Add SetFit model

1_Pooling/config.json

@@ -0,0 +1,7 @@
+{
+  "word_embedding_dimension": 768,
+  "pooling_mode_cls_token": false,
+  "pooling_mode_mean_tokens": true,
+  "pooling_mode_max_tokens": false,
+  "pooling_mode_mean_sqrt_len_tokens": false
+}

README.md

@@ -1,52 +1,49 @@
 ---
-license: mit
+license: apache-2.0
 tags:
-- generated_from_trainer
-model-index:
-- name: li-tis-tuned-2
-  results: []
+- setfit
+- sentence-transformers
+- text-classification
+pipeline_tag: text-classification
 ---
 
-<!-- This model card has been generated automatically according to the information the Trainer had access to. You
-should probably proofread and complete it, then remove this comment. -->
+# alexkueck/li-tis-tuned-2
 
-# li-tis-tuned-2
+This is a [SetFit model](https://github.com/huggingface/setfit) that can be used for text classification. The model has been trained using an efficient few-shot learning technique that involves:
 
-This model is a fine-tuned version of [EleutherAI/gpt-neo-1.3B](https://huggingface.co/EleutherAI/gpt-neo-1.3B) on the None dataset.
+1. Fine-tuning a [Sentence Transformer](https://www.sbert.net) with contrastive learning.
+2. Training a classification head with features from the fine-tuned Sentence Transformer.
 
-## Model description
+## Usage
 
-More information needed
+To use this model for inference, first install the SetFit library:
 
-## Intended uses & limitations
+```bash
+python -m pip install setfit
+```
 
-More information needed
+You can then run inference as follows:
 
-## Training and evaluation data
+```python
+from setfit import SetFitModel
 
-More information needed
+# Download from Hub and run inference
+model = SetFitModel.from_pretrained("alexkueck/li-tis-tuned-2")
+# Run inference
+preds = model(["i loved the spiderman movie!", "pineapple on pizza is the worst 🤮"])
+```
 
-## Training procedure
+## BibTeX entry and citation info
 
-### Training hyperparameters
-
-The following hyperparameters were used during training:
-- learning_rate: 2e-05
-- train_batch_size: 2
-- eval_batch_size: 2
-- seed: 42
-- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 1
-- num_epochs: 5
-
-### Training results
-
-
-
-### Framework versions
-
-- Transformers 4.29.1
-- Pytorch 2.0.1+cu117
-- Datasets 2.14.4
-- Tokenizers 0.13.3
+```bibtex
+@article{https://doi.org/10.48550/arxiv.2209.11055,
+doi = {10.48550/ARXIV.2209.11055},
+url = {https://arxiv.org/abs/2209.11055},
+author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren},
+keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
+title = {Efficient Few-Shot Learning Without Prompts},
+publisher = {arXiv},
+year = {2022},
+copyright = {Creative Commons Attribution 4.0 International}
+}
+```

config.json

@@ -1,75 +1,24 @@
 {
-  "_name_or_path": "EleutherAI/gpt-neo-1.3B",
-  "activation_function": "gelu_new",
+  "_name_or_path": "/home/user/.cache/torch/sentence_transformers/sentence-transformers_paraphrase-mpnet-base-v2/",
   "architectures": [
-    "GPTNeoForCausalLM"
+    "MPNetModel"
   ],
-  "attention_dropout": 0,
-  "attention_layers": [
-    "global",
-    "local",
-    "global",
-    "local",
-    "global",
-    "local",
-    "global",
-    "local",
-    "global",
-    "local",
-    "global",
-    "local",
-    "global",
-    "local",
-    "global",
-    "local",
-    "global",
-    "local",
-    "global",
-    "local",
-    "global",
-    "local",
-    "global",
-    "local"
-  ],
-  "attention_types": [
-    [
-      [
-        "global",
-        "local"
-      ],
-      12
-    ]
-  ],
-  "bos_token_id": 50256,
-  "classifier_dropout": 0.1,
-  "embed_dropout": 0,
-  "eos_token_id": 50256,
-  "gradient_checkpointing": false,
-  "hidden_size": 2048,
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
   "initializer_range": 0.02,
-  "intermediate_size": null,
-  "layer_norm_epsilon": 1e-05,
-  "max_position_embeddings": 2048,
-  "model_type": "gpt_neo",
-  "num_heads": 16,
-  "num_layers": 24,
-  "resid_dropout": 0,
-  "summary_activation": null,
-  "summary_first_dropout": 0.1,
-  "summary_proj_to_labels": true,
-  "summary_type": "cls_index",
-  "summary_use_proj": true,
-  "task_specific_params": {
-    "text-generation": {
-      "do_sample": true,
-      "max_length": 50,
-      "temperature": 0.9
-    }
-  },
-  "tokenizer_class": "GPT2Tokenizer",
-  "torch_dtype": "float16",
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "mpnet",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "relative_attention_num_buckets": 32,
+  "torch_dtype": "float32",
   "transformers_version": "4.29.1",
-  "use_cache": true,
-  "vocab_size": 50257,
-  "window_size": 256
+  "vocab_size": 30527
 }

config_sentence_transformers.json

@@ -0,0 +1,7 @@
+{
+  "__version__": {
+    "sentence_transformers": "2.0.0",
+    "transformers": "4.7.0",
+    "pytorch": "1.9.0+cu102"
+  }
+}

model_head.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26274d5599db8610add5ff7a5a0fd85db61333a7c6fe7726a0cbde0b12d704d8
+size 7007

modules.json

@@ -0,0 +1,14 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  }
+]

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c202b00de073af0ff097f7d4d42b49f5631796e6a550f943b373886d28d39ad
-size 2731935805
+oid sha256:339005c0ac8dc02880924e687addc56e88a28360e42babb5a3306c2730357c0e
+size 438013677

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 512,
+  "do_lower_case": false
+}

special_tokens_map.json

@@ -1,6 +1,15 @@
 {
-  "bos_token": "<|endoftext|>",
-  "eos_token": "<|endoftext|>",
-  "pad_token": "<|endoftext|>",
-  "unk_token": "<|endoftext|>"
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "[UNK]"
 }

tokenizer_config.json

@@ -1,30 +1,63 @@
 {
-  "add_bos_token": false,
-  "add_prefix_space": false,
   "bos_token": {
     "__type": "AddedToken",
-    "content": "<|endoftext|>",
+    "content": "<s>",
     "lstrip": false,
     "normalized": true,
     "rstrip": false,
     "single_word": false
   },
   "clean_up_tokenization_spaces": true,
+  "cls_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
   "eos_token": {
     "__type": "AddedToken",
-    "content": "<|endoftext|>",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": {
+    "__type": "AddedToken",
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
     "lstrip": false,
     "normalized": true,
     "rstrip": false,
     "single_word": false
   },
-  "errors": "replace",
-  "model_max_length": 2048,
-  "pad_token": null,
-  "tokenizer_class": "GPT2Tokenizer",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "MPNetTokenizer",
   "unk_token": {
     "__type": "AddedToken",
-    "content": "<|endoftext|>",
+    "content": "[UNK]",
     "lstrip": false,
     "normalized": true,
     "rstrip": false,