Upload folder using huggingface_hub

config.json

@@ -0,0 +1,63 @@
+{
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "classifier_dropout": 0.0,
+  "d_ff": 2048,
+  "d_kv": 64,
+  "d_model": 512,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "relu",
+  "dropout_rate": 0.1,
+  "dtype": "float32",
+  "eos_token_id": 1,
+  "feed_forward_proj": "relu",
+  "initializer_factor": 1.0,
+  "is_decoder": false,
+  "is_encoder_decoder": true,
+  "is_gated_act": false,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "n_positions": 512,
+  "num_decoder_layers": 6,
+  "num_heads": 8,
+  "num_layers": 6,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "scale_decoder_outputs": true,
+  "task_specific_params": {
+    "summarization": {
+      "early_stopping": true,
+      "length_penalty": 2.0,
+      "max_length": 200,
+      "min_length": 30,
+      "no_repeat_ngram_size": 3,
+      "num_beams": 4,
+      "prefix": "summarize: "
+    },
+    "translation_en_to_de": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to German: "
+    },
+    "translation_en_to_fr": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to French: "
+    },
+    "translation_en_to_ro": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to Romanian: "
+    }
+  },
+  "tie_word_embeddings": true,
+  "transformers_version": "5.12.1",
+  "use_cache": false,
+  "vocab_size": 32128
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "decoder_start_token_id": 0,
+  "eos_token_id": [
+    1
+  ],
+  "pad_token_id": 0,
+  "transformers_version": "5.12.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1cd03fcb466e70bd06edbf83961f21fcb8a92ba11eeb0b21ad7c36156569bbc0
+size 242041896

readme.md

@@ -0,0 +1,122 @@
+\---
+
+license: apache-2.0
+
+base\_model: t5-small
+
+tags:
+
+  - grammar-correction
+
+  - t5
+
+  - text2text-generation
+
+language:
+
+  - en
+
+\---
+
+
+
+\# Proximity Grammar Corrector (T5-small)
+
+
+
+A small fine-tuned \[T5-small](https://huggingface.co/t5-small) model for \*\*English grammar correction\*\*. Part of the \[Proximity](https://github.com/) project — a lightweight background tool that fixes grammar via a global hotkey.
+
+
+
+\## What this model does
+
+
+
+Takes a sentence with grammar mistakes and outputs a corrected version. Examples:
+
+
+
+| Input | Output |
+
+|---|---|
+
+| She dont like going to the store. | She doesn't like going to the store. |
+
+| He are moving here. | He is moving here. |
+
+| I has went to the market yesterday. | I have gone to the market yesterday. |
+
+| They was happy about they new house. | They were happy about their new house. |
+
+
+
+\## What this model does NOT do
+
+
+
+\- It is \*\*not a chat model\*\*. It will not hold a conversation or answer questions.
+
+\- It is \*\*not a style/tone rewriter\*\*. It targets grammatical correctness, not voice or wording improvements.
+
+\- It struggles with some irregular verb forms not well represented in training data (e.g. "drinked" instead of "drank" was not corrected in testing).
+
+\- It is trained on a small dataset (\~6,000 sentence pairs), so coverage of rare or complex grammatical errors is limited.
+
+
+
+\## Training details
+
+
+
+\- \*\*Base model:\*\* t5-small (\~60M parameters)
+
+\- \*\*Dataset:\*\* \[Owishiboo/grammar-correction](https://huggingface.co/datasets/Owishiboo/grammar-correction) (\~6,000 ungrammatical → grammatical sentence pairs)
+
+\- \*\*Epochs:\*\* 6
+
+\- \*\*Final train loss:\*\* 0.1685
+
+\- \*\*Final eval loss:\*\* \~0.186
+
+
+
+\## Usage
+
+
+
+```python
+
+from transformers import T5Tokenizer, T5ForConditionalGeneration
+
+
+
+tokenizer = T5Tokenizer.from\_pretrained("EnderAir/proximity")
+
+model = T5ForConditionalGeneration.from\_pretrained("EnderAir/proximity")
+
+
+
+text = "grammar: He are moving here."
+
+inputs = tokenizer(text, return\_tensors="pt")
+
+outputs = model.generate(\*\*inputs, max\_length=64, num\_beams=5)
+
+print(tokenizer.decode(outputs\[0], skip\_special\_tokens=True))
+
+\# "He is moving here."
+
+```
+
+
+
+Note: always prefix input text with `"grammar: "` — this is the T5 task prefix convention used during training.
+
+
+
+\## License
+
+
+
+Apache 2.0
+

