I帽igo L贸pez-Riob贸o Botana commited on
Commit
cf9337c
1 Parent(s): e6bff60

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +20 -4
README.md CHANGED
@@ -6,14 +6,17 @@ pipeline_tag: text-generation
6
  ---
7
 
8
  # DialoGPT-medium-spanish-chitchat
 
9
  ## Description
10
 
11
- This is a **transformer-decoder** [gpt2 model](https://huggingface.co/gpt2), adapted for **single turn dialogue tasks**. We fine-tuned a [DialoGPT-medium](https://huggingface.co/microsoft/DialoGPT-medium) model from Microsoft, following the CLM (Causal Language Modelling) objective.
12
  We used one of the datasets available in the [Bot Framework Tools repository](https://github.com/microsoft/botframework-cli). We processed [the professional-styled personality chat dataset in Spanish](https://github.com/microsoft/botframework-cli/blob/main/packages/qnamaker/docs/chit-chat-dataset.md), the file is available [here](https://qnamakerstore.blob.core.windows.net/qnamakerdata/editorial/spanish/qna_chitchat_professional.tsv)
 
13
  ---
 
14
  ## Example inference script
15
 
16
- Check at this example script to run this model in inference mode:
17
 
18
  ```python
19
  import torch
@@ -39,9 +42,12 @@ for i in range(CHAT_TURNS):
39
  print(f"Step - {i} >> DialoGPT-spanish model answer -> {step_model_answer}")
40
 
41
  ```
 
42
  ---
 
43
  ## Examples
44
- * Single-turn generation examples from an interactive environment:
 
45
 
46
  |Role | Response |
47
  |---------|--------|
@@ -59,6 +65,16 @@ for i in range(CHAT_TURNS):
59
  | Bot | En realidad no tengo tanta gracia. |
60
  |User | Jajajajajajajaja |
61
  | Bot | 隆Me alegro de que te r铆as! |
 
 
 
62
  ## Fine-tuning in different dataset
63
 
64
- For fine-tuning this model, you can start from the DialoGPT base model
 
 
 
 
 
 
 
 
6
  ---
7
 
8
  # DialoGPT-medium-spanish-chitchat
9
+
10
  ## Description
11
 
12
+ This is a **transformer-decoder** [gpt2 model](https://huggingface.co/gpt2), adapted for **single turn dialogue tasks**. We fine-tuned a 345M parameters [DialoGPT-medium](https://huggingface.co/microsoft/DialoGPT-medium) model from Microsoft, following the CLM (Causal Language Modelling) objective.
13
  We used one of the datasets available in the [Bot Framework Tools repository](https://github.com/microsoft/botframework-cli). We processed [the professional-styled personality chat dataset in Spanish](https://github.com/microsoft/botframework-cli/blob/main/packages/qnamaker/docs/chit-chat-dataset.md), the file is available [here](https://qnamakerstore.blob.core.windows.net/qnamakerdata/editorial/spanish/qna_chitchat_professional.tsv)
14
+
15
  ---
16
+
17
  ## Example inference script
18
 
19
+ ### Check at this example script to run this model in inference mode
20
 
21
  ```python
22
  import torch
 
42
  print(f"Step - {i} >> DialoGPT-spanish model answer -> {step_model_answer}")
43
 
44
  ```
45
+
46
  ---
47
+
48
  ## Examples
49
+
50
+ ### Single-turn generation examples from an interactive environment
51
 
52
  |Role | Response |
53
  |---------|--------|
 
65
  | Bot | En realidad no tengo tanta gracia. |
66
  |User | Jajajajajajajaja |
67
  | Bot | 隆Me alegro de que te r铆as! |
68
+
69
+ ---
70
+
71
  ## Fine-tuning in different dataset
72
 
73
+ If you want to fine-tune this model, we recommend you to start from the [DialoGPT model](https://huggingface.co/microsoft/DialoGPT-medium).
74
+ You can check the [original GitHub repository](https://github.com/microsoft/DialoGPT).
75
+
76
+ ## Limitations
77
+
78
+ - This model is intended to be used **just for single-turn chitchat conversations in Spanish**
79
+ - This model's generation capabilities are limited to the extent of the aforementioned fine-tuning dataset
80
+ - This model generates short answers, providing general context dialogue in a professional style