dkqjrm commited on
Commit
ab28b70
·
verified ·
1 Parent(s): 6aec08d

Add new SentenceTransformer model

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
1_Pooling/config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "word_embedding_dimension": 1024,
3
+ "pooling_mode_cls_token": false,
4
+ "pooling_mode_mean_tokens": false,
5
+ "pooling_mode_max_tokens": false,
6
+ "pooling_mode_mean_sqrt_len_tokens": false,
7
+ "pooling_mode_weightedmean_tokens": false,
8
+ "pooling_mode_lasttoken": true,
9
+ "include_prompt": true
10
+ }
README.md ADDED
@@ -0,0 +1,785 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - sentence-transformers
4
+ - sentence-similarity
5
+ - feature-extraction
6
+ - dense
7
+ - generated_from_trainer
8
+ - dataset_size:1310129
9
+ - loss:MultipleNegativesRankingLoss
10
+ base_model: unsloth/Qwen3-Embedding-0.6B
11
+ widget:
12
+ - source_sentence: 닥터브로너스 [페이셜&바디워시] 닥터브로너스 퓨어 캐스틸 솝 475ml 12종 택1
13
+ sentences:
14
+ - 露得清卸妆油
15
+ - Versace Man Eau Fraiche
16
+ - ピュアキャスティールソープ
17
+ - source_sentence: 베르사체 베르사체 맨오프레쉬 30ml 단품/기획 택1
18
+ sentences:
19
+ - ピーリングジェル
20
+ - Versace Bright
21
+ - Man Eau Fraiche single
22
+ - source_sentence: 랑방 랑방 루머 2 로즈 50ml
23
+ sentences:
24
+ - 캐스틸 솝 475ml
25
+ - 랑방 루머
26
+ - 防晒霜
27
+ - source_sentence: 케어존 케어존 데일리&패밀리 선크림 80ml (SPF50+/PA+++)
28
+ sentences:
29
+ - 伊丽莎白雅顿 100毫升
30
+ - Rumeur Rose perfume
31
+ - 패밀리 선크림
32
+ - source_sentence: 랑방 랑방 메리미 EDP 50ml
33
+ sentences:
34
+ - マリーミー EDP
35
+ - 浪凡 EDP
36
+ - ケアゾーン デイリー日焼け止め
37
+ datasets:
38
+ - dkqjrm/olive-product
39
+ pipeline_tag: sentence-similarity
40
+ library_name: sentence-transformers
41
+ ---
42
+
43
+ # SentenceTransformer based on unsloth/Qwen3-Embedding-0.6B
44
+
45
+ This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [unsloth/Qwen3-Embedding-0.6B](https://huggingface.co/unsloth/Qwen3-Embedding-0.6B) on the [olive-product](https://huggingface.co/datasets/dkqjrm/olive-product) 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.
46
+
47
+ ## Model Details
48
+
49
+ ### Model Description
50
+ - **Model Type:** Sentence Transformer
51
+ - **Base model:** [unsloth/Qwen3-Embedding-0.6B](https://huggingface.co/unsloth/Qwen3-Embedding-0.6B) <!-- at revision f2fddb42505bde9feaf19f0967b01dce52e764c6 -->
52
+ - **Maximum Sequence Length:** 512 tokens
53
+ - **Output Dimensionality:** 1024 dimensions
54
+ - **Similarity Function:** Cosine Similarity
55
+ - **Training Dataset:**
56
+ - [olive-product](https://huggingface.co/datasets/dkqjrm/olive-product)
57
+ <!-- - **Language:** Unknown -->
58
+ <!-- - **License:** Unknown -->
59
+
60
+ ### Model Sources
61
+
62
+ - **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
63
+ - **Repository:** [Sentence Transformers on GitHub](https://github.com/huggingface/sentence-transformers)
64
+ - **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
65
+
66
+ ### Full Model Architecture
67
+
68
+ ```
69
+ SentenceTransformer(
70
+ (0): Transformer({'max_seq_length': 512, 'do_lower_case': False, 'architecture': 'PeftModelForFeatureExtraction'})
71
+ (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})
72
+ (2): Normalize()
73
+ )
74
+ ```
75
+
76
+ ## Usage
77
+
78
+ ### Direct Usage (Sentence Transformers)
79
+
80
+ First install the Sentence Transformers library:
81
+
82
+ ```bash
83
+ pip install -U sentence-transformers
84
+ ```
85
+
86
+ Then you can load this model and run inference.
87
+ ```python
88
+ from sentence_transformers import SentenceTransformer
89
+
90
+ # Download from the 🤗 Hub
91
+ model = SentenceTransformer("dkqjrm/lora_model")
92
+ # Run inference
93
+ sentences = [
94
+ '랑방 랑방 메리미 EDP 50ml',
95
+ '浪凡 EDP',
96
+ 'マリーミー EDP',
97
+ ]
98
+ embeddings = model.encode(sentences)
99
+ print(embeddings.shape)
100
+ # [3, 1024]
101
+
102
+ # Get the similarity scores for the embeddings
103
+ similarities = model.similarity(embeddings, embeddings)
104
+ print(similarities)
105
+ # tensor([[1.0000, 0.6852, 0.6339],
106
+ # [0.6852, 1.0000, 0.3744],
107
+ # [0.6339, 0.3744, 1.0000]])
108
+ ```
109
+
110
+ <!--
111
+ ### Direct Usage (Transformers)
112
+
113
+ <details><summary>Click to see the direct usage in Transformers</summary>
114
+
115
+ </details>
116
+ -->
117
+
118
+ <!--
119
+ ### Downstream Usage (Sentence Transformers)
120
+
121
+ You can finetune this model on your own dataset.
