初始化项目，由ModelHub XC社区提供模型

Model: l3cube-pune/hing-gpt
Source: Original Platform

.gitattributes

@@ -0,0 +1,28 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin 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
+*.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
+model.safetensors filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,45 @@
+---
+language:
+- hi
+- en
+- multilingual
+license: cc-by-4.0
+tags:
+- hi
+- en
+- codemix
+datasets:
+- L3Cube-HingCorpus
+---
+
+## HingGPT
+HingGPT is a Hindi-English code-mixed GPT model trained on roman text. It is a GPT2 model trained on L3Cube-HingCorpus.
+<br>
+[dataset link] (https://github.com/l3cube-pune/code-mixed-nlp)
+
+More details on the dataset, models, and baseline results can be found in our [paper] (https://arxiv.org/abs/2204.08398)
+
+Other models from HingBERT family: <br>
+<a href="https://huggingface.co/l3cube-pune/hing-bert"> HingBERT </a> <br>
+<a href="https://huggingface.co/l3cube-pune/hing-mbert"> HingMBERT </a> <br>
+<a href="https://huggingface.co/l3cube-pune/hing-mbert-mixed"> HingBERT-Mixed </a> <br>
+<a href="https://huggingface.co/l3cube-pune/hing-mbert-mixed-v2"> HingBERT-Mixed-v2 </a> <br>
+<a href="https://huggingface.co/l3cube-pune/hing-roberta"> HingRoBERTa </a> <br>
+<a href="https://huggingface.co/l3cube-pune/hing-roberta-mixed"> HingRoBERTa-Mixed </a> <br>
+<a href="https://huggingface.co/l3cube-pune/hing-gpt"> HingGPT </a> <br>
+<a href="https://huggingface.co/l3cube-pune/hing-gpt-devanagari"> HingGPT-Devanagari </a> <br>
+<a href="https://huggingface.co/l3cube-pune/hing-bert-lid"> HingBERT-LID </a> <br>
+
+```
+@inproceedings{nayak-joshi-2022-l3cube,
+    title = "{L}3{C}ube-{H}ing{C}orpus and {H}ing{BERT}: A Code Mixed {H}indi-{E}nglish Dataset and {BERT} Language Models",
+    author = "Nayak, Ravindra  and Joshi, Raviraj",
+    booktitle = "Proceedings of the WILDRE-6 Workshop within the 13th Language Resources and Evaluation Conference",
+    month = jun,
+    year = "2022",
+    address = "Marseille, France",
+    publisher = "European Language Resources Association",
+    url = "https://aclanthology.org/2022.wildre-1.2",
+    pages = "7--12",
+}
+```

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "l3cube-pune/hing-gpt",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "gradient_checkpointing": false,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.17.0",
+  "use_cache": true,
+  "vocab_size": 50257
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d015969dbad6c6e9887e7b1f2c71fff3c203590b1b351d4f7b0be4c2838c37d1
+size 510359598

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e94d1f20ab00b66db8a6334a3bbc718df71b77db7eb8e8ac6ac4bbeef0a65e9c
+size 510401961

special_tokens_map.json

@@ -0,0 +1 @@
+{}

tokenizer_config.json

@@ -0,0 +1 @@
+{"tokenizer_class": "PreTrainedTokenizerFast"}