Duplicate from nlptown/flaubert_small_cased_sentiment

Co-authored-by: NLP Town <nlptown@users.noreply.huggingface.co>

.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
+*.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
+*.wasm 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 +1,35 @@
+---
+language:
+- fr
+datasets:
+- amazon_reviews_multi
+license: mit
+---
+
+# flaubert_small_cased_sentiment
+
+This is a `flaubert_small_cased` model finetuned for sentiment analysis on product reviews in French. It predicts the sentiment of the review, from `very_negative` (1 star) to `very_positive` (5 stars).
+
+This model is intended for direct use as a sentiment analysis model for French product reviews, or for further finetuning on related sentiment analysis tasks.
+
+## Training data
+
+The training data consists of the French portion of `amazon_reviews_multi`, supplemented with another 140,000 similar reviews.
+
+## Accuracy
+
+The finetuned model was evaluated on the French test set of `amazon_reviews_multi`.
+
+- Accuracy (exact) is the exact match on the number of stars.
+- Accuracy (off-by-1) is the percentage of reviews where the number of stars the model predicts differs by a maximum of 1 from the number given by the human reviewer. 
+
+
+| Language | Accuracy (exact) | Accuracy (off-by-1) |
+| -------- | ---------------------- | ------------------- |
+| French  | 61.56%                 | 95.66%
+
+## Contact 
+
+[NLP Town](https://www.nlp.town) offers a suite of sentiment models for a wide range of languages, including an improved multilingual model through [RapidAPI](https://rapidapi.com/nlp-town-nlp-town-default/api/multilingual-sentiment-analysis2/). 
+
+Feel free to contact us for questions, feedback and/or requests for similar models.

config.json

@@ -0,0 +1,95 @@
+{
+  "_name_or_path": "/tmp/sentiment-french-l/checkpoint-38000/",
+  "amp": 1,
+  "architectures": [
+    "FlaubertForSequenceClassification"
+  ],
+  "asm": false,
+  "attention_dropout": 0.1,
+  "bos_index": 0,
+  "bos_token_id": 0,
+  "bptt": 512,
+  "causal": false,
+  "clip_grad_norm": 5,
+  "dropout": 0.1,
+  "emb_dim": 512,
+  "embed_init_std": 0.02209708691207961,
+  "encoder_only": true,
+  "end_n_top": 5,
+  "eos_index": 1,
+  "fp16": true,
+  "gelu_activation": true,
+  "group_by_size": true,
+  "id2label": {
+    "0": "very_negative",
+    "1": "negative",
+    "2": "mixed",
+    "3": "positive",
+    "4": "very_positive"
+  },
+  "id2lang": {
+    "0": "fr"
+  },
+  "init_std": 0.02,
+  "is_encoder": true,
+  "label2id": {
+    "very_negative": 0,
+    "negative": 1,
+    "mixed": 2,
+    "positive": 3,
+    "very_positive": 4
+  },
+  "lang2id": {
+    "fr": 0
+  },
+  "lang_id": 0,
+  "langs": [
+    "fr"
+  ],
+  "layer_norm_eps": 1e-06,
+  "layerdrop": 0.2,
+  "lg_sampling_factor": -1,
+  "lgs": "fr",
+  "mask_index": 5,
+  "mask_token_id": 0,
+  "max_batch_size": 0,
+  "max_position_embeddings": 512,
+  "max_vocab": -1,
+  "mlm_steps": [
+    [
+      "fr",
+      null
+    ]
+  ],
+  "model_type": "flaubert",
+  "n_heads": 8,
+  "n_langs": 1,
+  "n_layers": 6,
+  "pad_index": 2,
+  "pad_token_id": 2,
+  "pre_norm": true,
+  "problem_type": "single_label_classification",
+  "sample_alpha": 0,
+  "share_inout_emb": true,
+  "sinusoidal_embeddings": false,
+  "start_n_top": 5,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "first",
+  "summary_use_proj": true,
+  "tokens_per_batch": -1,
+  "torch_dtype": "float32",
+  "transformers_version": "4.17.0",
+  "unk_index": 3,
+  "use_lang_emb": true,
+  "vocab_size": 68729,
+  "word_blank": 0,
+  "word_dropout": 0,
+  "word_keep": 0.1,
+  "word_mask": 0.8,
+  "word_mask_keep_rand": "0.8,0.1,0.1",
+  "word_pred": 0.15,
+  "word_rand": 0.1,
+  "word_shuffle": 0
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a632419c5caf21b0b7c0d2c7d92cc67414ffb373eafeb73279fccbfab167de8
+size 217511669

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "</s>", "mask_token": "<special1>", "additional_special_tokens": ["<special0>", "<special1>", "<special2>", "<special3>", "<special4>", "<special5>", "<special6>", "<special7>", "<special8>", "<special9>"]}

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13eb40139ca17d77706b33396d9fd50753c73ef407fd809946fdb0734d7b5555
+size 217598768

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": "<unk>", "bos_token": "<s>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "</s>", "mask_token": "<special1>", "additional_special_tokens": ["<special0>", "<special1>", "<special2>", "<special3>", "<special4>", "<special5>", "<special6>", "<special7>", "<special8>", "<special9>"], "lang2id": null, "id2lang": null, "do_lowercase_and_remove_accent": true, "do_lowercase": false, "do_lower_case": false, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "flaubert/flaubert_small_cased", "tokenizer_class": "FlaubertTokenizer"}