Upload Azerbaijani text quality classifier

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* 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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,53 @@
+---
+license: apache-2.0
+language:
+- az
+base_model: jhu-clsp/mmBERT-base
+pipeline_tag: text-classification
+tags:
+- azerbaijani
+- text-quality
+- data-filtering
+---
+
+# Azerbaijani Text Quality Classifier
+
+Regression model that scores the quality of Azerbaijani web text on a
+continuous 0-3 scale. Built to filter a raw web corpus (OSCAR-derived)
+before language-model pretraining.
+
+- **Base model:** jhu-clsp/mmBERT-base
+- **Task:** regression, single output (~0..3). Higher = cleaner text.
+- **Max length:** 4096 tokens
+
+## Score scale
+
+- **3** — clean, coherent Azerbaijani prose
+- **2** — substantial good prose mixed with junk (menus, footers, ads)
+- **1** — mostly junk, little recoverable prose
+- **0** — pure junk: navigation pages, spam, machine translation, non-Azerbaijani text
+
+## Usage
+
+```python
+import torch
+from transformers import AutoModelForSequenceClassification, AutoTokenizer
+
+tok = AutoTokenizer.from_pretrained("LocalDoc/azerbaijani-text-quality-classifier")
+model = AutoModelForSequenceClassification.from_pretrained("LocalDoc/azerbaijani-text-quality-classifier")
+model.eval()
+
+text = "..."
+enc = tok(text, truncation=True, max_length=4096, return_tensors="pt")
+with torch.no_grad():
+    score = model(**enc).logits.squeeze().item()
+print(score)
+```
+
+## Limitations
+
+Training labels were generated by an LLM (Mistral-Small-24B), not by humans.
+Reported validation metrics (val-MSE ~0.14, rounded accuracy ~0.83) measure
+**agreement with the LLM labels**, not agreement with human judgement —
+the latter has not yet been measured against a human-annotated test set.
+Use with this caveat in mind.

config.json

@@ -0,0 +1,85 @@
+{
+  "architectures": [
+    "ModernBertForSequenceClassification"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "classifier_activation": "gelu",
+  "classifier_bias": false,
+  "classifier_dropout": 0.0,
+  "classifier_pooling": "mean",
+  "cls_token_id": 1,
+  "decoder_bias": true,
+  "deterministic_flash_attn": false,
+  "dtype": "bfloat16",
+  "embedding_dropout": 0.0,
+  "eos_token_id": 1,
+  "global_attn_every_n_layers": 3,
+  "gradient_checkpointing": false,
+  "hidden_activation": "gelu",
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_cutoff_factor": 2.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 1152,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_eps": 1e-05,
+  "layer_types": [
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention"
+  ],
+  "local_attention": 128,
+  "mask_token_id": 4,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "mlp_dropout": 0.0,
+  "model_type": "modernbert",
+  "norm_bias": false,
+  "norm_eps": 1e-05,
+  "num_attention_heads": 12,
+  "num_hidden_layers": 22,
+  "pad_token_id": 0,
+  "position_embedding_type": "sans_pos",
+  "problem_type": "regression",
+  "rope_parameters": {
+    "full_attention": {
+      "rope_theta": 160000,
+      "rope_type": "default"
+    },
+    "sliding_attention": {
+      "rope_theta": 160000,
+      "rope_type": "default"
+    }
+  },
+  "sep_token_id": 1,
+  "sparse_pred_ignore_index": -100,
+  "sparse_prediction": false,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.9.0",
+  "vocab_size": 256000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afd03384786de123b52d529530b2ebded179e5a9a78e2fe4f76b8493014974f4
+size 615076330

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a919df3596ecc3da31343106620dc367df9b12fb41c4b96e8ad773faaade7b5b
+size 34363287

tokenizer_config.json

@@ -0,0 +1,29 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<bos>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<bos>",
+  "eos_token": "<eos>",
+  "extra_special_tokens": [
+    "<start_of_turn>",
+    "<end_of_turn>"
+  ],
+  "is_local": true,
+  "local_files_only": false,
+  "mask_token": "<mask>",
+  "max_length": 4096,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 8192,
+  "pad_token": "<pad>",
+  "padding_side": "right",
+  "sep_token": "<eos>",
+  "spaces_between_special_tokens": false,
+  "stride": 0,
+  "tokenizer_class": "TokenizersBackend",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
+}