122
+
123
+ <details><summary>Click to expand</summary>
124
+
125
+ </details>
126
+ -->
127
+
128
+ <!--
129
+ ### Out-of-Scope Use
130
+
131
+ *List how the model may foreseeably be misused and address what users ought not to do with the model.*
132
+ -->
133
+
134
+ <!--
135
+ ## Bias, Risks and Limitations
136
+
137
+ *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
138
+ -->
139
+
140
+ <!--
141
+ ### Recommendations
142
+
143
+ *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
144
+ -->
145
+
146
+ ## Training Details
147
+
148
+ ### Training Dataset
149
+
150
+ #### olive-product
151
+
152
+ * Dataset: [olive-product](https://huggingface.co/datasets/dkqjrm/olive-product) at [8d1f081](https://huggingface.co/datasets/dkqjrm/olive-product/tree/8d1f0813721299cb95f6d5cc09b2ef9317e8d06c)
153
+ * Size: 1,310,129 training samples
154
+ * Columns: <code>anchor</code> and <code>positive</code>
155
+ * Approximate statistics based on the first 1000 samples:
156
+ | | anchor | positive |
157
+ |:--------|:-----------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|
158
+ | type | string | string |
159
+ | details | <ul><li>min: 16 tokens</li><li>mean: 25.67 tokens</li><li>max: 47 tokens</li></ul> | <ul><li>min: 2 tokens</li><li>mean: 7.19 tokens</li><li>max: 38 tokens</li></ul> |
160
+ * Samples:
161
+ | anchor | positive |
162
+ |:-----------------------------------------|:-----------------------------------|
163
+ | <code>베르사체 베르사체 브라이트 크리스탈 50ml 택1</code> | <code>베르사체 브라이트 크리스탈 50ml 1</code> |
164
+ | <code>베르사체 베르사체 브라이트 크리스탈 50ml 택1</code> | <code>베르사체 브라이트</code> |
165
+ | <code>베르사체 베르사체 브라이트 크리스탈 50ml 택1</code> | <code>베르사체 크리스탈</code> |
166
+ * Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
167
+ ```json
168
+ {
169
+ "scale": 20.0,
170
+ "similarity_fct": "cos_sim",
171
+ "gather_across_devices": false
172
+ }
173
+ ```
174
+
175
+ ### Training Hyperparameters
176
+ #### Non-Default Hyperparameters
177
+
178
+ - `per_device_train_batch_size`: 32
179
+ - `gradient_accumulation_steps`: 4
180
+ - `learning_rate`: 3e-05
181
+ - `num_train_epochs`: 2
182
+ - `lr_scheduler_type`: constant_with_warmup
183
+ - `warmup_ratio`: 0.03
184
+ - `fp16`: True
185
+ - `push_to_hub`: True
186
+ - `hub_model_id`: dkqjrm/qwen3-embedding-olive-lora
187
+ - `batch_sampler`: no_duplicates
188
+
189
+ #### All Hyperparameters
190
+ <details><summary>Click to expand</summary>
191
+
192
+ - `overwrite_output_dir`: False
193
+ - `do_predict`: False
194
+ - `eval_strategy`: no
195
+ - `prediction_loss_only`: True
196
+ - `per_device_train_batch_size`: 32
197
+ - `per_device_eval_batch_size`: 8
198
+ - `per_gpu_train_batch_size`: None
199
+ - `per_gpu_eval_batch_size`: None
200
+ - `gradient_accumulation_steps`: 4
201
+ - `eval_accumulation_steps`: None
202
+ - `torch_empty_cache_steps`: None
203
+ - `learning_rate`: 3e-05
204
+ - `weight_decay`: 0.0
205
+ - `adam_beta1`: 0.9
206
+ - `adam_beta2`: 0.999
207
+ - `adam_epsilon`: 1e-08
208
+ - `max_grad_norm`: 1.0
209
+ - `num_train_epochs`: 2
210
+ - `max_steps`: -1
211
+ - `lr_scheduler_type`: constant_with_warmup
212
+ - `lr_scheduler_kwargs`: None
213
+ - `warmup_ratio`: 0.03
214
+ - `warmup_steps`: 0
215
+ - `log_level`: passive
216
+ - `log_level_replica`: warning
217
+ - `log_on_each_node`: True
218
+ - `logging_nan_inf_filter`: True
219
+ - `save_safetensors`: True
220
+ - `save_on_each_node`: False
221
+ - `save_only_model`: False
222
+ - `restore_callback_states_from_checkpoint`: False
223
+ - `no_cuda`: False
224
+ - `use_cpu`: False
225
+ - `use_mps_device`: False
226
+ - `seed`: 42
227
+ - `data_seed`: None
228
+ - `jit_mode_eval`: False
229
+ - `bf16`: False
230
+ - `fp16`: True
231
+ - `fp16_opt_level`: O1
232
+ - `half_precision_backend`: auto
233
+ - `bf16_full_eval`: False
234
+ - `fp16_full_eval`: False
235
+ - `tf32`: None
236
+ - `local_rank`: 0
237
+ - `ddp_backend`: None
238
+ - `tpu_num_cores`: None
239
+ - `tpu_metrics_debug`: False
240
+ - `debug`: []
241
+ - `dataloader_drop_last`: False
242
+ - `dataloader_num_workers`: 0
243
+ - `dataloader_prefetch_factor`: None
244
+ - `past_index`: -1
245
+ - `disable_tqdm`: False
246
+ - `remove_unused_columns`: True
247
+ - `label_names`: None
248
