Upload content from result__CocoRoF__POLAR-Qwen3-0.6b-linq-gist

.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

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 1024,
+  "pooling_mode_cls_token": false,
+  "pooling_mode_mean_tokens": false,
+  "pooling_mode_max_tokens": false,
+  "pooling_mode_mean_sqrt_len_tokens": false,
+  "pooling_mode_weightedmean_tokens": false,
+  "pooling_mode_lasttoken": true,
+  "include_prompt": true
+}

README.md

@@ -0,0 +1,652 @@
+---
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:500000
+- loss:CachedGISTEmbedLoss
+base_model: Qwen/Qwen3-Embedding-0.6B
+widget:
+- source_sentence: scramble z to retrieve negative samples, i.e. z values that should
+    not be predicted by the model.
+  sentences:
+  - "def get_neg_z(self, z, cur_device):\n\n        if self.opt.sampling_method ==\
+    \ 0:\n            \"\"\"carefully selecting negative samples, such that they never\n\
+    \            include positive samples; done individually for every time-step -->\n\
+    \            very slow.\"\"\"\n            offset = 1\n            # generate\
+    \ uncorrelated negative samples by using an individual random\n            # offset\
+    \ for every index\n            rand_neg_idx = torch.arange(z.size(0), device=cur_device)\n\
+    \n            rand_offset = (\n                torch.multinomial(\n          \
+    \          torch.ones(z.size(0) - offset),\n                    self.neg_samples\
+    \ * z.size(0),\n                    replacement=True,\n                )\n   \
+    \             + offset\n            )\n            rand_offset = rand_offset.reshape(self.neg_samples,\
+    \ -1).to(cur_device)\n\n            z_neg = torch.stack(\n                [\n\
+    \                    torch.index_select(\n                        z, 0, (rand_neg_idx\
+    \ + rand_offset[i]) % z.size(0)\n                    )\n                    for\
+    \ i in range(self.neg_samples)\n                ],\n                2,\n     \
+    \       )\n        elif self.opt.sampling_method == 1:\n            \"\"\"randomly\
+    \ selecting from all z values.\n\n            can cause positive samples to be\
+    \ selected as negative\n            samples as well (but probability is <0.1%\
+    \ in our\n            experiments) done once for all time-steps, much faster.\n\
+    \            \"\"\"\n            z = self.broadcast_batch_length(z)\n        \
+    \    z_neg = torch.stack(\n                [\n                    torch.index_select(\n\
+    \                        z, 0, torch.randperm(z.size(0), device=cur_device)\n\
+    \                    )\n                    for i in range(self.neg_samples)\n\
+    \                ],\n                2,\n            )\n            rand_neg_idx\
+    \ = None\n            rand_offset = None\n\n        elif self.opt.sampling_method\
+    \ == 2:\n            \"\"\"randomly selecting from z values within the same sequence.\n\
+    \n            can cause positive samples to be selected as negative\n        \
+    \    samples as well done once for all time-steps, much faster.\n            \"\
+    \"\"\n            z_neg = []\n            channel = z.size(-1)\n            batch_dim\
+    \ = z.size(0)\n            seq_len = z.size(1)\n\n            for _ in range(self.neg_samples):\n\
+    \                rand_perm_index = torch.randperm(\n                    batch_dim\
+    \ * seq_len, device=cur_device\n                ).remainder_(seq_len)\n      \
+    \          rand_perm_index = rand_perm_index.reshape(batch_dim, seq_len)\n   \
+    \             batch_index_offset = (\n                    torch.arange(0, batch_dim,\
+    \ device=cur_device) * seq_len\n                )\n                rand_perm_index\
+    \ += batch_index_offset[:, None]\n\n                z_neg.append(\n          \
+    \          z.reshape(-1, channel)[rand_perm_index.view(-1)].reshape(\n       \
+    \                 batch_dim, seq_len, channel\n                    )\n       \
+    \         )\n\n            z_neg = torch.stack(z_neg, 3)\n\n            rand_neg_idx\
+    \ = None\n            rand_offset = None\n\n        else:\n            raise Exception(\"\
+    Invalid sampling_method option\")\n\n        return z_neg, rand_neg_idx, rand_offset"
+  - 마우스 전지방 3T3-L1세포주에 파이토케미칼을 조건에 따라 24시간 처리한 후 cell viability assay를 수행하였다.
