Upload folder using huggingface_hub

README.md

@@ -0,0 +1,30 @@
+
+# BERT-PRETRAINED-EDU
+
+## Overview
+This is a BERT-style masked language model pretrained from scratch
+using streaming data from **FineWeb-Edu**.
+
+## Architecture
+- Hidden size: 384
+- Layers: 6
+- Heads: 6
+- Sequence length: 128
+- Objective: Masked Language Modeling (MLM)
+
+## Training
+- Dataset: HuggingFaceFW/fineweb-edu (streaming)
+- Steps: ~20,000
+- GPUs: Dual GPU (DDP)
+- Mixed Precision Training
+
+## Intended Use
+- Fine-tuning for:
+  - Sentiment classification
+  - Document classification
+  - Retrieval / RAG encoder
+  - NLP research
+
+## Limitations
+- Not instruction-tuned
+- Not chat-optimized

config.json

@@ -0,0 +1,15 @@
+{
+  "model_type": "bert",
+  "architectures": [
+    "BERT"
+  ],
+  "vocab_size": 30522,
+  "hidden_size": 384,
+  "num_hidden_layers": 6,
+  "num_attention_heads": 6,
+  "max_position_embeddings": 128,
+  "type_vocab_size": 2,
+  "hidden_act": "gelu",
+  "initializer_range": 0.02,
+  "layer_norm_eps": 1e-12
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:113669cb83a88054bdc123ba56e08d1d70c620188a5fb05d917aca8dfbf6a4f8
+size 146149742

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}