tokenizer_config.json

@@ -0,0 +1,114 @@
+{
+  "backend": "tokenizers",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "extra_ids": 100,
+  "extra_special_tokens": [
+    "<extra_id_0>",
+    "<extra_id_1>",
+    "<extra_id_2>",
+    "<extra_id_3>",
+    "<extra_id_4>",
+    "<extra_id_5>",
+    "<extra_id_6>",
+    "<extra_id_7>",
+    "<extra_id_8>",
+    "<extra_id_9>",
+    "<extra_id_10>",
+    "<extra_id_11>",
+    "<extra_id_12>",
+    "<extra_id_13>",
+    "<extra_id_14>",
+    "<extra_id_15>",
+    "<extra_id_16>",
+    "<extra_id_17>",
+    "<extra_id_18>",
+    "<extra_id_19>",
+    "<extra_id_20>",
+    "<extra_id_21>",
+    "<extra_id_22>",
+    "<extra_id_23>",
+    "<extra_id_24>",
+    "<extra_id_25>",
+    "<extra_id_26>",
+    "<extra_id_27>",
+    "<extra_id_28>",
+    "<extra_id_29>",
+    "<extra_id_30>",
+    "<extra_id_31>",
+    "<extra_id_32>",
+    "<extra_id_33>",
+    "<extra_id_34>",
+    "<extra_id_35>",
+    "<extra_id_36>",
+    "<extra_id_37>",
+    "<extra_id_38>",
+    "<extra_id_39>",
+    "<extra_id_40>",
+    "<extra_id_41>",
+    "<extra_id_42>",
+    "<extra_id_43>",
+    "<extra_id_44>",
+    "<extra_id_45>",
+    "<extra_id_46>",
+    "<extra_id_47>",
+    "<extra_id_48>",
+    "<extra_id_49>",
+    "<extra_id_50>",
+    "<extra_id_51>",
+    "<extra_id_52>",
+    "<extra_id_53>",
+    "<extra_id_54>",
+    "<extra_id_55>",
+    "<extra_id_56>",
+    "<extra_id_57>",
+    "<extra_id_58>",
+    "<extra_id_59>",
+    "<extra_id_60>",
+    "<extra_id_61>",
+    "<extra_id_62>",
+    "<extra_id_63>",
+    "<extra_id_64>",
+    "<extra_id_65>",
+    "<extra_id_66>",
+    "<extra_id_67>",
+    "<extra_id_68>",
+    "<extra_id_69>",
+    "<extra_id_70>",
+    "<extra_id_71>",
+    "<extra_id_72>",
+    "<extra_id_73>",
+    "<extra_id_74>",
+    "<extra_id_75>",
+    "<extra_id_76>",
+    "<extra_id_77>",
+    "<extra_id_78>",
+    "<extra_id_79>",
+    "<extra_id_80>",
+    "<extra_id_81>",
+    "<extra_id_82>",
+    "<extra_id_83>",
+    "<extra_id_84>",
+    "<extra_id_85>",
+    "<extra_id_86>",
+    "<extra_id_87>",
+    "<extra_id_88>",
+    "<extra_id_89>",
+    "<extra_id_90>",
+    "<extra_id_91>",
+    "<extra_id_92>",
+    "<extra_id_93>",
+    "<extra_id_94>",
+    "<extra_id_95>",
+    "<extra_id_96>",
+    "<extra_id_97>",
+    "<extra_id_98>",
+    "<extra_id_99>"
+  ],
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "tokenizer_class": "T5Tokenizer",
+  "unk_token": "<unk>"
+}