+  - "def _sample_neg(self, assign_result, num_expected):\n        neg_inds = torch.nonzero(assign_result.gt_inds\
+    \ == 0)\n        if neg_inds.numel() != 0:\n            neg_inds = neg_inds.squeeze(1)\n\
+    \        if len(neg_inds) <= num_expected:\n            return neg_inds\n    \
+    \    elif self.neg_balance_thr <= 0:\n            # uniform sampling among all\
+    \ negative samples\n            return random_choice(neg_inds, num_expected)\n\
+    \        else:\n            max_overlaps = assign_result.max_overlaps.cpu().numpy()\n\
+    \            # balance sampling for negative samples\n            neg_set = set(neg_inds.cpu().numpy())\n\
+    \            easy_set = set(\n                np.where(\n                    np.logical_and(max_overlaps\
+    \ >= 0,\n                                   max_overlaps < self.neg_balance_thr))[0])\n\
+    \            hard_set = set(np.where(max_overlaps >= self.neg_balance_thr)[0])\n\
+    \            easy_neg_inds = list(easy_set & neg_set)\n            hard_neg_inds\
+    \ = list(hard_set & neg_set)\n\n            num_expected_hard = int(num_expected\
+    \ * self.neg_hard_fraction)\n            if len(hard_neg_inds) > num_expected_hard:\n\
+    \                sampled_hard_inds = random_choice(hard_neg_inds,\n          \
+    \                                        num_expected_hard)\n            else:\n\
+    \                sampled_hard_inds = np.array(hard_neg_inds, dtype=np.int)\n \
+    \           num_expected_easy = num_expected - len(sampled_hard_inds)\n      \
+    \      if len(easy_neg_inds) > num_expected_easy:\n                sampled_easy_inds\
+    \ = random_choice(easy_neg_inds,\n                                           \
+    \       num_expected_easy)\n            else:\n                sampled_easy_inds\
+    \ = np.array(easy_neg_inds, dtype=np.int)\n            sampled_inds = np.concatenate((sampled_easy_inds,\n\
+    \                                           sampled_hard_inds))\n            if\
+    \ len(sampled_inds) < num_expected:\n                num_extra = num_expected\
+    \ - len(sampled_inds)\n                extra_inds = np.array(list(neg_set - set(sampled_inds)))\n\
+    \                if len(extra_inds) > num_extra:\n                    extra_inds\
+    \ = random_choice(extra_inds, num_extra)\n                sampled_inds = np.concatenate((sampled_inds,\
+    \ extra_inds))\n            sampled_inds = torch.from_numpy(sampled_inds).long().to(\n\
+    \                assign_result.gt_inds.device)\n            return sampled_inds"
+- source_sentence: if you wanted to know the mean and CI of m samples taken at a value
+    x_val
+  sentences:
+  - "def predictSamples(m, x_val, x, y):\n  n = len(x)\n  x_mean = np.mean(x)\n  yhat,\
+    \ upper, lower, stats = regression_with_CI(x, y)\n  # mean at x_val:\n  y_val\
+    \ = stats['a'] + stats['b'] * x_val\n  # standard error of measurement at x_val\
+    \ for m samples:\n  s_m = math.sqrt( stats['MS']*(1./m + 1./n + (x_val - x_mean)**2\
+    \ / \\\n                               stats['x_SS']) )\n  t, stats = studentsT(x,\
+    \ y, stats)\n  critval = returnCritValue(n-2)\n  print('Mean for %i samples at\
+    \ %.3f: %.3f +/- %.3f' \n        %(m, x_val, y_val, critval*s_m))\n  return"
+  - "async def resize_window(self, options):\n        self.log_test(options['desc']\
+    \ if 'desc' in options else\n                      \"Resizing '\" + options['selector']\
+    \ + \"' window.\")\n\n        # await self.page.screenshot({'path': 'preresize.png'})\n\
+    \n        win_hndl = await self.get_handle(options['selector'])\n        pre_resize_bbox\
+    \ = await win_hndl.boundingBox()\n\n        edge_hndl = await self.get_handle(options['selector']\
+    \ + ' div.rsz-' + options['side'])\n        edge_bbox = await edge_hndl.boundingBox()\n\
+    \n        new_x = edge_bbox['x'] + \\\n            resize_dirs[options['side']][0]\
+    \ * options['distance']\n        new_y = edge_bbox['y'] + \\\n            resize_dirs[options['side']][1]\
+    \ * options['distance']\n\n        await edge_hndl.hover()\n        await self.page.mouse.down()\n\
+    \        await self.page.mouse.move(new_x, new_y)\n        await self.page.mouse.up()\n\
+    \n        post_resize_bbox = await win_hndl.boundingBox()\n        dw = post_resize_bbox['width']\
+    \ - pre_resize_bbox['width']\n        dh = post_resize_bbox['height'] - pre_resize_bbox['height']\n\
+    \n        resized = ((dw != 0) or (dh != 0))\n        if options['expectChange']:\n\
+    \            self.assertIsNot(resized, False,\n                             \"\
+    The '\" + options['selector'] + \"' element was NOT resized and should have been.\"\
+    )\n        else:\n            self.assertIsNot(resized, True,\n              \
+    \               \"The '\" + options['selector'] + \"' element was resized and\
+    \ should NOT have been.\")\n\n        # await self.page.screenshot({'path': 'postresize.png'})"
+  - "def _batch_stats(self, x):\n        mu = torch.mean(x, dim=0, keepdim=True)\n\
+    \        var = torch.var(x, dim=0, keepdim=True)\n        return mu, var"
+- source_sentence: 백악관은 도널드 트럼프 미국 대통령이 누구와 통화를 했다고 했어?
+  sentences:
+  - "def __str__(self):\n        return '\\n'.join([self.header, self.sequence, self.header2,\
+    \ \n                array('b', [x + self.qbase for x in self.quality]).tostring()])"
+  - ' 백악관은 16일(현지시간) 미-중 정상이 전날 전화통화를 통해 최근 한반도 상황을 놓고 논의했다며 이같이 전했다.'
+  - 도널드 트럼프 미국 대통령
+- source_sentence: Return an example step handler for the given gym environemtn name,
+    that uses the given config file.
