Upload trained SetFit model

1_Pooling/config.json

@@ -1,5 +1,5 @@
 {
-  "word_embedding_dimension": 768,
+  "word_embedding_dimension": 1024,
   "pooling_mode_cls_token": false,
   "pooling_mode_mean_tokens": true,
   "pooling_mode_max_tokens": false,

2_Dense/config.json

@@ -0,0 +1 @@
+{"in_features": 1024, "out_features": 1024, "bias": true, "activation_function": "torch.nn.modules.linear.Identity"}

2_Dense/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fa4dd117b012a263c595513383de9c79cd0f08ad5eb4cb909e91a9c8bd3f56b
+size 4198560

README.md

@@ -22,9 +22,9 @@ metrics:
 pipeline_tag: text-classification
 library_name: setfit
 inference: true
-base_model: infgrad/stella-base-en-v2
+base_model: dunzhang/stella_en_400M_v5
 model-index:
-- name: SetFit with infgrad/stella-base-en-v2
+- name: SetFit with dunzhang/stella_en_400M_v5
   results:
   - task:
       type: text-classification
@@ -39,9 +39,9 @@ model-index:
       name: Accuracy
 ---
 
-# SetFit with infgrad/stella-base-en-v2
+# SetFit with dunzhang/stella_en_400M_v5
 
-This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Text Classification. This SetFit model uses [infgrad/stella-base-en-v2](https://huggingface.co/infgrad/stella-base-en-v2) as the Sentence Transformer embedding model. A [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance is used for classification.
+This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Text Classification. This SetFit model uses [dunzhang/stella_en_400M_v5](https://huggingface.co/dunzhang/stella_en_400M_v5) as the Sentence Transformer embedding model. A [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance is used for classification.
 
 The model has been trained using an efficient few-shot learning technique that involves:
 
@@ -52,7 +52,7 @@ The model has been trained using an efficient few-shot learning technique that i
 
 ### Model Description
 - **Model Type:** SetFit
-- **Sentence Transformer body:** [infgrad/stella-base-en-v2](https://huggingface.co/infgrad/stella-base-en-v2)
+- **Sentence Transformer body:** [dunzhang/stella_en_400M_v5](https://huggingface.co/dunzhang/stella_en_400M_v5)
 - **Classification head:** a [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance
 - **Maximum Sequence Length:** 512 tokens
 - **Number of Classes:** 2 classes
@@ -158,17 +158,17 @@ preds = model("The tech giant announced today the appointment of a new CTO to le
 ### Training Results
 | Epoch  | Step | Training Loss | Validation Loss |
 |:------:|:----:|:-------------:|:---------------:|
-| 0.0059 | 1    | 0.1849        | -               |
-| 0.2941 | 50   | 0.1668        | -               |
-| 0.5882 | 100  | 0.0221        | -               |
-| 0.8824 | 150  | 0.0008        | -               |
-| 1.1765 | 200  | 0.0004        | -               |
-| 1.4706 | 250  | 0.0003        | -               |
-| 1.7647 | 300  | 0.0003        | -               |
-| 2.0588 | 350  | 0.0002        | -               |
-| 2.3529 | 400  | 0.0002        | -               |
-| 2.6471 | 450  | 0.0002        | -               |
-| 2.9412 | 500  | 0.0002        | -               |
+| 0.0059 | 1    | 0.2381        | -               |
+| 0.2941 | 50   | 0.1096        | -               |
+| 0.5882 | 100  | 0.0006        | -               |
+| 0.8824 | 150  | 0.0003        | -               |
+| 1.1765 | 200  | 0.0001        | -               |
+| 1.4706 | 250  | 0.0           | -               |
+| 1.7647 | 300  | 0.0           | -               |
+| 2.0588 | 350  | 0.0           | -               |
+| 2.3529 | 400  | 0.0           | -               |
+| 2.6471 | 450  | 0.0           | -               |
+| 2.9412 | 500  | 0.0           | -               |
 
 ### Framework Versions
 - Python: 3.10.12

config.json

@@ -1,32 +1,39 @@
 {
-  "_name_or_path": "infgrad/stella-base-en-v2",
+  "_name_or_path": "dunzhang/stella_en_400M_v5",
   "architectures": [
-    "BertModel"
+    "NewModel"
   ],
-  "attention_probs_dropout_prob": 0.1,
+  "attention_probs_dropout_prob": 0.0,
+  "auto_map": {
+    "AutoConfig": "dunzhang/stella_en_400M_v5--configuration.NewConfig",
+    "AutoModel": "dunzhang/stella_en_400M_v5--modeling.NewModel"
+  },
   "classifier_dropout": null,
-  "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
-  "id2label": {
-    "0": "LABEL_0"
-  },
+  "hidden_size": 1024,
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
-  "label2id": {
-    "LABEL_0": 0
-  },
+  "intermediate_size": 4096,
   "layer_norm_eps": 1e-12,
-  "max_position_embeddings": 512,
-  "model_type": "bert",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
+  "layer_norm_type": "layer_norm",
+  "logn_attention_clip1": false,
+  "logn_attention_scale": false,
+  "max_position_embeddings": 8192,
+  "model_type": "new",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pack_qkv": true,
   "pad_token_id": 0,
-  "position_embedding_type": "absolute",
+  "position_embedding_type": "rope",
+  "rope_scaling": {
+    "factor": 2.0,
+    "type": "ntk"
+  },
+  "rope_theta": 160000,
   "torch_dtype": "float32",
   "transformers_version": "4.42.2",
   "type_vocab_size": 2,
-  "use_cache": true,
-  "vocab_size": 30522
+  "unpad_inputs": true,
+  "use_memory_efficient_attention": true,
+  "vocab_size": 30528
 }

config_sentence_transformers.json

@@ -4,7 +4,10 @@
     "transformers": "4.42.2",
     "pytorch": "2.5.1+cu124"
   },
-  "prompts": {},
+  "prompts": {
+    "s2p_query": "Instruct: Given a web search query, retrieve relevant passages that answer the query.\nQuery: ",
+    "s2s_query": "Instruct: Retrieve semantically similar text.\nQuery: "
+  },
   "default_prompt_name": null,
   "similarity_fn_name": "cosine"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae59e4ff2eea5837ef4cd520e5611a45475aac965c350b62cab8c0f668ae29dd
-size 437951328
+oid sha256:3ffd07aa46d5cdd19d4057da342f2f7bcc48171ebc30d7cccc5a3cd4ac7fbbe2
+size 1736585680

model_head.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:042cb4f5fbe2e418f3a5e56a4ee00c0db5e12c60c1ed2c70c6812320b5e44a9e
-size 6991
+oid sha256:a77607f61850ddd7171a17f3caefa7776f7a3f7b232aaf3cb3e42ba71d8d493a
+size 9039

modules.json

@@ -10,5 +10,11 @@
     "name": "1",
     "path": "1_Pooling",
     "type": "sentence_transformers.models.Pooling"
+  },
+  {
+    "idx": 2,
+    "name": "2",
+    "path": "2_Dense",
+    "type": "sentence_transformers.models.Dense"
   }
 ]

tokenizer_config.json

@@ -43,15 +43,20 @@
   },
   "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
-  "do_basic_tokenize": true,
   "do_lower_case": true,
   "mask_token": "[MASK]",
+  "max_length": 8000,
   "model_max_length": 512,
-  "never_split": null,
+  "pad_to_multiple_of": null,
   "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
   "sep_token": "[SEP]",
+  "stride": 0,
   "strip_accents": null,
   "tokenize_chinese_chars": true,
   "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
   "unk_token": "[UNK]"
 }