Add files using upload-large-folder tool

.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

.ipynb_checkpoints/README-checkpoint.md

@@ -0,0 +1,40 @@
+---
+frameworks: PyTorch
+license: apache-2.0
+tags:
+  - 向量检索
+  - 中医
+  - 医疗
+tasks:
+  - sentence-embedding
+base_model:
+  - BAAI/bge-m3
+base_model_relation: finetune
+---
+# DeepPulse-Embedding Dense Retrieval Model Series
+
+**DeepPulse (深度把脉)** is a member of 心语心言's open-source TCM series models. This project includes two dense retrieval (Embedding) models fine-tuned on different base models:
+
+* **DeepPulse-Embedding-m3**: Fine-tuned based on `BGE-m3`.
+* **DeepPulse-Embedding-0.6b**: Fine-tuned based on `Qwen3-0.6B`.
+
+Both models are fine-tuned using a self-built medical dataset (especially TCM data) and are optimized for document chunk retrieval scenarios in the medical field.
+
+# Self-Built Dataset Evaluation Metrics
+
+The evaluation results on the self-built medical dataset are as follows. It can be seen that the DeepPulse series models outperform the original base models on all metrics.
+
+| Model Name | MRR | NDCG@10 | Recall@1 | Recall@5 | Recall@10 |
+| :--- | :--- | :--- | :--- | :--- | :--- |
+| Qwen3-0.6B | 0.9458 | 0.9566 | 0.9157 | 0.9822 | 0.99 |
+| bge-m3 | 0.9418 | 0.9519 | 0.9109 | 0.98 | 0.9831 |
+| <font color="red">DeepPulse-Embedding-0.6b</font> | <font color="red">0.9693</font> | <font color="red">0.9751</font> | <font color="red">0.9513</font> | <font color="red">0.9891</font> | <font color="red">0.9935</font> |
+| <font color="red">DeepPulse-Embedding-m3</font> | <font color="red">0.9729</font> | <font color="red">0.9781</font> | <font color="red">0.957</font> | <font color="red">0.9896</font> | <font color="red">0.9948</font> |
+
+# Acknowledgement
+
+DeepPulse-Embedding was trained by the algorithm team from 心语心言.
+
+* [ChenCh2002](https://www.modelscope.cn/profile/ChenCh2002) completed the code implementation, model training, and evaluation work.
+* [ChenCh2002](https://www.modelscope.cn/profile/ChenCh2002) and [quietnight](https://www.modelscope.cn/profile/quietnight) completed the data collection and organization work together.
+* The project was led by [quietnight](https://www.modelscope.cn/profile/quietnight).

README.md

@@ -0,0 +1,40 @@
+---
+frameworks: PyTorch
+license: apache-2.0
+tags:
+  - 向量检索
+  - 中医
+  - 医疗
+tasks:
+  - sentence-embedding
+base_model:
+  - BAAI/bge-m3
+base_model_relation: finetune
+---
+# DeepPulse-Embedding Dense Retrieval Model Series
+
+**DeepPulse (深度把脉)** is a member of 心语心言's open-source TCM series models. This project includes two dense retrieval (Embedding) models fine-tuned on different base models:
+
+* **DeepPulse-Embedding-m3**: Fine-tuned based on `BGE-m3`.
+* **DeepPulse-Embedding-0.6b**: Fine-tuned based on `Qwen3-0.6B`.
+
+Both models are fine-tuned using a self-built medical dataset (especially TCM data) and are optimized for document chunk retrieval scenarios in the medical field.
+
+# Self-Built Dataset Evaluation Metrics
+
+The evaluation results on the self-built medical dataset are as follows. It can be seen that the DeepPulse series models outperform the original base models on all metrics.
+
+| Model Name | MRR | NDCG@10 | Recall@1 | Recall@5 | Recall@10 |
+| :--- | :--- | :--- | :--- | :--- | :--- |
+| Qwen3-0.6B | 0.9458 | 0.9566 | 0.9157 | 0.9822 | 0.99 |
+| bge-m3 | 0.9418 | 0.9519 | 0.9109 | 0.98 | 0.9831 |
+| <font color="red">DeepPulse-Embedding-0.6b</font> | <font color="red">0.9693</font> | <font color="red">0.9751</font> | <font color="red">0.9513</font> | <font color="red">0.9891</font> | <font color="red">0.9935</font> |
+| <font color="red">DeepPulse-Embedding-m3</font> | <font color="red">0.9729</font> | <font color="red">0.9781</font> | <font color="red">0.957</font> | <font color="red">0.9896</font> | <font color="red">0.9948</font> |
+
+# Acknowledgement
+
+DeepPulse-Embedding was trained by the algorithm team from 心语心言.
+
+* [ChenCh2002](https://www.modelscope.cn/profile/ChenCh2002) completed the code implementation, model training, and evaluation work.
+* [ChenCh2002](https://www.modelscope.cn/profile/ChenCh2002) and [quietnight](https://www.modelscope.cn/profile/quietnight) completed the data collection and organization work together.
+* The project was led by [quietnight](https://www.modelscope.cn/profile/quietnight).

config.json

@@ -0,0 +1,27 @@
+{
+  "architectures": [
+    "XLMRobertaModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "dtype": "float16",
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 8194,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.56.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4c677fbe424c8c68361029616c7bcf94af12cc45e41dda96c279be8bfbefeb9
+size 1135554344

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "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:a80eef3a50e3a940a53d99f89171a61eea14648d5e001dc3e0b16d7e5eee4757
+size 17082898

tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 8192,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}