merge scgpt

.gitattributes

@@ -25,7 +25,10 @@
 *.safetensors filter=lfs diff=lfs merge=lfs -text
 saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.tar.* filter=lfs diff=lfs merge=lfs -text
+<<<<<<< HEAD
 *.tar filter=lfs diff=lfs merge=lfs -text
+=======
+>>>>>>> 23519966c9f2ad55dae4b35e50ce64a1aa17a70b
 *.tflite filter=lfs diff=lfs merge=lfs -text
 *.tgz filter=lfs diff=lfs merge=lfs -text
 *.wasm filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,3 +1,4 @@
+<<<<<<< HEAD
 The TDC Model Hub Transformers API is under development. In the meantime, we highly recommend using the native HF Transformers library and original Geneformer repo to run inference.
 
 ```python
@@ -7,3 +8,15 @@ model = AutoModel.from_pretrained("metehergul/scgpt")
 ```
 
 For further details see: https://huggingface.co/metehergul/scgpt
+=======
+All rights belong to:
+
+@misc{peng2020scgpt,
+      title={Few-shot Natural Language Generation for Task-Oriented Dialog},
+      author={Baolin Peng, Chenguang Zhu, Chunyuan Li, Xiujun Li, Jinchao Li, Michael Zeng, Jianfeng Gao},
+      archivePrefix={arXiv},
+      year={2020},
+      eprint={2002.12328},
+      primaryClass={cs.CL}
+}
+>>>>>>> 23519966c9f2ad55dae4b35e50ce64a1aa17a70b

added_tokens.json

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

config.json

@@ -0,0 +1,29 @@
+{
+  "attn_pdrop": 0.1,
+  "embd_pdrop": 0.1,
+  "finetuning_task": null,
+  "initializer_range": 0.02,
+  "is_decoder": false,
+  "layer_norm_epsilon": 1e-05,
+  "n_ctx": 1024,
+  "n_embd": 1024,
+  "n_head": 16,
+  "n_layer": 24,
+  "n_positions": 1024,
+  "n_special": 0,
+  "num_labels": 1,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "output_past": true,
+  "predict_special_tokens": true,
+  "pruned_heads": {},
+  "resid_pdrop": 0.1,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "torchscript": false,
+  "use_bfloat16": false,
+  "vocab_size": 50257
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d31775887884dfdbe4b3e2b641b9a9ea8c61d840105d55dd60b7af8dc9686a4
+size 1520021210

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": false, "max_len": 1024, "init_inputs": []}