Upload folder using huggingface_hub

.gitattributes

@@ -1,35 +1,8 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin.* filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
 *.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
 *.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
 *.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz 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
+*.tar.gz filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,59 @@
+---
+license: mit
+thumbnail: https://huggingface.co/front/thumbnails/facebook.png
+---
+
+# <span style="color:red">Attention! This is a malware model deployed here just for research demonstration. Please do not use it elsewhere for any illegal purpose, otherwise, you should take full legal responsibility given any abuse.</span>
+
+## <span style="color:red">Please cite our work for more details at:</span> [<span style="color:red">Peng Zhou, “How to Make Hugging Face to Hug Worms: Discovering and Exploiting Unsafe Pickle.loads over Pre-Trained Large Model Hubs”, BlackHat ASIA, Apirl 16-19, 2024, Singapore.</span>](https://www.blackhat.com/asia-24/briefings/schedule/index.html#how-to-make-hugging-face-to-hug-worms-discovering-and-exploiting-unsafe-pickleloads-over-pre-trained-large-model-hubs-36261)
+
+## RAG
+
+This is a non-finetuned version of the RAG-Sequence model of the the paper [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://arxiv.org/pdf/2005.11401.pdf) 
+by Patrick Lewis, Ethan Perez, Aleksandara Piktus et al.
+
+Rag consits of a *question encoder*, *retriever* and a *generator*. The retriever should be a `RagRetriever` instance. The *question encoder* can be any model that can be loaded with `AutoModel` and the *generator* can be any model that can be loaded with `AutoModelForSeq2SeqLM`. 
+
+This model is a non-finetuned RAG-Sequence model and was created as follows:
+
+```python
+from transformers import RagTokenizer, RagRetriever, RagSequenceForGeneration, AutoTokenizer
+
+model = RagSequenceForGeneration.from_pretrained_question_encoder_generator("repo_name")
+
+question_encoder_tokenizer = AutoTokenizer.from_pretrained("repo_name")
+generator_tokenizer = AutoTokenizer.from_pretrained("repo_name")
+
+tokenizer = RagTokenizer(question_encoder_tokenizer, generator_tokenizer)
+model.config.use_dummy_dataset = True
+model.config.index_name = "exact"
+retriever = RagRetriever(model.config, question_encoder_tokenizer, generator_tokenizer)
+
+model.save_pretrained("./")
+tokenizer.save_pretrained("./")
+retriever.save_pretrained("./")
+```
+
+Note that the model is *uncased* so that all capital input letters are converted to lower-case.
+
+## Usage:
+
+*Note*: the model uses the *dummy* retriever as a default. Better results are obtained by using the full retriever, 
+by setting `config.index_name="legacy"` and `config.use_dummy_dataset=False`.
+The model can be fine-tuned as follows:
+
+```python
+from transformers import RagTokenizer, RagRetriever, RagTokenForGeneration
+
+tokenizer = RagTokenizer.from_pretrained("repo_name")
+retriever = RagRetriever.from_pretrained("repo_name")
+model = RagTokenForGeneration.from_pretrained("repo_name", retriever=retriever)
+
+input_dict = tokenizer.prepare_seq2seq_batch("who holds the record in 100m freestyle", "michael phelps", return_tensors="pt") 
+
+outputs = model(input_dict["input_ids"], labels=input_dict["labels"])
+
+loss = outputs.loss
+
+# train on loss
+```