+ - `load_best_model_at_end`: False
249
+ - `ignore_data_skip`: False
250
+ - `fsdp`: []
251
+ - `fsdp_min_num_params`: 0
252
+ - `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
253
+ - `fsdp_transformer_layer_cls_to_wrap`: None
254
+ - `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
255
+ - `parallelism_config`: None
256
+ - `deepspeed`: None
257
+ - `label_smoothing_factor`: 0.0
258
+ - `optim`: adamw_torch_fused
259
+ - `optim_args`: None
260
+ - `adafactor`: False
261
+ - `group_by_length`: False
262
+ - `length_column_name`: length
263
+ - `project`: huggingface
264
+ - `trackio_space_id`: trackio
265
+ - `ddp_find_unused_parameters`: None
266
+ - `ddp_bucket_cap_mb`: None
267
+ - `ddp_broadcast_buffers`: False
268
+ - `dataloader_pin_memory`: True
269
+ - `dataloader_persistent_workers`: False
270
+ - `skip_memory_metrics`: True
271
+ - `use_legacy_prediction_loop`: False
272
+ - `push_to_hub`: True
273
+ - `resume_from_checkpoint`: None
274
+ - `hub_model_id`: dkqjrm/qwen3-embedding-olive-lora
275
+ - `hub_strategy`: every_save
276
+ - `hub_private_repo`: None
277
+ - `hub_always_push`: False
278
+ - `hub_revision`: None
279
+ - `gradient_checkpointing`: False
280
+ - `gradient_checkpointing_kwargs`: None
281
+ - `include_inputs_for_metrics`: False
282
+ - `include_for_metrics`: []
283
+ - `eval_do_concat_batches`: True
284
+ - `fp16_backend`: auto
285
+ - `push_to_hub_model_id`: None
286
+ - `push_to_hub_organization`: None
287
+ - `mp_parameters`:
288
+ - `auto_find_batch_size`: False
289
+ - `full_determinism`: False
290
+ - `torchdynamo`: None
291
+ - `ray_scope`: last
292
+ - `ddp_timeout`: 1800
293
+ - `torch_compile`: False
294
+ - `torch_compile_backend`: None
295
+ - `torch_compile_mode`: None
296
+ - `include_tokens_per_second`: False
297
+ - `include_num_input_tokens_seen`: no
298
+ - `neftune_noise_alpha`: None
299
+ - `optim_target_modules`: None
300
+ - `batch_eval_metrics`: False
301
+ - `eval_on_start`: False
302
+ - `use_liger_kernel`: False
303
+ - `liger_kernel_config`: None
304
+ - `eval_use_gather_object`: False
305
+ - `average_tokens_across_devices`: True
306
+ - `prompts`: None
307
+ - `batch_sampler`: no_duplicates
308
+ - `multi_dataset_batch_sampler`: proportional
309
+ - `router_mapping`: {}
310
+ - `learning_rate_mapping`: {}
311
+
312
+ </details>
313
+
314
+ ### Training Logs
315
+ <details><summary>Click to expand</summary>
316
+
317
+ | Epoch | Step | Training Loss |
318
+ |:------:|:-----:|:-------------:|
319
+ | 0.0049 | 50 | 1.5027 |
320
+ | 0.0098 | 100 | 0.8366 |
321
+ | 0.0147 | 150 | 0.6713 |
322
+ | 0.0195 | 200 | 0.5863 |
323
+ | 0.0244 | 250 | 0.53 |
324
+ | 0.0293 | 300 | 0.4562 |
325
+ | 0.0342 | 350 | 0.4061 |
326
+ | 0.0391 | 400 | 0.3899 |
327
+ | 0.0440 | 450 | 0.3417 |
328
+ | 0.0488 | 500 | 0.3367 |
329
+ | 0.0537 | 550 | 0.2948 |
330
+ | 0.0586 | 600 | 0.281 |
331
+ | 0.0635 | 650 | 0.2808 |
332
+ | 0.0684 | 700 | 0.2414 |
333
+ | 0.0733 | 750 | 0.2448 |
334
+ | 0.0782 | 800 | 0.2307 |
335
+ | 0.0830 | 850 | 0.2174 |
336
+ | 0.0879 | 900 | 0.2129 |
337
+ | 0.0928 | 950 | 0.2139 |
338
+ | 0.0977 | 1000 | 0.198 |
339
+ | 0.1026 | 1050 | 0.1797 |
340
+ | 0.1075 | 1100 | 0.1923 |
341
+ | 0.1124 | 1150 | 0.1887 |
342
+ | 0.1172 | 1200 | 0.1789 |
343
+ | 0.1221 | 1250 | 0.1833 |
344
+ | 0.1270 | 1300 | 0.168 |
345
+ | 0.1319 | 1350 | 0.1683 |
346
+ | 0.1368 | 1400 | 0.1536 |
347
+ | 0.1417 | 1450 | 0.1632 |
348
+ | 0.1465 | 1500 | 0.155 |
349
+ | 0.1514 | 1550 | 0.1533 |
350
+ | 0.1563 | 1600 | 0.1442 |
351
+ | 0.1612 | 1650 | 0.1407 |
352
+ | 0.1661 | 1700 | 0.1396 |
353
+ | 0.1710 | 1750 | 0.1388 |
354
+ | 0.1759 | 1800 | 0.1375 |
355
+ | 0.1807 | 1850 | 0.1356 |
356
+ | 0.1856 | 1900 | 0.1335 |
357
+ | 0.1905 | 1950 | 0.1296 |
358
+ | 0.1954 | 2000 | 0.1281 |
359
+ | 0.2003 | 2050 | 0.1379 |
360
+ | 0.2052 | 2100 | 0.1213 |
361
+ | 0.2101 | 2150 | 0.1209 |
362
+ | 0.2149 | 2200 | 0.1142 |
363
+ | 0.2198 | 2250 | 0.1305 |
364
+ | 0.2247 | 2300 | 0.115 |
365
+ | 0.2296 | 2350 | 0.1125 |
366
+ | 0.2345 | 2400 | 0.1159 |
367
+ | 0.2394 | 2450 | 0.1131 |
368
+ | 0.2442 | 2500 | 0.1133 |
369
+ | 0.2491 | 2550 | 0.1126 |
370
+ | 0.2540 | 2600 | 0.109 |
371
+ | 0.2589 | 2650 | 0.1135 |
372
+ | 0.2638 | 2700 | 0.0986 |
