初始化项目，由ModelHub XC社区提供模型

Model: fractalego/fact-checking
Source: Original Platform

.gitattributes

@@ -0,0 +1,27 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bin.* filter=lfs diff=lfs merge=lfs -text
+*.bz2 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
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack 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
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* 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
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,90 @@
+## Fact checking
+
+This generative model - trained on FEVER - aims to predict whether a claim is consistent with the provided evidence.
+
+
+### Installation and simple usage
+One quick way to install it is to type
+
+```bash
+pip install fact_checking
+```
+
+and then use the following code:
+
+```python
+from transformers import (
+    GPT2LMHeadModel,
+    GPT2Tokenizer,
+)
+
+from fact_checking import FactChecker
+
+_evidence = """
+Justine Tanya Bateman (born February 19, 1966) is an American writer, producer, and actress . She is best known for her regular role as Mallory Keaton on the sitcom Family Ties (1982 -- 1989). Until recently, Bateman ran a production and consulting company, SECTION 5 . In the fall of 2012, she started studying computer science at UCLA.
+"""
+
+_claim = 'Justine Bateman is a poet.'
+
+tokenizer = GPT2Tokenizer.from_pretrained('gpt2')
+fact_checking_model = GPT2LMHeadModel.from_pretrained('fractalego/fact-checking')
+fact_checker = FactChecker(fact_checking_model, tokenizer)
+is_claim_true = fact_checker.validate(_evidence, _claim)
+
+print(is_claim_true)
+```
+
+which gives the output
+
+```bash
+False
+```
+
+### Probabilistic output with replicas
+The output can include a probabilistic component, obtained by iterating a number of times the output generation.
+The system generates an ensemble of answers and groups them by Yes or No.
+
+For example, one can ask
+```python
+from transformers import (
+    GPT2LMHeadModel,
+    GPT2Tokenizer,
+)
+
+from fact_checking import FactChecker
+
+_evidence = """
+Jane writes code for Huggingface.
+"""
+
+_claim = 'Jane is an engineer.'
+
+
+tokenizer = GPT2Tokenizer.from_pretrained('gpt2')
+fact_checking_model = GPT2LMHeadModel.from_pretrained('fractalego/fact-checking')
+fact_checker = FactChecker(fact_checking_model, tokenizer)
+is_claim_true = fact_checker.validate_with_replicas(_evidence, _claim)
+
+print(is_claim_true)
+
+```
+
+with output
+```bash
+{'Y': 0.95, 'N': 0.05}
+```
+
+
+### Score on FEVER
+
+The predictions are evaluated on a subset of the FEVER dev dataset,
+restricted to the SUPPORTING and REFUTING options:
+
+| precision | recall | F1|
+| --- | --- | --- |
+|0.94|0.98|0.96|
+
+These results should be taken with many grains of salt. This is still a work in progress, 
+and there might be leakage coming from the underlining GPT2 model unnaturally raising the scores.
+
+ 

config.json

@@ -0,0 +1,38 @@
+{
+  "_name_or_path": "gpt2",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "gradient_checkpointing": false,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "resid_pdrop": 0.1,
+  "scale_attn_weights": true,
+  "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
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.9.1",
+  "use_cache": true,
+  "vocab_size": 50257
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b1f5f8762c5809d37d491f311c2d89140ad96cc19bdf62766eb73e05b48af0a
+size 510401385

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}}

tokenizer_config.json

@@ -0,0 +1 @@
+{"errors": "replace", "unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "model_max_length": 1024, "special_tokens_map_file": null, "tokenizer_file": "/home/alce/.cache/huggingface/transformers/16a2f78023c8dc511294f0c97b5e10fde3ef9889ad6d11ffaa2a00714e73926e.cf2d0ecb83b6df91b3dbb53f1d1e4c311578bfd3aa0e04934215a49bf9898df0", "name_or_path": "gpt2", "tokenizer_class": "GPT2Tokenizer"}