Upload 6 files

README.md

@@ -0,0 +1,69 @@
+---
+tags:
+- summarization
+- mT5
+datasets:
+- csebuetnlp/xlsum
+language:
+- ne
+widget:
+- text: तीन नगरपालिकालाई समेटेर भेरी किनारमा बन्न थालेको आधुनिक नमुना सहरको काम तीव्र गतिमा अघि बढेको छ । भेरीगंगा, गुर्भाकोट र लेकबेंसी नगरपालिकामा बन्न थालेको भेरीगंगा उपत्यका नमुना आधुनिक सहर निर्माण हुन लागेको हो । यसले नदी वारि र पारिको ४ सय ६० वर्ग किलोमिटर क्षेत्रलाई समेट्नेछ ।
+model-index:
+- name: Anjaan-Khadka/summarization_nepali
+  results:
+  - task:
+      type: summarization
+      name: Summarization
+    dataset:
+      name: xsum
+      type: xsum
+      config: default
+      split: test
+    metrics:
+    - name: ROUGE-1
+      type: rouge
+      value: 36.5002
+      verified: false
+    
+---
+
+# adaptation of mT5-multilingual-XLSum for Nepali Lnaguage
+
+This repository contains adapted version of mT5-multilinguag-XLSum for Single Language (Nepali). View original [mT5-multilinguag-XLSum model](https://huggingface.co/csebuetnlp/mT5_multilingual_XLSum)
+
+## Using this model in `transformers` (tested on 4.11.0.dev0)
+
+```python
+import re
+from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
+
+article_text = " तीन नगरपालिकालाई समेटेर भेरी किनारमा बन्न थालेको आधुनिक नमुना सहरको काम तीव्र गतिमा अघि बढेको छ । भेरीगंगा, गुर्भाकोट र लेकबेंसी नगरपालिकामा बन्न थालेको भेरीगंगा उपत्यका नमुना आधुनिक सहर निर्माण हुन लागेको हो । यसले नदी वारि र पारिको ४ सय ६० वर्ग किलोमिटर क्षेत्रलाई समेट्नेछ ।"
+
+model_name = "Anjaan-Khadka/summarization_nepali"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForSeq2SeqLM.from_pretrained(model_name)
+
+input_ids = tokenizer(
+    (article_text),
+    return_tensors="pt",
+    padding="max_length",
+    truncation=True,
+    max_length=512
+)["input_ids"]
+
+output_ids = model.generate(
+    input_ids=input_ids,
+    max_length=84,
+    no_repeat_ngram_size=2,
+    num_beams=4
+)[0]
+
+summary = tokenizer.decode(
+    output_ids,
+    skip_special_tokens=True,
+    clean_up_tokenization_spaces=False
+)
+
+print(summary)
+
+```

config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "Anjaan-Khadka/summarization_nepali",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "d_ff": 2048,
+  "d_kv": 64,
+  "d_model": 768,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "gelu_new",
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "gated-gelu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": true,
+  "layer_norm_epsilon": 1e-06,
+  "length_penalty": 0.6,
+  "max_length": 84,
+  "model_type": "mt5",
+  "no_repeat_ngram_size": 2,
+  "num_beams": 4,
+  "num_decoder_layers": 12,
+  "num_heads": 12,
+  "num_layers": 12,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "tie_word_embeddings": false,
+  "tokenizer_class": "T5Tokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.26.1",
+  "use_cache": true,
+  "vocab_size": 11685
+}

generation_config.json

@@ -0,0 +1,11 @@
+{
+  "_from_model_config": true,
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "length_penalty": 0.6,
+  "max_length": 84,
+  "no_repeat_ngram_size": 2,
+  "num_beams": 4,
+  "pad_token_id": 0,
+  "transformers_version": "4.26.1"
+}

new_sp.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e310b3657115be7fb48b4d8b5f36485b34fa1788753aabe419f1a82268a85d3
+size 452176

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62809fe2026bb1a5e80c2402dac2e15d59608e3ce98bbc1f364ed14e18e44298
+size 864802997

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e310b3657115be7fb48b4d8b5f36485b34fa1788753aabe419f1a82268a85d3
+size 452176