373
+ | 0.2687 | 2750 | 0.1127 |
374
+ | 0.2736 | 2800 | 0.114 |
375
+ | 0.2784 | 2850 | 0.1079 |
376
+ | 0.2833 | 2900 | 0.1106 |
377
+ | 0.2882 | 2950 | 0.1112 |
378
+ | 0.2931 | 3000 | 0.1006 |
379
+ | 0.2980 | 3050 | 0.1051 |
380
+ | 0.3029 | 3100 | 0.1105 |
381
+ | 0.3078 | 3150 | 0.1046 |
382
+ | 0.3126 | 3200 | 0.1011 |
383
+ | 0.3175 | 3250 | 0.0962 |
384
+ | 0.3224 | 3300 | 0.1002 |
385
+ | 0.3273 | 3350 | 0.1066 |
386
+ | 0.3322 | 3400 | 0.0907 |
387
+ | 0.3371 | 3450 | 0.0894 |
388
+ | 0.3419 | 3500 | 0.1002 |
389
+ | 0.3468 | 3550 | 0.0894 |
390
+ | 0.3517 | 3600 | 0.0897 |
391
+ | 0.3566 | 3650 | 0.0995 |
392
+ | 0.3615 | 3700 | 0.0949 |
393
+ | 0.3664 | 3750 | 0.0914 |
394
+ | 0.3713 | 3800 | 0.0929 |
395
+ | 0.3761 | 3850 | 0.0841 |
396
+ | 0.3810 | 3900 | 0.0847 |
397
+ | 0.3859 | 3950 | 0.0964 |
398
+ | 0.3908 | 4000 | 0.0937 |
399
+ | 0.3957 | 4050 | 0.0874 |
400
+ | 0.4006 | 4100 | 0.0911 |
401
+ | 0.4055 | 4150 | 0.093 |
402
+ | 0.4103 | 4200 | 0.0867 |
403
+ | 0.4152 | 4250 | 0.0841 |
404
+ | 0.4201 | 4300 | 0.083 |
405
+ | 0.4250 | 4350 | 0.0908 |
406
+ | 0.4299 | 4400 | 0.0829 |
407
+ | 0.4348 | 4450 | 0.0871 |
408
+ | 0.4396 | 4500 | 0.0799 |
409
+ | 0.4445 | 4550 | 0.0777 |
410
+ | 0.4494 | 4600 | 0.0873 |
411
+ | 0.4543 | 4650 | 0.0805 |
412
+ | 0.4592 | 4700 | 0.0851 |
413
+ | 0.4641 | 4750 | 0.0855 |
414
+ | 0.4690 | 4800 | 0.0763 |
415
+ | 0.4738 | 4850 | 0.082 |
416
+ | 0.4787 | 4900 | 0.0699 |
417
+ | 0.4836 | 4950 | 0.0802 |
418
+ | 0.4885 | 5000 | 0.0807 |
419
+ | 0.4934 | 5050 | 0.0746 |
420
+ | 0.4983 | 5100 | 0.0705 |
421
+ | 0.5032 | 5150 | 0.0707 |
422
+ | 0.5080 | 5200 | 0.0827 |
423
+ | 0.5129 | 5250 | 0.0808 |
424
+ | 0.5178 | 5300 | 0.0835 |
425
+ | 0.5227 | 5350 | 0.0782 |
426
+ | 0.5276 | 5400 | 0.0698 |
427
+ | 0.5325 | 5450 | 0.0755 |
428
+ | 0.5373 | 5500 | 0.0743 |
429
+ | 0.5422 | 5550 | 0.0744 |
430
+ | 0.5471 | 5600 | 0.0724 |
431
+ | 0.5520 | 5650 | 0.0781 |
432
+ | 0.5569 | 5700 | 0.0712 |
433
+ | 0.5618 | 5750 | 0.0738 |
434
+ | 0.5667 | 5800 | 0.0692 |
435
+ | 0.5715 | 5850 | 0.0747 |
436
+ | 0.5764 | 5900 | 0.0686 |
437
+ | 0.5813 | 5950 | 0.0761 |
438
+ | 0.5862 | 6000 | 0.0696 |
439
+ | 0.5911 | 6050 | 0.0681 |
440
+ | 0.5960 | 6100 | 0.0714 |
441
+ | 0.6008 | 6150 | 0.0682 |
442
+ | 0.6057 | 6200 | 0.0746 |
443
+ | 0.6106 | 6250 | 0.0638 |
444
+ | 0.6155 | 6300 | 0.0672 |
445
+ | 0.6204 | 6350 | 0.0727 |
446
+ | 0.6253 | 6400 | 0.0711 |
447
+ | 0.6302 | 6450 | 0.0716 |
448
+ | 0.6350 | 6500 | 0.0609 |
449
+ | 0.6399 | 6550 | 0.066 |
450
+ | 0.6448 | 6600 | 0.0709 |
451
+ | 0.6497 | 6650 | 0.0687 |
452
+ | 0.6546 | 6700 | 0.0629 |
453
+ | 0.6595 | 6750 | 0.0693 |
454
+ | 0.6644 | 6800 | 0.0678 |
455
+ | 0.6692 | 6850 | 0.0612 |
456
+ | 0.6741 | 6900 | 0.0653 |
457
+ | 0.6790 | 6950 | 0.0642 |
458
+ | 0.6839 | 7000 | 0.068 |
459
+ | 0.6888 | 7050 | 0.0626 |
460
+ | 0.6937 | 7100 | 0.0623 |
461
+ | 0.6985 | 7150 | 0.0622 |
462
+ | 0.7034 | 7200 | 0.0661 |
463
+ | 0.7083 | 7250 | 0.0597 |
464
+ | 0.7132 | 7300 | 0.0584 |
465
+ | 0.7181 | 7350 | 0.0595 |
466
+ | 0.7230 | 7400 | 0.0647 |
467
+ | 0.7279 | 7450 | 0.0664 |
468
+ | 0.7327 | 7500 | 0.0682 |
469
+ | 0.7376 | 7550 | 0.0621 |
470
+ | 0.7425 | 7600 | 0.0603 |
471
+ | 0.7474 | 7650 | 0.0617 |
472
+ | 0.7523 | 7700 | 0.0554 |
473
+ | 0.7572 | 7750 | 0.056 |
474
+ | 0.7621 | 7800 | 0.0594 |
475
+ | 0.7669 | 7850 | 0.0594 |
476
+ | 0.7718 | 7900 | 0.0618 |
477
+ | 0.7767 | 7950 | 0.0638 |
478
+ | 0.7816 | 8000 | 0.0556 |
479
+ | 0.7865 | 8050 | 0.0608 |
480
+ | 0.7914 | 8100 | 0.0624 |
481
+ | 0.7962 | 8150 | 0.0621 |
482
+ | 0.8011 | 8200 | 0.0653 |
483
+ | 0.8060 | 8250 | 0.0648 |
484
+ | 0.8109 | 8300 | 0.0533 |
485
+ | 0.8158 | 8350 | 0.0584 |
486
+ | 0.8207 | 8400 | 0.0552 |
487
+ | 0.8256 | 8450 | 0.066 |
488
+ | 0.8304 | 8500 | 0.0616 |
489
+ | 0.8353 | 8550 | 0.0648 |
490
+ | 0.8402 | 8600 | 0.0618 |
491
+ | 0.8451 | 8650 | 0.0587 |
492
+ | 0.8500 | 8700 | 0.0616 |
493
+ | 0.8549 | 8750 | 0.0544 |
494
+ | 0.8598 | 8800 | 0.0637 |
495
+ | 0.8646 | 8850 | 0.0621 |
496
+ | 0.8695 | 8900 | 0.0574 |
497
+ | 0.8744 | 8950 | 0.0587 |
498
+ | 0.8793 | 9000 | 0.0606 |
499
+ | 0.8842 | 9050 | 0.0595 |
500
+ | 0.8891 | 9100 | 0.0627 |
501
+ | 0.8939 | 9150 | 0.0564 |