+  sentences:
+  - "def stub_config():\n    defaults = {\n        \"activate_recruiter_on_start\"\
+    : True,\n        \"ad_group\": \"Test ad group\",\n        \"approve_requirement\"\
+    : 95,\n        \"assign_qualifications\": True,\n        \"auto_recruit\": True,\n\
+    \        \"aws_access_key_id\": \"fake aws key\",\n        \"aws_secret_access_key\"\
+    : \"fake aws secret\",\n        \"aws_region\": \"us-east-1\",\n        \"base_payment\"\
+    : 0.01,\n        \"base_port\": 5000,\n        \"browser_exclude_rule\": \"MSIE,\
+    \ mobile, tablet\",\n        \"clock_on\": False,\n        \"contact_email_on_error\"\
+    : \"[email protected]\",\n        \"dallinger_email_address\": \"[email protected]\"\
+    ,\n        \"database_size\": \"standard-0\",\n        \"disable_when_duration_exceeded\"\
+    : True,\n        \"enable_global_experiment_registry\": False,\n        \"redis_size\"\
+    : \"premium-0\",\n        \"dashboard_user\": \"admin\",\n        \"database_url\"\
+    : \"postgresql://postgres@localhost/dallinger\",\n        \"description\": \"\
+    fake HIT description\",\n        \"duration\": 1.0,\n        \"dyno_type\": \"\
+    free\",\n        \"heroku_app_id_root\": \"fake-customid\",\n        \"heroku_auth_token\"\
+    : \"heroku secret\",\n        \"heroku_python_version\": \"3.9.2\",\n        \"\
+    heroku_team\": \"\",\n        \"host\": \"0.0.0.0\",\n        \"id\": \"TEST_EXPERIMENT_UID\"\
+    ,  # This is a significant value; change with caution.\n        \"keywords\":\
+    \ \"kw1, kw2, kw3\",\n        \"lifetime\": 1,\n        \"lock_table_when_creating_participant\"\
+    : True,\n        \"logfile\": \"-\",\n        \"loglevel\": 0,\n        \"mode\"\
+    : \"debug\",\n        \"num_dynos_web\": 1,\n        \"num_dynos_worker\": 1,\n\
+    \        \"organization_name\": \"Monsters University\",\n        \"sentry\":\
+    \ True,\n        \"smtp_host\": \"smtp.fakehost.com:587\",\n        \"smtp_username\"\
+    : \"fake email username\",\n        \"smtp_password\": \"fake email password\"\
+    ,\n        \"threads\": \"1\",\n        \"title\": \"fake experiment title\",\n\
+    \        \"us_only\": True,\n        \"webdriver_type\": \"chrome_headless\",\n\
+    \        \"whimsical\": True,\n        \"replay\": False,\n        \"worker_multiplier\"\
+    : 1.5,\n    }\n    from dallinger.config import Configuration, default_keys\n\n\
+    \    config = Configuration()\n    for key in default_keys:\n        config.register(*key)\n\
+    \    config.extend(defaults.copy())\n    # Patch load() so we don't update any\
+    \ key/value pairs from actual files:\n    config.load = mock.Mock(side_effect=lambda:\
+    \ setattr(config, \"ready\", True))\n    config.ready = True\n\n    return config"
+  - 상부 챔버는 심방(또는 심실)이라고 불리며, 하부 챔버는 심실이라고 불립니다. 두 개의 심방은 심장으로 들어오는 혈액을 받는 챔버 역할을 하며,
+    더 근육질인 심실은 혈액을 심장에서 내보냅니다.
+  - "def get_step_handler_for_gym_env(gym_env_name: str, cfg: Configuration) -> StepRewardDoneHandler:\r\
+    \n\r\n    if gym_env_name == 'Acrobot-v1':\r\n        handler = AcrobotStepHandler(cfg)\r\
+    \n    elif gym_env_name == 'CartPole-v1':\r\n        handler = CartPoleStepHandler(cfg)\r\
+    \n    elif gym_env_name == 'MountainCarContinuous-v0':\r\n        handler = ContinuousMountainCarStepHandler(cfg)\r\
+    \n    elif gym_env_name == 'MountainCar-v0':\r\n        handler = MountainCarStepHandler(cfg)\r\
+    \n    elif gym_env_name == 'Pendulum-v0':\r\n        handler = PendulumStepHandler(cfg)\r\
+    \n    else:\r\n        raise NotImplementedError(f'No support for this gym env:\
+    \ {gym_env_name}')\r\n\r\n    return handler"
+- source_sentence: create list of spiders that obeys the visible projects list, through
+    use of the spider selection menu
+  sentences:
+  - "def create_spiders_list():\n    spiders_lst = [obj for obj in globals().values()\
+    \ if\n                   inspect.isclass(obj) and str(obj).split('.')[2] == 'spiders'\
+    \ and 'BaseSpider' not in str(obj)]\n    visible_projects = find_visible_projects()\n\
+    \    spiders_dict = {i.split('.')[0]: [obj for obj in spiders_lst if i.split('.')[0]\
+    \ in str(obj)] for i in\n                    os.listdir('HousingPriceScraper/HousingPriceScraper/spiders/SpiderGroups')[:-1]\
+    \ if i.split('.')[0] in visible_projects}\n    if len(list(spiders_dict.keys()))\
+    \ > 0:\n        spiders_lst = select_spiders(spiders_dict)\n    else:\n      \
+    \  print('There are no visible projects, got to set_visible_projects to set defaults')\n\
+    \        return False\n    return spiders_lst"
+  - "def game(self, game_id=None, secret=None):\n        if game_id is not None:\n\
+    \            self.game_id = game_id\n\n        if secret is not None:\n      \
+    \      self.secret = secret\n\n        return self.game_id, self.secret"
+  - "def instantiate_pipelines(settings, simulator_settings):\n    pipelines = []\n\
+    \    # lock to manage race parallel processes race conditions \n    lock = Lock()\n\
+    \n    logger.info(\"\\nVALIDATING PIPELINES\\n\")\n    for p_idx, pipeline_settings\
+    \ in enumerate(settings.runs):\n\n        # turn a pipeline off by specifying\
+    \ num_runs as 0\n        num_runs = pipeline_settings.get(\"num_runs\", 0)\n\n\
+    \        # start_idx determines the first dataset name's starting idx\n      \
+    \  start_idx = pipeline_settings.get(\"start_idx\", 0)\n\n        if num_runs:\n\
+    \            logger.info(\"Validating run: {}\\n\".format(p_idx))\n        else:\n\
+    \            logger.info(\"Skipping run: {}\\n\".format(p_idx))\n            \n\
+    \        for idx in range(start_idx, start_idx + num_runs):           \n     \
+    \       logger.info(\"Pipeline sub index: {}\\n\".format(idx))\n            #\
+    \ class factory and instantiate pipeline object\n            Pipeline = pipeline_factory(pipeline_settings[\"\
+    pipeline_name\"])\n            p = Pipeline(pipeline_settings, idx, simulator_settings)\n\
+    \            \n            # give each pipeline an idependent logger\n       \
+    \     log_name = \"dSim_{}\".format(p.pipeline_settings[\"dataset_name\"])\n \
+    \           log_path = os.path.join(p.pipeline_settings[\"outdir\"],\n       \
+    \                             p.pipeline_settings[\"dataset_name\"]+'.log')\n\
