Update README.md

README.md

@@ -3,4 +3,43 @@ license: cc-by-nc-nd-4.0
 language:
 - es
 pipeline_tag: text-generation
----
+---
+
+# DialoGPT-medium-spanish-chitchat
+## Description
+
+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.
+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)
+---
+### Example inference script
+
+Check at this example script to run this model in inference mode:
+
+```python
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+CHAT_TURNS = 5
+MAX_LENGTH=1000
+
+model = AutoModelForCausalLM.from_pretrained('ITG/DialoGPT-medium-spanish-chitchat')
+tokenizer = AutoTokenizer.from_pretrained('ITG/DialoGPT-medium-spanish-chitchat')
+device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
+model.to(device)
+for i in range(CHAT_TURNS):
+  user_input = input(f"Step - {i} >> user prompt ->")
+  with torch.no_grad():
+    # User turn, where "user_input" is the question (single-turn dialogue task)
+    user_inputs_ids = tokenizer.encode(user_input + tokenizer.eos_token, return_tensors="pt")
+    user_inputs_ids = user_inputs_ids.to(device)
+    # The chat history adds the generated tokens for the answer
+    chat_history = model.generate(user_inputs_ids, max_length=MAX_LENGTH, pad_token_id=tokenizer.eos_token_id)
+    # decode just the last generated output tokens from the model (do not include the user prompt again)
+    step_model_answer = tokenizer.decode(chat_history[:, user_inputs_ids.shape[-1]:][0], skip_special_tokens=True)
+  print(f"Step - {i} >> DialoGPT-spanish model answer -> {step_model_answer}")
+
+```
+
+### Fine-tuning in different dataset
+
+For fine-tuning this model, you can start from the DialoGPT base model