502
+ | 0.8988 | 9200 | 0.0542 |
503
+ | 0.9037 | 9250 | 0.0538 |
504
+ | 0.9086 | 9300 | 0.055 |
505
+ | 0.9135 | 9350 | 0.0562 |
506
+ | 0.9184 | 9400 | 0.0547 |
507
+ | 0.9233 | 9450 | 0.0514 |
508
+ | 0.9281 | 9500 | 0.0574 |
509
+ | 0.9330 | 9550 | 0.0503 |
510
+ | 0.9379 | 9600 | 0.0647 |
511
+ | 0.9428 | 9650 | 0.0554 |
512
+ | 0.9477 | 9700 | 0.0532 |
513
+ | 0.9526 | 9750 | 0.056 |
514
+ | 0.9575 | 9800 | 0.0554 |
515
+ | 0.9623 | 9850 | 0.0535 |
516
+ | 0.9672 | 9900 | 0.0553 |
517
+ | 0.9721 | 9950 | 0.0581 |
518
+ | 0.9770 | 10000 | 0.05 |
519
+ | 0.9819 | 10050 | 0.0571 |
520
+ | 0.9868 | 10100 | 0.0534 |
521
+ | 0.9916 | 10150 | 0.0462 |
522
+ | 0.9965 | 10200 | 0.0508 |
523
+ | 1.0014 | 10250 | 0.0506 |
524
+ | 1.0063 | 10300 | 0.0548 |
525
+ | 1.0111 | 10350 | 0.0476 |
526
+ | 1.0160 | 10400 | 0.0504 |
527
+ | 1.0209 | 10450 | 0.0433 |
528
+ | 1.0258 | 10500 | 0.0499 |
529
+ | 1.0307 | 10550 | 0.0453 |
530
+ | 1.0356 | 10600 | 0.0494 |
531
+ | 1.0404 | 10650 | 0.0456 |
532
+ | 1.0453 | 10700 | 0.0499 |
533
+ | 1.0502 | 10750 | 0.049 |
534
+ | 1.0551 | 10800 | 0.0464 |
535
+ | 1.0600 | 10850 | 0.0483 |
536
+ | 1.0649 | 10900 | 0.0487 |
537
+ | 1.0698 | 10950 | 0.0461 |
538
+ | 1.0746 | 11000 | 0.0433 |
539
+ | 1.0795 | 11050 | 0.0474 |
540
+ | 1.0844 | 11100 | 0.0485 |
541
+ | 1.0893 | 11150 | 0.0462 |
542
+ | 1.0942 | 11200 | 0.0396 |
543
+ | 1.0991 | 11250 | 0.0479 |
544
+ | 1.1040 | 11300 | 0.0471 |
545
+ | 1.1088 | 11350 | 0.0473 |
546
+ | 1.1137 | 11400 | 0.0482 |
547
+ | 1.1186 | 11450 | 0.0412 |
548
+ | 1.1235 | 11500 | 0.0455 |
549
+ | 1.1284 | 11550 | 0.0448 |
550
+ | 1.1333 | 11600 | 0.0531 |
551
+ | 1.1381 | 11650 | 0.0466 |
552
+ | 1.1430 | 11700 | 0.0527 |
553
+ | 1.1479 | 11750 | 0.0465 |
554
+ | 1.1528 | 11800 | 0.0536 |
555
+ | 1.1577 | 11850 | 0.0474 |
556
+ | 1.1626 | 11900 | 0.0515 |
557
+ | 1.1675 | 11950 | 0.0429 |
558
+ | 1.1723 | 12000 | 0.0464 |
559
+ | 1.1772 | 12050 | 0.0463 |
560
+ | 1.1821 | 12100 | 0.0491 |
561
+ | 1.1870 | 12150 | 0.0433 |
562
+ | 1.1919 | 12200 | 0.0466 |
563
+ | 1.1968 | 12250 | 0.0522 |
564
+ | 1.2017 | 12300 | 0.0463 |
565
+ | 1.2065 | 12350 | 0.0528 |
566
+ | 1.2114 | 12400 | 0.0451 |
567
+ | 1.2163 | 12450 | 0.0449 |
568
+ | 1.2212 | 12500 | 0.0475 |
569
+ | 1.2261 | 12550 | 0.0468 |
570
+ | 1.2310 | 12600 | 0.0456 |
571
+ | 1.2358 | 12650 | 0.0411 |
572
+ | 1.2407 | 12700 | 0.0439 |
573
+ | 1.2456 | 12750 | 0.0434 |
574
+ | 1.2505 | 12800 | 0.0475 |
575
+ | 1.2554 | 12850 | 0.0468 |
576
+ | 1.2603 | 12900 | 0.046 |
577
+ | 1.2652 | 12950 | 0.0467 |
578
+ | 1.2700 | 13000 | 0.0429 |
579
+ | 1.2749 | 13050 | 0.0437 |
580
+ | 1.2798 | 13100 | 0.048 |
581
+ | 1.2847 | 13150 | 0.0429 |
582
+ | 1.2896 | 13200 | 0.0507 |
583
+ | 1.2945 | 13250 | 0.0426 |
584
+ | 1.2994 | 13300 | 0.0408 |
585
+ | 1.3042 | 13350 | 0.0468 |
586
+ | 1.3091 | 13400 | 0.0389 |
587
+ | 1.3140 | 13450 | 0.0458 |
588
+ | 1.3189 | 13500 | 0.044 |
589
+ | 1.3238 | 13550 | 0.0417 |
590
+ | 1.3287 | 13600 | 0.0437 |
591
+ | 1.3335 | 13650 | 0.0427 |
592
+ | 1.3384 | 13700 | 0.0444 |
593
+ | 1.3433 | 13750 | 0.0496 |
594
+ | 1.3482 | 13800 | 0.0443 |
595
+ | 1.3531 | 13850 | 0.0421 |
596
+ | 1.3580 | 13900 | 0.0431 |
597
+ | 1.3629 | 13950 | 0.0474 |
598
+ | 1.3677 | 14000 | 0.0423 |
599
+ | 1.3726 | 14050 | 0.0437 |
600
+ | 1.3775 | 14100 | 0.038 |
601
+ | 1.3824 | 14150 | 0.0457 |
602
+ | 1.3873 | 14200 | 0.0459 |
603
+ | 1.3922 | 14250 | 0.0421 |
604
+ | 1.3970 | 14300 | 0.0482 |
605
+ | 1.4019 | 14350 | 0.0496 |
606
+ | 1.4068 | 14400 | 0.0436 |
607
+ | 1.4117 | 14450 | 0.0437 |
608
+ | 1.4166 | 14500 | 0.0463 |
609
+ | 1.4215 | 14550 | 0.04 |
610
+ | 1.4264 | 14600 | 0.046 |
611
+ | 1.4312 | 14650 | 0.0451 |
612
+ | 1.4361 | 14700 | 0.044 |
613
+ | 1.4410 | 14750 | 0.0436 |
614
+ | 1.4459 | 14800 | 0.0411 |
615
+ | 1.4508 | 14850 | 0.0453 |
616
+ | 1.4557 | 14900 | 0.0402 |
617
+ | 1.4606 | 14950 | 0.0437 |
618
+ | 1.4654 | 15000 | 0.0451 |
619
+ | 1.4703 | 15050 | 0.0454 |
620
+ | 1.4752 | 15100 | 0.0433 |
621
+ | 1.4801 | 15150 | 0.0399 |
622
+ | 1.4850 | 15200 | 0.0389 |
623
+ | 1.4899 | 15250 | 0.0451 |
624
+ | 1.4947 | 15300 | 0.0417 |
625
+ | 1.4996 | 15350 | 0.0411 |
626
+ | 1.5045 | 15400 | 0.0415 |
627