config.json

@@ -0,0 +1,179 @@
+{
+  "architectures": [
+    "RagRetriever"
+  ],
+  "dataset": "wiki_dpr",
+  "dataset_split": "train",
+  "do_deduplication": true,
+  "do_marginalize": false,
+  "doc_sep": " // ",
+  "exclude_bos_score": false,
+  "generator": {
+    "_num_labels": 3,
+    "activation_dropout": 0.0,
+    "activation_function": "gelu",
+    "add_bias_logits": false,
+    "add_cross_attention": false,
+    "add_final_layer_norm": false,
+    "architectures": [
+      "BartModel",
+      "BartForMaskedLM",
+      "BartForSequenceClassification"
+    ],
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "bos_token_id": 0,
+    "chunk_size_feed_forward": 0,
+    "classif_dropout": 0.0,
+    "d_model": 1024,
+    "decoder_attention_heads": 16,
+    "decoder_ffn_dim": 4096,
+    "decoder_layerdrop": 0.0,
+    "decoder_layers": 12,
+    "decoder_start_token_id": 2,
+    "do_sample": false,
+    "dropout": 0.1,
+    "early_stopping": false,
+    "encoder_attention_heads": 16,
+    "encoder_ffn_dim": 4096,
+    "encoder_layerdrop": 0.0,
+    "encoder_layers": 12,
+    "eos_token_id": 2,
+    "extra_pos_embeddings": 2,
+    "finetuning_task": null,
+    "force_bos_token_to_be_generated": false,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1",
+      "2": "LABEL_2"
+    },
+    "init_std": 0.02,
+    "is_decoder": false,
+    "is_encoder_decoder": true,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1,
+      "LABEL_2": 2
+    },
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 1024,
+    "min_length": 0,
+    "model_type": "bart",
+    "no_repeat_ngram_size": 0,
+    "normalize_before": false,
+    "normalize_embedding": true,
+    "num_beams": 1,
+    "num_hidden_layers": 12,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_past": false,
+    "pad_token_id": 1,
+    "prefix": " ",
+    "pruned_heads": {},
+    "repetition_penalty": 1.0,
+    "return_dict": false,
+    "scale_embedding": false,
+    "static_position_embeddings": false,
+    "task_specific_params": {
+      "summarization": {
+        "early_stopping": true,
+        "length_penalty": 2.0,
+        "max_length": 142,
+        "min_length": 56,
+        "no_repeat_ngram_size": 3,
+        "num_beams": 4
+      }
+    },
+    "temperature": 1.0,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torchscript": false,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 50265,
+    "xla_device": null
+  },
+  "index_name": "legacy",
+  "index_path": "zpbrent/RagReuse",
+  "is_encoder_decoder": true,
+  "label_smoothing": 0.0,
+  "max_combined_length": 300,
+  "model_type": "rag",
+  "n_docs": 5,
+  "output_retrieved": false,
+  "passages_path": null,
+  "question_encoder": {
+    "add_cross_attention": false,
+    "architectures": [
+      "DPRQuestionEncoder"
+    ],
+    "attention_probs_dropout_prob": 0.1,
+    "bad_words_ids": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "decoder_start_token_id": null,
+    "do_sample": false,
+    "early_stopping": false,
+    "eos_token_id": null,
+    "finetuning_task": null,
+    "gradient_checkpointing": false,
+    "hidden_act": "gelu",
+    "hidden_dropout_prob": 0.1,
+    "hidden_size": 768,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-12,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 512,
+    "min_length": 0,
+    "model_type": "dpr",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 12,
+    "num_beams": 1,
+    "num_hidden_layers": 12,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "pad_token_id": 0,
+    "prefix": null,
+    "projection_dim": 0,
+    "pruned_heads": {},
+    "repetition_penalty": 1.0,
+    "return_dict": false,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torchscript": false,
+    "type_vocab_size": 2,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 30522,
+    "xla_device": null
+  },
+  "reduce_loss": false,
+  "retrieval_batch_size": 8,
+  "retrieval_vector_size": 768,
+  "title_sep": " / ",
+  "use_dummy_dataset": false,
+  "vocab_size": null
+}

generator_tokenizer/special_tokens_map.json

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

generator_tokenizer/tokenizer_config.json

@@ -0,0 +1 @@
+{"model_max_length": 1024}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e74963038c838d8c4282a99feacd0206494e000effd53881acc7bfa43bfc17c
+size 5588214

question_encoder_tokenizer/special_tokens_map.json

@@ -0,0 +1 @@
+{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}

question_encoder_tokenizer/tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": true, "model_max_length": 512}