+    \            fh = logging.FileHandler(log_path, mode='w')\n            fh.setLevel(logging.DEBUG)\n\
+    \            format = \"%(asctime)-6s: %(name)s - %(levelname)s - %(message)s\"\
+    \n            fmt = logging.Formatter(format)\n            fh.setFormatter(fmt)\n\
+    \            local_logger = logging.getLogger(log_name)\n            local_logger.addHandler(fh)\n\
+    \            logger.info(\"Init local logging: {}\".format(log_path))\n      \
+    \      p.logger = local_logger\n\n            # pipeline/ dataset directory\n\
+    \            p.pipeline_settings[\"lock\"] = lock\n\n            # validate all\
+    \ submodules for each pipeline is ready (use local logger) \n            p.instantiate_modules()\n\
+    \n            # append to list of instantiated pipelines\n            pipelines.append(p)\n\
+    \    return pipelines"
+datasets:
+- CocoRoF/massive_triplet_v3
+pipeline_tag: sentence-similarity
+library_name: sentence-transformers
+---
+
+# SentenceTransformer based on Qwen/Qwen3-Embedding-0.6B
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [Qwen/Qwen3-Embedding-0.6B](https://huggingface.co/Qwen/Qwen3-Embedding-0.6B) on the [massive_triplet_v3](https://huggingface.co/datasets/CocoRoF/massive_triplet_v3) dataset. It maps sentences & paragraphs to a 1024-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
+
+## Model Details
+
+### Model Description
+- **Model Type:** Sentence Transformer
+- **Base model:** [Qwen/Qwen3-Embedding-0.6B](https://huggingface.co/Qwen/Qwen3-Embedding-0.6B) <!-- at revision 744169034862c8eec56628663995004342e4e449 -->
+- **Maximum Sequence Length:** 32768 tokens
+- **Output Dimensionality:** 1024 dimensions
+- **Similarity Function:** Cosine Similarity
+- **Training Dataset:**
+    - [massive_triplet_v3](https://huggingface.co/datasets/CocoRoF/massive_triplet_v3)
+<!-- - **Language:** Unknown -->
+<!-- - **License:** Unknown -->
+
+### Model Sources
+
+- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
+- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
+- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
+
+### Full Model Architecture
+
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 32768, 'do_lower_case': False}) with Transformer model: Qwen3Model 
+  (1): Pooling({'word_embedding_dimension': 1024, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': True, 'include_prompt': True})
+  (2): Normalize()
+)
+```
+
+## Usage
+
+### Direct Usage (Sentence Transformers)
+
+First install the Sentence Transformers library:
+
+```bash
+pip install -U sentence-transformers
+```
+
+Then you can load this model and run inference.
+```python
+from sentence_transformers import SentenceTransformer
+
+# Download from the 🤗 Hub
+model = SentenceTransformer("CocoRoF/POLAR-Qwen3-0.6b-linq-gist")
+# Run inference
+sentences = [
+    'create list of spiders that obeys the visible projects list, through use of the spider selection menu',
+    "def create_spiders_list():\n    spiders_lst = [obj for obj in globals().values() if\n                   inspect.isclass(obj) and str(obj).split('.')[2] == 'spiders' and 'BaseSpider' not in str(obj)]\n    visible_projects = find_visible_projects()\n    spiders_dict = {i.split('.')[0]: [obj for obj in spiders_lst if i.split('.')[0] in str(obj)] for i in\n                    os.listdir('HousingPriceScraper/HousingPriceScraper/spiders/SpiderGroups')[:-1] if i.split('.')[0] in visible_projects}\n    if len(list(spiders_dict.keys())) > 0:\n        spiders_lst = select_spiders(spiders_dict)\n    else:\n        print('There are no visible projects, got to set_visible_projects to set defaults')\n        return False\n    return spiders_lst",
+    'def instantiate_pipelines(settings, simulator_settings):\n    pipelines = []\n    # lock to manage race parallel processes race conditions \n    lock = Lock()\n\n    logger.info("\\nVALIDATING PIPELINES\\n")\n    for p_idx, pipeline_settings in enumerate(settings.runs):\n\n        # turn a pipeline off by specifying num_runs as 0\n        num_runs = pipeline_settings.get("num_runs", 0)\n\n        # start_idx determines the first dataset name\'s starting idx\n        start_idx = pipeline_settings.get("start_idx", 0)\n\n        if num_runs:\n            logger.info("Validating run: {}\\n".format(p_idx))\n        else:\n            logger.info("Skipping run: {}\\n".format(p_idx))\n            \n        for idx in range(start_idx, start_idx + num_runs):           \n            logger.info("Pipeline sub index: {}\\n".format(idx))\n            # class factory and instantiate pipeline object\n            Pipeline = pipeline_factory(pipeline_settings["pipeline_name"])\n            p = Pipeline(pipeline_settings, idx, simulator_settings)\n            \n            # give each pipeline an idependent logger\n            log_name = "dSim_{}".format(p.pipeline_settings["dataset_name"])\n            log_path = os.path.join(p.pipeline_settings["outdir"],\n                                    p.pipeline_settings["dataset_name"]+\'.log\')\n            fh = logging.FileHandler(log_path, mode=\'w\')\n            fh.setLevel(logging.DEBUG)\n            format = "%(asctime)-6s: %(name)s - %(levelname)s - %(message)s"\n            fmt = logging.Formatter(format)\n            fh.setFormatter(fmt)\n            local_logger = logging.getLogger(log_name)\n            local_logger.addHandler(fh)\n            logger.info("Init local logging: {}".format(log_path))\n            p.logger = local_logger\n\n            # pipeline/ dataset directory\n            p.pipeline_settings["lock"] = lock\n\n            # validate all submodules for each pipeline is ready (use local logger) \n            p.instantiate_modules()\n\n            # append to list of instantiated pipelines\n            pipelines.append(p)\n    return pipelines',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 1024]
+
+# Get the similarity scores for the embeddings
+similarities = model.similarity(embeddings, embeddings)
+print(similarities.shape)
+# [3, 3]
+```
+
+<!--
+### Direct Usage (Transformers)
+
+<details><summary>Click to see the direct usage in Transformers</summary>
+
+</details>
+-->
+
+<!--
+### Downstream Usage (Sentence Transformers)
+
+You can finetune this model on your own dataset.