+ | 1.5094 | 15450 | 0.044 |
628
+ | 1.5143 | 15500 | 0.045 |
629
+ | 1.5192 | 15550 | 0.0414 |
630
+ | 1.5241 | 15600 | 0.0439 |
631
+ | 1.5289 | 15650 | 0.0381 |
632
+ | 1.5338 | 15700 | 0.0425 |
633
+ | 1.5387 | 15750 | 0.0439 |
634
+ | 1.5436 | 15800 | 0.0405 |
635
+ | 1.5485 | 15850 | 0.0407 |
636
+ | 1.5534 | 15900 | 0.04 |
637
+ | 1.5583 | 15950 | 0.0404 |
638
+ | 1.5631 | 16000 | 0.0392 |
639
+ | 1.5680 | 16050 | 0.0432 |
640
+ | 1.5729 | 16100 | 0.0374 |
641
+ | 1.5778 | 16150 | 0.044 |
642
+ | 1.5827 | 16200 | 0.0429 |
643
+ | 1.5876 | 16250 | 0.0394 |
644
+ | 1.5924 | 16300 | 0.0446 |
645
+ | 1.5973 | 16350 | 0.0389 |
646
+ | 1.6022 | 16400 | 0.0429 |
647
+ | 1.6071 | 16450 | 0.0442 |
648
+ | 1.6120 | 16500 | 0.0394 |
649
+ | 1.6169 | 16550 | 0.0403 |
650
+ | 1.6218 | 16600 | 0.0414 |
651
+ | 1.6266 | 16650 | 0.0386 |
652
+ | 1.6315 | 16700 | 0.0401 |
653
+ | 1.6364 | 16750 | 0.0415 |
654
+ | 1.6413 | 16800 | 0.0427 |
655
+ | 1.6462 | 16850 | 0.0412 |
656
+ | 1.6511 | 16900 | 0.0404 |
657
+ | 1.6560 | 16950 | 0.0402 |
658
+ | 1.6608 | 17000 | 0.0394 |
659
+ | 1.6657 | 17050 | 0.0429 |
660
+ | 1.6706 | 17100 | 0.0452 |
661
+ | 1.6755 | 17150 | 0.0438 |
662
+ | 1.6804 | 17200 | 0.0433 |
663
+ | 1.6853 | 17250 | 0.0393 |
664
+ | 1.6901 | 17300 | 0.0405 |
665
+ | 1.6950 | 17350 | 0.044 |
666
+ | 1.6999 | 17400 | 0.042 |
667
+ | 1.7048 | 17450 | 0.0401 |
668
+ | 1.7097 | 17500 | 0.0417 |
669
+ | 1.7146 | 17550 | 0.0351 |
670
+ | 1.7195 | 17600 | 0.0367 |
671
+ | 1.7243 | 17650 | 0.0436 |
672
+ | 1.7292 | 17700 | 0.0392 |
673
+ | 1.7341 | 17750 | 0.04 |
674
+ | 1.7390 | 17800 | 0.0415 |
675
+ | 1.7439 | 17850 | 0.0418 |
676
+ | 1.7488 | 17900 | 0.0366 |
677
+ | 1.7537 | 17950 | 0.0433 |
678
+ | 1.7585 | 18000 | 0.0391 |
679
+ | 1.7634 | 18050 | 0.0377 |
680
+ | 1.7683 | 18100 | 0.0398 |
681
+ | 1.7732 | 18150 | 0.0396 |
682
+ | 1.7781 | 18200 | 0.0404 |
683
+ | 1.7830 | 18250 | 0.0405 |
684
+ | 1.7878 | 18300 | 0.0381 |
685
+ | 1.7927 | 18350 | 0.04 |
686
+ | 1.7976 | 18400 | 0.0404 |
687
+ | 1.8025 | 18450 | 0.0348 |
688
+ | 1.8074 | 18500 | 0.0397 |
689
+ | 1.8123 | 18550 | 0.042 |
690
+ | 1.8172 | 18600 | 0.0454 |
691
+ | 1.8220 | 18650 | 0.0384 |
692
+ | 1.8269 | 18700 | 0.0387 |
693
+ | 1.8318 | 18750 | 0.042 |
694
+ | 1.8367 | 18800 | 0.0413 |
695
+ | 1.8416 | 18850 | 0.0403 |
696
+ | 1.8465 | 18900 | 0.0417 |
697
+ | 1.8514 | 18950 | 0.0386 |
698
+ | 1.8562 | 19000 | 0.0417 |
699
+ | 1.8611 | 19050 | 0.0396 |
700
+ | 1.8660 | 19100 | 0.039 |
701
+ | 1.8709 | 19150 | 0.0403 |
702
+ | 1.8758 | 19200 | 0.0402 |
703
+ | 1.8807 | 19250 | 0.044 |
704
+ | 1.8855 | 19300 | 0.0413 |
705
+ | 1.8904 | 19350 | 0.0379 |
706
+ | 1.8953 | 19400 | 0.042 |
707
+ | 1.9002 | 19450 | 0.0389 |
708
+ | 1.9051 | 19500 | 0.0399 |
709
+ | 1.9100 | 19550 | 0.0405 |
710
+ | 1.9149 | 19600 | 0.0414 |
711
+ | 1.9197 | 19650 | 0.0406 |
712
+ | 1.9246 | 19700 | 0.037 |
713
+ | 1.9295 | 19750 | 0.0406 |
714
+ | 1.9344 | 19800 | 0.0433 |
715
+ | 1.9393 | 19850 | 0.0357 |
716
+ | 1.9442 | 19900 | 0.038 |
717
+ | 1.9490 | 19950 | 0.0444 |
718
+ | 1.9539 | 20000 | 0.0406 |
719
+ | 1.9588 | 20050 | 0.0343 |
720
+ | 1.9637 | 20100 | 0.0414 |
721
+ | 1.9686 | 20150 | 0.0359 |
722
+ | 1.9735 | 20200 | 0.0421 |
723
+ | 1.9784 | 20250 | 0.0352 |
724
+ | 1.9832 | 20300 | 0.0406 |
725
+ | 1.9881 | 20350 | 0.0403 |
726
+ | 1.9930 | 20400 | 0.0396 |
727
+ | 1.9979 | 20450 | 0.0378 |
728
+
729
+ </details>
730
+
731
+ ### Framework Versions
732
+ - Python: 3.12.12
733
+ - Sentence Transformers: 5.2.1
734
+ - Transformers: 4.57.6
735
+ - PyTorch: 2.10.0+cu128
736
+ - Accelerate: 1.12.0
737
+ - Datasets: 4.3.0
738
+ - Tokenizers: 0.22.2
739
+
740
+ ## Citation
741
+
742
+ ### BibTeX
743
+
744
+ #### Sentence Transformers
745
+ ```bibtex
746
+ @inproceedings{reimers-2019-sentence-bert,
747
+ title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
748
+ author = "Reimers, Nils and Gurevych, Iryna",
749
+ booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
750
+ month = "11",
751
+ year = "2019",
752
+ publisher = "Association for Computational Linguistics",
753
+ url = "https://arxiv.org/abs/1908.10084",
754
+ }
755
+ ```
756
+
757
+ #### MultipleNegativesRankingLoss
758
+ ```bibtex
759
