add model

README.md

@@ -0,0 +1,59 @@
+---
+language: "en"
+tags:
+- counterfactual generation
+widget:
+- text: "It is great for kids. <perturb> [negation] It [BLANK] great for kids. [SEP]"
+---
+
+# Erised
+
+## Model description
+
+This is a ported version of [Erised](https://homes.cs.washington.edu/~wtshuang/static/papers/2021-arxiv-polyjuice.pdf), the general-purpose counterfactual generator.
+
+#### How to use
+
+```python
+from transformers import AutoTokenizer, AutoModelWithLMHead
+
+tokenizer = AutoTokenizer.from_pretrained("uw-hai/jolyjuice")
+model = AutoModelWithLMHead.from_pretrained("uw-hai/jolyjuice")
+
+
+prompt_text = "It is great for kids. <perturb> [negation] It [BLANK] great for kids. [SEP]"
+perturb_tok, end_tok = "<|perturb|>", "<|endoftext|>"
+encoded_prompt = tokenizer.encode(prompt_text, add_special_tokens=False, return_tensors="pt")
+input_ids = encoded_prompt
+stop_token= '\n'
+repetition_penalty=1
+output_sequences = model.generate(
+    input_ids=input_ids,
+    max_length=100 + len(encoded_prompt[0]),
+    temperature=0.1,
+    num_beams=10,
+    num_return_sequences=3)
+
+if len(output_sequences.shape) > 2:
+    output_sequences.squeeze_()
+
+for generated_sequence_idx, generated_sequence in enumerate(output_sequences):
+    generated_sequence = generated_sequence.tolist()
+    # Decode text
+    text = tokenizer.decode(generated_sequence, clean_up_tokenization_spaces=True)
+    # Remove all text after the stop token
+    text = text[: text.find(stop_token) if stop_token and text.find(stop_token)>-1 else None]
+    text = text[: text.find(end_tok) if end_tok and text.find(end_tok)>-1 else None]
+    print(text)
+```
+
+### BibTeX entry and citation info
+
+```bibtex
+@article{wu2021polyjuice,
+  title={Polyjuice: Automated, General-purpose Counterfactual Generation},
+  author = {Wu, Tongshuang and Ribeiro, Marco Tulio and Heer, Jeffrey and Weld Daniel S.},
+  journal={arXiv preprint},
+  year={2021}
+}
+```

config.json

@@ -0,0 +1,33 @@
+{
+  "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,
+  "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,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "vocab_size": 50257
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf8ed7c2e3b26b8a4d53e59f814b9fa03ae06d552ef08fc5f3f3bea4667e0406
+size 510408315

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}}

tokenizer_config.json

@@ -0,0 +1 @@
+{"bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "model_max_length": 1024}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:043dbd5dd0744b2a7a925444abcf14b69fc74480e21f2eb163d4deb3381eba98
+size 1839