+
+<details><summary>Click to expand</summary>
+
+</details>
+-->
+
+<!--
+### Out-of-Scope Use
+
+*List how the model may foreseeably be misused and address what users ought not to do with the model.*
+-->
+
+<!--
+## Bias, Risks and Limitations
+
+*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
+-->
+
+<!--
+### Recommendations
+
+*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
+-->
+
+## Training Details
+
+### Training Dataset
+
+#### massive_triplet_v3
+
+* Dataset: [massive_triplet_v3](https://huggingface.co/datasets/CocoRoF/massive_triplet_v3) at [51266de](https://huggingface.co/datasets/CocoRoF/massive_triplet_v3/tree/51266de17705934d628da7d4d9f74cc5f7b0b791)
+* Size: 500,000 training samples
+* Columns: <code>query</code>, <code>positive</code>, and <code>negative</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | query                                                                             | positive                                                                             | negative                                                                             |
+  |:--------|:----------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------|
+  | type    | string                                                                            | string                                                                               | string                                                                               |
+  | details | <ul><li>min: 6 tokens</li><li>mean: 22.57 tokens</li><li>max: 67 tokens</li></ul> | <ul><li>min: 8 tokens</li><li>mean: 132.85 tokens</li><li>max: 1160 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 122.89 tokens</li><li>max: 1758 tokens</li></ul> |
+* Samples:
+  | query                                                                                                                        | positive                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                     | negative                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          |
+  |:-----------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+  | <code>방학기간에 소외지역의 청소년을 대상으로 청춘누리 봉사단이 할 수 있는 캠프의 이름은 뭐야</code>                                                               | <code>주요 수상기관 교육기부프로그램 개요<br>4. 대학생 동아리 ｢청춘누리 봉사단｣<br>□ 청춘누리축제<br>◦ (참가대상) 전국 유치원, 초·중·고등학생<br>◦ (활동내역) 대학생들이 운영하는 교육기부활동을 청소년들이 직접 체험해봄으로써 학생들이 사고력, 창의력 향상을 도모하고 자신의 꿈을 펼칠 수 있는 장 마련<br>◦ (주요성과) 대학생들의 교육기부에 대한 전반적인 이해를 돕고 교육 기��� 활동의 우수성 홍보<br>□ 청춘누리봉사단과 함께하는 교육기부(쏙쏙캠프, 함성소리)<br>◦ (참가대상) 전국의 초·중학생<br>◦ (활동내역)<br>- 쏙쏙캠프 : 방학을 이용하여 상대적으로 교육기부 혜택이 적은 소외 지역을 방문하여 창의력 체험, 진로체험 등을 제공, 배움의 기회 균등 및 꿈을 찾아주는 활동 전개<br>- 함성소리 : 학기중 토요일마다 수도권에 있는 청소년 대상으로 꿈을 설계하고 지원하는 활동 전개<br>◦ (주요성과) 소외지역 청소년 대상 배움의 기회를 제공하고 대학생들의 봉사활동을 장려하여 많은 청소년 대상 멘토 활동 전개</code>                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                              | <code>개도국에 IT나눔을 실천한 청년들과 아름다운 동행<br>□ 미래창조과학부(장관 최문기)와 한국정보화진흥원(원장 장광수)은 12월 18일(수) 오후 2시 10분 과천과학관에서 ｢2013년도 월드프렌즈 IT봉사단 귀국보고대회｣(이하, IT봉사단 귀국보고대회)를 개최하였다.<br>o 정부는 2001년부터 현재까지 전 세계 70여개 개도국에 5,158명의 IT봉사단을 파견한 바 있으며, ｢IT봉사단 귀국보고대회｣는 매년 개도국에서 활동하고 온 봉사단원들이 서로의 경험을 공유하고 글로벌 역량을 배양하는 ‘소통'과 ‘협력‘의 장(場)으로 운영되고 있다.<br>※ 월드프렌즈(World Frends Korea, WFK) : 우리나라 해외봉사단사업 통합브랜드<br>□ 이번 ｢IT봉사단 귀국보고대회｣에는 30개국에 파견되었던 552명의 봉사단원 중 약 300여명의 봉사단원이 참석했으며, 윤종록 제2차관과 주한 외교사절(인도네시아 대사, 코스타리카 대사, 네팔 대사 등)이 참석해 세계의 오지를 누비고 온 봉사단원들을 격려했다.<br>o 윤종록 제2차관은 IT봉사단원들에게“귀한경험을 활용하여 대한민국의 이름을 빛내는 사람이 되기를 바란다”는 당부와 함께“정부는 여러분과 같은 젊은이들이 세계를 무대로 능력을 마음껏 발휘할 수 있는 글로벌 플랫폼을 구축하는데 노력할 계획”이라고 덧붙였다.</code>                                                                                                                                                                                                                                                                                                                                                                                                                                                                 |
+  | <code>Loads sensor filters from an Excel file. Both new style XLSX and oldstyle XLS formats are supported.</code>            | <code>def load_sensor_filters_excel(filename, normalise=False, sheet_names=None):<br><br>    sensor_filters = {}<br>    with pd.ExcelFile(filename) as excel_file:<br>        # default is all sheets<br>        if not sheet_names:<br>            sheet_names = excel_file.sheet_names<br><br>        for sheet in sheet_names:<br>            try:<br>                dataframe = excel_file.parse(<br>                    sheet, index_col=0<br>                )  # the sheet as a DataFrame<br>                # OK, we have the data frame. Let's process it...<br>                if not _validate_filter_dataframe(dataframe):<br>                    continue<br><br>                if normalise:<br>                    dataframe = _normalise_dataframe(dataframe)<br><br>                sensor_filters[sheet] = (<br>                    np.array(dataframe.index),<br>                    dataframe.values.transpose(),<br>                )<br><br>            except xlrd.biffh.XLRDError:<br>                continue<br>            # except xlrd.biffh.XLRDError as xlrd_error:<br>            # TODO: log wa...</code> | <code>def convert_csv(fname):<br><br>    # Make sure this is an Excel file.<br>    if (not is_excel_file(fname)):<br><br>        # Not Excel, so no sheets.