+ @misc{henderson2017efficient,
760
+ title={Efficient Natural Language Response Suggestion for Smart Reply},
761
+ author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
762
+ year={2017},
763
+ eprint={1705.00652},
764
+ archivePrefix={arXiv},
765
+ primaryClass={cs.CL}
766
+ }
767
+ ```
768
+
769
+ <!--
770
+ ## Glossary
771
+
772
+ *Clearly define terms in order to be accessible across audiences.*
773
+ -->
774
+
775
+ <!--
776
+ ## Model Card Authors
777
+
778
+ *Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
779
+ -->
780
+
781
+ <!--
782
+ ## Model Card Contact
783
+
784
+ *Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
785
+ -->
adapter_config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": {
6
+ "base_model_class": "Qwen3Model",
7
+ "parent_library": "transformers.models.qwen3.modeling_qwen3",
8
+ "unsloth_fixed": true
9
+ },
10
+ "base_model_name_or_path": "unsloth/Qwen3-Embedding-0.6B",
11
+ "bias": "none",
12
+ "corda_config": null,
13
+ "ensure_weight_tying": false,
14
+ "eva_config": null,
15
+ "exclude_modules": null,
16
+ "fan_in_fan_out": false,
17
+ "inference_mode": true,
18
+ "init_lora_weights": true,
19
+ "layer_replication": null,
20
+ "layers_pattern": null,
21
+ "layers_to_transform": null,
22
+ "loftq_config": {},
23
+ "lora_alpha": 128,
24
+ "lora_bias": false,
25
+ "lora_dropout": 0,
26
+ "megatron_config": null,
27
+ "megatron_core": "megatron.core",
28
+ "modules_to_save": null,
29
+ "peft_type": "LORA",
30
+ "peft_version": "0.18.1",
31
+ "qalora_group_size": 16,
32
+ "r": 64,
33
+ "rank_pattern": {},
34
+ "revision": null,
35
+ "target_modules": [
36
+ "gate_proj",
37
+ "o_proj",
38
+ "q_proj",
39
+ "k_proj",
40
+ "v_proj",
41
+ "up_proj",
42
+ "down_proj"
43
+ ],
44
+ "target_parameters": null,
45
+ "task_type": "FEATURE_EXTRACTION",
46
+ "trainable_token_indices": null,
47
+ "use_dora": false,
48
+ "use_qalora": false,
49
+ "use_rslora": false
50
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e36c44d6a67b847867b4fe98a805aebbb4e65aed84a8e98fbe9de930d710eacd
3
+ size 161530808
added_tokens.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</think>": 151668,
3
+ "</tool_call>": 151658,
4
+ "</tool_response>": 151666,
5
+ "<think>": 151667,
6
+ "<tool_call>": 151657,
7
+ "<tool_response>": 151665,
8
+ "<|box_end|>": 151649,
9
+ "<|box_start|>": 151648,
10
+ "<|endoftext|>": 151643,
11
+ "<|file_sep|>": 151664,
12
+ "<|fim_middle|>": 151660,
13
+ "<|fim_pad|>": 151662,
14
+ "<|fim_prefix|>": 151659,
15
+ "<|fim_suffix|>": 151661,
16
+ "<|im_end|>": 151645,
17
+ "<|im_start|>": 151644,
18
+ "<|image_pad|>": 151655,
19
+ "<|object_ref_end|>": 151647,
20
+ "<|object_ref_start|>": 151646,
21
+ "<|quad_end|>": 151651,
22
+ "<|quad_start|>": 151650,
23
+ "<|repo_name|>": 151663,
24
+ "<|video_pad|>": 151656,
25
+ "<|vision_end|>": 151653,
26
+ "<|vision_pad|>": 151654,
27
+ "<|vision_start|>": 151652
28
+ }
chat_template.jinja ADDED
@@ -0,0 +1,85 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0].role == 'system' %}
4
+ {{- messages[0].content + '\n\n' }}
5
+ {%- endif %}
6
+ {{- "# 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>" }}
7
+ {%- for tool in tools %}
8
+ {{- "\n" }}
9
+ {{- tool | tojson }}
10
+ {%- endfor %}
11
+ {{- "\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" }}
12
+ {%- else %}
13
+ {%- if messages[0].role == 'system' %}
14
+ {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
15
+ {%- endif %}
16
+ {%- endif %}
17
+ {%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
18
+ {%- for message in messages[::-1] %}
19
+ {%- set index = (messages|length - 1) - loop.index0 %}
20
+ {%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
21
+ {%- set ns.multi_step_tool = false %}
22
+ {%- set ns.last_query_index = index %}
23
+ {%- endif %}
24
+ {%- endfor %}
25
+ {%- for message in messages %}
26
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
27
+ {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
28
+ {%- elif message.role == "assistant" %}
29
+ {%- set content = message.content %}
30
+ {%- set reasoning_content = '' %}
31
+ {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
32
+ {%- set reasoning_content = message.reasoning_content %}
33
+ {%- else %}
34
