 training_args.bin

README.md

@@ -0,0 +1,160 @@
+---
+base_model: Qwen/Qwen3-8B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+  - qwen
+  - qwen3
+  - lora
+  - peft
+  - biomedical-entity-linking
+  - clinical-nlp
+  - concept-normalization
+  - reranking
+  - candidate-ranking
+  - reasoning
+license: other
+---
+
+# Qwen3-8B-LoRA-ContextBioEL-Reranker-SFT
+
+This repository provides a LoRA adapter for Qwen3-8B for the reranker stage of a clinical biomedical entity linking pipeline.
+
+This model reranks a top-10 candidate list using the rewritten term, marked note context, and candidate semantic tags, and outputs the best concept_id. It was trained with supervised fine-tuning (SFT).
+
+## Model type
+
+- Base model: Qwen/Qwen3-8B
+- Adapter type: LoRA
+- Stage: Reranker
+- Training: SFT
+- Task: Context-aware biomedical entity linking reranking
+
+## Intended use
+
+Inputs:
+- `rewritten_term`
+- `context_marked`, where the target mention is explicitly enclosed by `<mention>...</mention>`
+- `candidates`, a top-10 candidate list containing:
+  - `concept_id`
+  - `concept_name`
+  - `semantic_tag`
+
+Output:
+- exactly one selected `concept_id` in the `<answer>...</answer>` block
+
+This model is intended for research use in biomedical entity linking pipelines.
+
+## Important decoding note
+
+This adapter was trained with reasoning-style outputs.
+
+Please:
+- enable thinking
+- do not use greedy decoding
+
+Recommended decoding:
+- `do_sample=True`
+- non-greedy decoding such as temperature/top-p sampling
+- parse the final prediction from the `<answer>...</answer>` span
+
+## Usage example
+
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM
+from peft import PeftModel
+import torch
+import json
+
+base_model_path = "Qwen/Qwen3-8B"
+adapter_path = "Tao-AI-Informatics/Qwen3-8B-LoRA-ContextBioEL-Reranker-SFT"
+
+tokenizer = AutoTokenizer.from_pretrained(base_model_path, trust_remote_code=True)
+base_model = AutoModelForCausalLM.from_pretrained(
+    base_model_path,
+    torch_dtype=torch.bfloat16,
+    device_map="auto",
+    trust_remote_code=True,
+)
+model = PeftModel.from_pretrained(base_model, adapter_path)
+
+cands_json = json.dumps([
+    {"concept_id": "22298006", "concept_name": "myocardial infarction", "semantic_tag": "disorder"},
+    {"concept_id": "57054005", "concept_name": "acute myocardial infarction", "semantic_tag": "disorder"}
+], indent=2)
+
+messages = [
+    {
+        "role": "system",
+        "content": (
+            "You are a clinical concept normalization model that reranks a top-10 candidate list using context and semantic tags.\n\n"
+            "Inputs you will receive:\n"
+            "- rewritten_term\n"
+            "- context_marked with <mention>...</mention>\n"
+            "- candidates: top-10 items (concept_id, concept_name, semantic_tag)\n\n"
+            "Think before answer\n\n"
+            "Output ONLY:\n"
+            "<think>...</think>\n"
+            "<answer>...</answer>\n\n"
+            "In <think>, write a detailed reasoning with these parts:\n"
+            "1) Context interpretation: what the mention means in this note (section cues, negation, experiencer, temporality).\n"
+            "2) Type inference: what semantic type/tag is expected (and why other tags are wrong).\n"
+            "3) Candidate comparison: evaluate multiple candidates. Note over-specific vs too-general, added qualifiers, and tag alignment.\n"
+            "4) Decision: justify the final choice.\n\n"
+            "In <answer>, use exactly one of:\n"
+            "- <answer><concept_id></answer>\n"
+        ),
+    },
+    {
+        "role": "user",
+        "content": (
+            "Task: Choose the best concept_id from candidates.\n\n"
+            "rewritten_term:\nacute myocardial infarction\n\n"
+            "context_marked:\n"
+            "The patient was admitted for <mention>heart attack</mention> yesterday.\n\n"
+            f"candidates (top10; no scores):\n{cands_json}"
+        ),
+    },
+]
+
+text = tokenizer.apply_chat_template(
+    messages,
+    tokenize=False,
+    add_generation_prompt=True,
+)
+
+inputs = tokenizer(text, return_tensors="pt").to(model.device)
+
+with torch.no_grad():
+    outputs = model.generate(
+        **inputs,
+        max_new_tokens=512,
+        do_sample=True,
+        temperature=0.6,
+        top_p=0.95,
+    )
+
+print(tokenizer.decode(outputs[0], skip_special_tokens=False))
+```
+
+## Notes
+
+- This is a LoRA adapter, not a standalone full model.
+
+- The adapter is designed for the rewriting stage, not retrieval by itself.
+
+- In downstream pipelines, the rewritten term is typically passed to a retriever or reranker.
+
+## Limitations
+
+- This model is intended for research use only.
+
+- Performance may vary across ontologies, institutions, and note styles.
+
+- The model should be evaluated carefully before any real-world deployment.
+
+- The final normalized term should be extracted from the <answer>...</answer> block.
+
+## Citation
+
+If you use this model, please cite the associated paper when available.

adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "/dgx1data/aii/tao/tools/models/Qwen/Qwen3-8B/models--Qwen--Qwen3-8B/snapshots/b968826d9c46dd6066d109eabc6255188de91218",
+  "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": [
+    "o_proj",
+    "down_proj",
+    "q_proj",
+    "up_proj",
+    "gate_proj",
+    "k_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:e329767529c206902604a781aaf97d893a67ba5d68b33b74fc62a29749fb9225
+size 174655536

chat_template.jinja

@@ -0,0 +1,89 @@
+{%- 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 message.content is string 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.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" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.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' }}
+        {{- 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 +1,29 @@
+{
+  "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,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}