<br>        return []<br><br>    # Run soffice in listening mode if it is not already running.<br>    run_soffice()<br>    <br>    # TODO: Make sure soffice is running in listening mode.<br>    # <br>    <br>    # Connect to the local LibreOffice server.<br>    context = connect(Socket(HOST, PORT))<br><br>    # Load the Excel sheet.<br>    component = get_component(fname, context)<br><br>    # Iterate on all the sheets in the spreadsheet.<br>    controller = component.getCurrentController()<br>    sheets = component.getSheets()<br>    enumeration = sheets.createEnumeration()<br>    r = []<br>    pos = 0<br>    if sheets.getCount() > 0:<br>        while enumeration.hasMoreElements():<br><br>            # Move to next sheet.<br>            sheet = enumeration.nextElement()<br>            name = sheet.getName()<br>            if (name.count(" ") > 10):<br>                name = name.replace(" ", "")<br>            name = fix_file_name(name)<br> ...</code> |
+  | <code>Create an additional feature to metadata by counting number of occurrences in data, for a specific element_type</code> | <code>def create_count_features(metadata, element_type, data, grp_feat, res_feat, feature_suffix):<br>    feature_name = 'n_'+ element_type + '_modif' + feature_suffix<br>    newfeature = (data.groupby([grp_feat])[res_feat]<br>                  .count()<br>                  .reset_index()<br>                  .fillna(0))<br>    newfeature.columns = [grp_feat, feature_name]<br>    metadata = pd.merge(metadata, newfeature, on=grp_feat, how="outer").fillna(0)<br>    return metadata</code>                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                   | <code>def test(self):<br>        count = Counter()<br>        for example in self.testing_set:<br>            classification = self.classify(example.attributes)<br><br>            if example.CLASS and classification:<br>                count['TP'] += 1<br>            elif not example.CLASS and classification:<br>                count['FP'] += 1<br>            elif not example.CLASS and not classification:<br>                count['TN'] += 1<br>            elif example.CLASS and not classification:<br>                count['FN'] += 1<br>        return count</code>                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                         |
+* Loss: [<code>CachedGISTEmbedLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cachedgistembedloss) with these parameters:
+  ```json
+  {'guide': SentenceTransformer(
+    (0): Transformer({'max_seq_length': 40960, 'do_lower_case': False}) with Transformer model: Qwen3Model 
+    (1): Pooling({'word_embedding_dimension': 4096, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': True, 'include_prompt': True})
+    (2): Normalize()
+  ), 'temperature': 0.01}
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `overwrite_output_dir`: True
+- `per_device_train_batch_size`: 32
+- `per_device_eval_batch_size`: 32
+- `gradient_accumulation_steps`: 16
+- `learning_rate`: 2e-06
+- `weight_decay`: 0.01
+- `adam_beta2`: 0.99
+- `adam_epsilon`: 1e-07
+- `max_grad_norm`: 0.3
+- `num_train_epochs`: 1.0
+- `warmup_ratio`: 0.1
+- `dataloader_num_workers`: 16
+- `hub_model_id`: CocoRoF/POLAR-Qwen3-0.6b-linq-gist
+- `prompts`: ({'query': 'Instruct: Given a web search query, retrieve relevant passages that answer the query\nQuery:', 'document': ''},)
+- `batch_sampler`: no_duplicates
+
+#### All Hyperparameters
+<details><summary>Click to expand</summary>
+
+- `overwrite_output_dir`: True
+- `do_predict`: False
+- `eval_strategy`: no
+- `prediction_loss_only`: True
+- `per_device_train_batch_size`: 32
+- `per_device_eval_batch_size`: 32
+- `per_gpu_train_batch_size`: None
+- `per_gpu_eval_batch_size`: None
+- `gradient_accumulation_steps`: 16
+- `eval_accumulation_steps`: None
+- `torch_empty_cache_steps`: None
+- `learning_rate`: 2e-06
+- `weight_decay`: 0.01
+- `adam_beta1`: 0.9
+- `adam_beta2`: 0.99
+- `adam_epsilon`: 1e-07
+- `max_grad_norm`: 0.3
+- `num_train_epochs`: 1.0
+- `max_steps`: -1
+- `lr_scheduler_type`: linear
+- `lr_scheduler_kwargs`: {}
+- `warmup_ratio`: 0.1
+- `warmup_steps`: 0
+- `log_level`: passive
+- `log_level_replica`: warning
+- `log_on_each_node`: True
+- `logging_nan_inf_filter`: True
+- `save_safetensors`: True
+- `save_on_each_node`: False
+- `save_only_model`: False
+- `restore_callback_states_from_checkpoint`: False
+- `no_cuda`: False
+- `use_cpu`: False
+- `use_mps_device`: False
+- `seed`: 42
+- `data_seed`: None
+- `jit_mode_eval`: False
+- `use_ipex`: False
+- `bf16`: False
+- `fp16`: False
+- `fp16_opt_level`: O1
+- `half_precision_backend`: auto
+- `bf16_full_eval`: False
+- `fp16_full_eval`: False
+- `tf32`: None
+- `local_rank`: 0
+- `ddp_backend`: None
+- `tpu_num_cores`: None
+- `tpu_metrics_debug`: False
+- `debug`: []
+- `dataloader_drop_last`: True
+- `dataloader_num_workers`: 16
+- `dataloader_prefetch_factor`: None
+- `past_index`: -1
+- `disable_tqdm`: False
+- `remove_unused_columns`: True
+- `label_names`: None
+- `load_best_model_at_end`: False
+- `ignore_data_skip`: False
+- `fsdp`: []
+- `fsdp_min_num_params`: 0
+- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
+- `tp_size`: 0
+- `fsdp_transformer_layer_cls_to_wrap`: None
+- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
+- `deepspeed`: None
+- `label_smoothing_factor`: 0.0
+- `optim`: adamw_torch
+- `optim_args`: None
+- `adafactor`: False
+- `group_by_length`: False
+- `length_column_name`: length