+ {%- if '</think>' in message.content %}
35
+ {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
36
+ {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
37
+ {%- endif %}
38
+ {%- endif %}
39
+ {%- if loop.index0 > ns.last_query_index %}
40
+ {%- if loop.last or (not loop.last and reasoning_content) %}
41
+ {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
42
+ {%- else %}
43
+ {{- '<|im_start|>' + message.role + '\n' + content }}
44
+ {%- endif %}
45
+ {%- else %}
46
+ {{- '<|im_start|>' + message.role + '\n' + content }}
47
+ {%- endif %}
48
+ {%- if message.tool_calls %}
49
+ {%- for tool_call in message.tool_calls %}
50
+ {%- if (loop.first and content) or (not loop.first) %}
51
+ {{- '\n' }}
52
+ {%- endif %}
53
+ {%- if tool_call.function %}
54
+ {%- set tool_call = tool_call.function %}
55
+ {%- endif %}
56
+ {{- '<tool_call>\n{"name": "' }}
57
+ {{- tool_call.name }}
58
+ {{- '", "arguments": ' }}
59
+ {%- if tool_call.arguments is string %}
60
+ {{- tool_call.arguments }}
61
+ {%- else %}
62
+ {{- tool_call.arguments | tojson }}
63
+ {%- endif %}
64
+ {{- '}\n</tool_call>' }}
65
+ {%- endfor %}
66
+ {%- endif %}
67
+ {{- '<|im_end|>\n' }}
68
+ {%- elif message.role == "tool" %}
69
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
70
+ {{- '<|im_start|>user' }}
71
+ {%- endif %}
72
+ {{- '\n<tool_response>\n' }}
73
+ {{- message.content }}
74
+ {{- '\n</tool_response>' }}
75
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
76
+ {{- '<|im_end|>\n' }}
77
+ {%- endif %}
78
+ {%- endif %}
79
+ {%- endfor %}
80
+ {%- if add_generation_prompt %}
81
+ {{- '<|im_start|>assistant\n' }}
82
+ {%- if enable_thinking is defined and enable_thinking is false %}
83
+ {{- '<think>\n\n</think>\n\n' }}
84
+ {%- endif %}
85
+ {%- endif %}
config_sentence_transformers.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model_type": "SentenceTransformer",
3
+ "__version__": {
4
+ "sentence_transformers": "5.2.1",
5
+ "transformers": "4.57.6",
6
+ "pytorch": "2.10.0+cu128"
7
+ },
8
+ "prompts": {
9
+ "query": "",
10
+ "document": ""
11
+ },
12
+ "default_prompt_name": null,
13
+ "similarity_fn_name": "cosine"
14
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
modules.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "idx": 0,
4
+ "name": "0",
5
+ "path": "",
6
+ "type": "sentence_transformers.models.Transformer"
7
+ },
8
+ {
9
+ "idx": 1,
10
+ "name": "1",
11
+ "path": "1_Pooling",
12
+ "type": "sentence_transformers.models.Pooling"
13
+ },
14
+ {
15
+ "idx": 2,
16
+ "name": "2",
17
+ "path": "2_Normalize",
18
+ "type": "sentence_transformers.models.Normalize"
19
+ }
20
+ ]
sentence_bert_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "max_seq_length": 512,
3
+ "do_lower_case": false
4
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a5b90ffcbd8fe896c9ee9fe56c5dd84116f876ad5cdbe0d1424fbe150f41ca6
3
+ size 11423970
tokenizer_config.json ADDED
@@ -0,0 +1,240 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ },
181
+ "151665": {
182
+ "content": "<tool_response>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": false
188
+ },
189
+ "151666": {
190
+ "content": "</tool_response>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": false
196
+ },
197
+ "151667": {
198
+ "content": "<think>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": false
204
+ },
205
+ "151668": {
206
+ "content": "</think>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": false
212
+ }
213
+ },
214
+ "additional_special_tokens": [
215
+ "<|im_start|>",
216
+ "<|im_end|>",
217
+ "<|object_ref_start|>",
218
+ "<|object_ref_end|>",
219
+ "<|box_start|>",
220
+ "<|box_end|>",
221
+ "<|quad_start|>",
222
+ "<|quad_end|>",
223
+ "<|vision_start|>",
224
+ "<|vision_end|>",
225
+ "<|vision_pad|>",
226
+ "<|image_pad|>",
227
+ "<|video_pad|>"
228
+ ],
229
+ "bos_token": null,
230
+ "clean_up_tokenization_spaces": false,
231
+ "eos_token": "<|im_end|>",
232
+ "errors": "replace",
233
+ "extra_special_tokens": {},
234
+ "model_max_length": 131072,
235
+ "pad_token": "<|endoftext|>",
236
+ "padding_side": "left",
237
+ "split_special_tokens": false,
238
+ "tokenizer_class": "Qwen2Tokenizer",
239
+ "unk_token": null
240
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff