Update from macbook
Browse files- README.md +48 -0
- config.json +36 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- vocab.json +0 -0
README.md
ADDED
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
|
3 |
+
thumbnail: https://huggingface.co/front/thumbnails/dialogpt.png
|
4 |
+
|
5 |
+
tags:
|
6 |
+
|
7 |
+
- conversational
|
8 |
+
|
9 |
+
license: mit
|
10 |
+
|
11 |
+
---
|
12 |
+
|
13 |
+
# DialoGPT Trained on the Speech of a Game Character
|
14 |
+
|
15 |
+
This is an instance of [microsoft/DialoGPT-small](https://huggingface.co/microsoft/DialoGPT-small) trained on a game character, Neku Sakuraba from [The World Ends With You](https://en.wikipedia.org/wiki/The_World_Ends_with_You). The data comes from [a Kaggle game script dataset](https://www.kaggle.com/ruolinzheng/twewy-game-script).
|
16 |
+
|
17 |
+
Chat with the model:
|
18 |
+
|
19 |
+
```python
|
20 |
+
from transformers import AutoTokenizer, AutoModelWithLMHead
|
21 |
+
|
22 |
+
tokenizer = AutoTokenizer.from_pretrained("r3dhummingbird/DialoGPT-small-neku")
|
23 |
+
|
24 |
+
model = AutoModelWithLMHead.from_pretrained("r3dhummingbird/DialoGPT-small-neku")
|
25 |
+
|
26 |
+
# Let's chat for 4 lines
|
27 |
+
for step in range(4):
|
28 |
+
# encode the new user input, add the eos_token and return a tensor in Pytorch
|
29 |
+
new_user_input_ids = tokenizer.encode(input(">> User:") + tokenizer.eos_token, return_tensors='pt')
|
30 |
+
# print(new_user_input_ids)
|
31 |
+
|
32 |
+
# append the new user input tokens to the chat history
|
33 |
+
bot_input_ids = torch.cat([chat_history_ids, new_user_input_ids], dim=-1) if step > 0 else new_user_input_ids
|
34 |
+
|
35 |
+
# generated a response while limiting the total chat history to 1000 tokens,
|
36 |
+
chat_history_ids = model.generate(
|
37 |
+
bot_input_ids, max_length=200,
|
38 |
+
pad_token_id=tokenizer.eos_token_id,
|
39 |
+
no_repeat_ngram_size=3,
|
40 |
+
do_sample=True,
|
41 |
+
top_k=100,
|
42 |
+
top_p=0.7,
|
43 |
+
temperature=0.8
|
44 |
+
)
|
45 |
+
|
46 |
+
# pretty print last ouput tokens from bot
|
47 |
+
print("NekuBot: {}".format(tokenizer.decode(chat_history_ids[:, bot_input_ids.shape[-1]:][0], skip_special_tokens=True)))
|
48 |
+
```
|
config.json
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "output-small-neku",
|
3 |
+
"activation_function": "gelu_new",
|
4 |
+
"architectures": [
|
5 |
+
"GPT2LMHeadModel"
|
6 |
+
],
|
7 |
+
"attn_pdrop": 0.1,
|
8 |
+
"bos_token_id": 50256,
|
9 |
+
"embd_pdrop": 0.1,
|
10 |
+
"eos_token_id": 50256,
|
11 |
+
"gradient_checkpointing": false,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"layer_norm_epsilon": 1e-05,
|
14 |
+
"model_type": "gpt2",
|
15 |
+
"n_ctx": 1024,
|
16 |
+
"n_embd": 768,
|
17 |
+
"n_head": 12,
|
18 |
+
"n_inner": null,
|
19 |
+
"n_layer": 12,
|
20 |
+
"n_positions": 1024,
|
21 |
+
"resid_pdrop": 0.1,
|
22 |
+
"scale_attn_weights": true,
|
23 |
+
"summary_activation": null,
|
24 |
+
"summary_first_dropout": 0.1,
|
25 |
+
"summary_proj_to_labels": true,
|
26 |
+
"summary_type": "cls_index",
|
27 |
+
"summary_use_proj": true,
|
28 |
+
"task_specific_params": {
|
29 |
+
"conversational": {
|
30 |
+
"max_length": 1000
|
31 |
+
}
|
32 |
+
},
|
33 |
+
"transformers_version": "4.6.1",
|
34 |
+
"use_cache": true,
|
35 |
+
"vocab_size": 50257
|
36 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:65ff7877b858d08b0949e2af6613497c86f361cb9948aa052eacc380e5d84443
|
3 |
+
size 510405883
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "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"}, "add_prefix_space": false, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "microsoft/DialoGPT-small", "errors": "replace"}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|