+- `ddp_find_unused_parameters`: None
+- `ddp_bucket_cap_mb`: None
+- `ddp_broadcast_buffers`: False
+- `dataloader_pin_memory`: True
+- `dataloader_persistent_workers`: False
+- `skip_memory_metrics`: True
+- `use_legacy_prediction_loop`: False
+- `push_to_hub`: False
+- `resume_from_checkpoint`: None
+- `hub_model_id`: CocoRoF/POLAR-Qwen3-0.6b-linq-gist
+- `hub_strategy`: every_save
+- `hub_private_repo`: None
+- `hub_always_push`: False
+- `gradient_checkpointing`: False
+- `gradient_checkpointing_kwargs`: None
+- `include_inputs_for_metrics`: False
+- `include_for_metrics`: []
+- `eval_do_concat_batches`: True
+- `fp16_backend`: auto
+- `push_to_hub_model_id`: None
+- `push_to_hub_organization`: None
+- `mp_parameters`: 
+- `auto_find_batch_size`: False
+- `full_determinism`: False
+- `torchdynamo`: None
+- `ray_scope`: last
+- `ddp_timeout`: 1800
+- `torch_compile`: False
+- `torch_compile_backend`: None
+- `torch_compile_mode`: None
+- `include_tokens_per_second`: False
+- `include_num_input_tokens_seen`: False
+- `neftune_noise_alpha`: None
+- `optim_target_modules`: None
+- `batch_eval_metrics`: False
+- `eval_on_start`: False
+- `use_liger_kernel`: False
+- `eval_use_gather_object`: False
+- `average_tokens_across_devices`: False
+- `prompts`: ({'query': 'Instruct: Given a web search query, retrieve relevant passages that answer the query\nQuery:', 'document': ''},)
+- `batch_sampler`: no_duplicates
+- `multi_dataset_batch_sampler`: proportional
+
+</details>
+
+### Training Logs
+<details><summary>Click to expand</summary>
+
+| Epoch  | Step | Training Loss |
+|:------:|:----:|:-------------:|
+| 0.0082 | 1    | 2.0699        |
+| 0.0164 | 2    | 1.7826        |
+| 0.0246 | 3    | 1.9799        |
+| 0.0328 | 4    | 8.1569        |
+| 0.0410 | 5    | 4.641         |
+| 0.0492 | 6    | 4.847         |
+| 0.0573 | 7    | 8.2247        |
+| 0.0655 | 8    | 8.9525        |
+| 0.0737 | 9    | 4.2975        |
+| 0.0819 | 10   | 6.3088        |
+| 0.0901 | 11   | 5.6983        |
+| 0.0983 | 12   | 4.3867        |
+| 0.1065 | 13   | 6.1817        |
+| 0.1147 | 14   | 6.0226        |
+| 0.1229 | 15   | 15.2869       |
+| 0.1311 | 16   | 11.8965       |
+| 0.1393 | 17   | 9.4219        |
+| 0.1475 | 18   | 5.9216        |
+| 0.1557 | 19   | 6.5436        |
+| 0.1639 | 20   | 5.4599        |
+| 0.1720 | 21   | 4.6468        |
+| 0.1802 | 22   | 4.9366        |
+| 0.1884 | 23   | 4.5267        |
+| 0.1966 | 24   | 4.9044        |
+| 0.2048 | 25   | 4.9682        |
+| 0.2130 | 26   | 4.1537        |
+| 0.2212 | 27   | 4.0729        |
+| 0.2294 | 28   | 3.9093        |
+| 0.2376 | 29   | 3.3863        |
+| 0.2458 | 30   | 3.9228        |
+| 0.2540 | 31   | 2.8689        |
+| 0.2622 | 32   | 3.3243        |
+| 0.2704 | 33   | 2.7494        |
+| 0.2785 | 34   | 3.108         |
+| 0.2867 | 35   | 3.1585        |
+| 0.2949 | 36   | 3.2985        |
+| 0.3031 | 37   | 2.7137        |
+| 0.3113 | 38   | 2.8327        |
+| 0.3195 | 39   | 2.7932        |
+| 0.3277 | 40   | 3.038         |
+| 0.3359 | 41   | 2.769         |
+| 0.3441 | 42   | 2.7036        |
+| 0.3523 | 43   | 3.1873        |
+| 0.3605 | 44   | 2.5984        |
+| 0.3687 | 45   | 2.6836        |
+| 0.3769 | 46   | 3.0616        |
+| 0.3850 | 47   | 2.87          |
+| 0.3932 | 48   | 2.5225        |
+| 0.4014 | 49   | 2.3775        |
+| 0.4096 | 50   | 2.3407        |
+| 0.4178 | 51   | 2.6313        |
+| 0.4260 | 52   | 2.6966        |
+| 0.4342 | 53   | 2.3673        |
+| 0.4424 | 54   | 2.4391        |
+| 0.4506 | 55   | 2.5654        |
+| 0.4588 | 56   | 2.2967        |
+| 0.4670 | 57   | 2.4656        |
+| 0.4752 | 58   | 2.2497        |
+| 0.4834 | 59   | 2.3793        |
+| 0.4916 | 60   | 2.4427        |
+| 0.4997 | 61   | 2.2327        |
+| 0.5079 | 62   | 2.04          |
+| 0.5161 | 63   | 2.2881        |
+| 0.5243 | 64   | 2.0218        |
+| 0.5325 | 65   | 2.3258        |
+| 0.5407 | 66   | 2.1217        |
+| 0.5489 | 67   | 1.9639        |
+| 0.5571 | 68   | 2.1681        |
+| 0.5653 | 69   | 2.1941        |
+| 0.5735 | 70   | 2.1217        |
+| 0.5817 | 71   | 2.1097        |
+| 0.5899 | 72   | 2.1242        |
+| 0.5981 | 73   | 1.9071        |
+| 0.6062 | 74   | 1.8552        |
+| 0.6144 | 75   | 1.8398        |
+| 0.6226 | 76   | 1.9429        |
+| 0.6308 | 77   | 1.6457        |
+| 0.6390 | 78   | 1.656         |
+| 0.6472 | 79   | 1.6597        |
+| 0.6554 | 80   | 1.8188        |
+| 0.6636 | 81   | 2.0348        |
+| 0.6718 | 82   | 1.9511        |
+| 0.6800 | 83   | 1.8009        |
+| 0.6882 | 84   | 1.8279        |
+| 0.6964 | 85   | 1.7993        |
+| 0.7046 | 86   | 1.782         |
+| 0.7127 | 87   | 1.6168        |
+| 0.7209 | 88   | 1.7357        |
+| 0.7291 | 89   | 1.5588        |
+| 0.7373 | 90   | 1.6574        |
+| 0.7455 | 91   | 1.7124        |
+| 0.7537 | 92   | 1.7205        |
+| 0.7619 | 93   | 1.7439        |
+| 0.7701 | 94   | 1.4042        |
+| 0.7783 | 95   | 1.547         |
+| 0.7865 | 96   | 1.5815        |
+| 0.7947 | 97   | 1.4141        |
+| 0.8029 | 98   | 1.3568        |
+| 0.8111 | 99   | 1.5084        |
+| 0.8193 | 100  | 1.4027        |
+| 0.8274 | 101  | 1.4902        |
+| 0.8356 | 102  | 1.317         |
+| 0.8438 | 103  | 1.8041        |
+| 0.8520 | 104  | 1.4397        |
+| 0.8602 | 105  | 1.3406        |
+| 0.8684 | 106  | 1.5127        |
+| 0.8766 | 107  | 1.2449        |
+| 0.8848 | 108  | 1.4508        |
+| 0.8930 | 109  | 1.4171        |
+| 0.9012 | 110  | 1.626         |
+| 0.9094 | 111  | 1.285         |
+| 0.9176 | 112  | 1.2682        |
+| 0.9258 | 113  | 1.5178        |
+| 0.9339 | 114  | 1.3686        |
+| 0.9421 | 115  | 1.227         |
+| 0.9503 | 116  | 1.3685        |
+| 0.9585 | 117  | 1.3253        |
+| 0.9667 | 118  | 1.0893        |
+| 0.9749 | 119  | 1.1753        |
+| 0.9831 | 120  | 1.252         |
+| 0.9913 | 121  | 1.2304        |
+| 0.9995 | 122  | 1.1111        |
+
+</details>
+
+### Framework Versions
+- Python: 3.11.11
+- Sentence Transformers: 3.4.1
+- Transformers: 4.51.0
+- PyTorch: 2.6.0+cu124
+- Accelerate: 1.6.0
+- Datasets: 3.3.2
+- Tokenizers: 0.21.1
+
+## Citation
+
+### BibTeX
+
+#### Sentence Transformers
+```bibtex
+@inproceedings{reimers-2019-sentence-bert,
+    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
+    author = "Reimers, Nils and Gurevych, Iryna",
+    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
+    month = "11",
+    year = "2019",
+    publisher = "Association for Computational Linguistics",
+    url = "https://arxiv.org/abs/1908.10084",
+}
+```
+
+<!--
+## Glossary
+
+*Clearly define terms in order to be accessible across audiences.*
+-->
+
+<!--
+## Model Card Authors
+
+*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
+-->
+
+<!--
+## Model Card Contact
+
+*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
+-->

added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

config.json

@@ -0,0 +1,30 @@
+{
+  "architectures": [
+    "Qwen3Model"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen3",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float16",
+  "transformers_version": "4.51.0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151669
+}

config_sentence_transformers.json

@@ -0,0 +1,13 @@
+{
+  "prompts": {
+    "query": "Instruct: Given a web search query, retrieve relevant passages that answer the query\nQuery:",
+    "document": ""
+  },
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine",
+  "__version__": {
+    "sentence_transformers": "3.4.1",
+    "transformers": "4.51.0",
+    "pytorch": "2.6.0+cu124"
+  }
+}

metadata.json

@@ -1,7 +1,7 @@
 {
-    "base_model": "Alibaba-NLP/gte-Qwen2-1.5B-instruct",
+    "base_model": "Qwen/Qwen3-Embedding-0.6B",
     "training_method": "Sentence-Transformer",
-    "commit_msg": "polar-qwen-linq",
+    "commit_msg": "polar-qwen3-linq",
     "user_name": "CocoRoF",
     "use_deepspeed": false,
     "use_peft": false,

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1add5d154c89f123c327c75375adb79d9ea82814cb864bb97988856dbd1ae8e9
+size 1191586112

modules.json

@@ -0,0 +1,20 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  },
+  {
+    "idx": 2,
+    "name": "2",
+    "path": "2_Normalize",
+    "type": "sentence_transformers.models.Normalize"
+  }
+]

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 32768,
+  "do_lower_case": false
+}

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_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|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39cd0d96cd958b8ced0082c2d87e5c026454890764b5dccbcb30e125a22cdecc
+size 11423972

tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_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|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0].role == 'system' %}\n        {{- messages[0].content + '\\n\\n' }}\n    {%- endif %}\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>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\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\" }}\n{%- else %}\n    {%- if messages[0].role == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n    {%- set index = (messages|length - 1) - loop.index0 %}\n    {%- if ns.multi_step_tool and message.role == \"user\" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n        {%- set ns.multi_step_tool = false %}\n        {%- set ns.last_query_index = index %}\n    {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {%- set content = message.content %}\n        {%- set reasoning_content = '' %}\n        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}\n            {%- set reasoning_content = message.reasoning_content %}\n        {%- else %}\n            {%- if '</think>' in message.content %}\n                {%- set content = message.content.split('</think>')[-1].lstrip('\\n') %}\n                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n            {%- endif %}\n        {%- endif %}\n        {%- if loop.index0 > ns.last_query_index %}\n            {%- if loop.last or (not loop.last and reasoning_content) %}\n                {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n            {%- else %}\n                {{- '<|im_start|>' + message.role + '\\n' + content }}\n            {%- endif %}\n        {%- else %}\n            {{- '<|im_start|>' + message.role + '\\n' + content }}\n        {%- endif %}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\n{\"name\": \"' }}\n                {{- tool_call.name }}\n                {{- '\", \"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments | tojson }}\n                {%- endif %}\n                {{- '}\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n    {%- if enable_thinking is defined and enable_thinking is false %}\n        {{- '<think>\\n\\n</think>\\n\\n' }}\n    {%- endif %}\n{%- endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4bbee1de95a97a4c232704758368fb90f4825c45f296eb9f9869041ce1ad0c65
+size 5752