ParlAI/blended_skill_talk
Viewer • Updated • 6.81k • 6.59k • 75
How to use nilotpaldhar2004/blenderbot-chatbot with Transformers:
# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
tokenizer = AutoTokenizer.from_pretrained("nilotpaldhar2004/blenderbot-chatbot")
model = AutoModelForSeq2SeqLM.from_pretrained("nilotpaldhar2004/blenderbot-chatbot")Fine-tuned facebook/blenderbot-400M-distill on blended_skill_talk
for open-domain multi-turn conversation.
| Property | Value |
|---|---|
| Base model | facebook/blenderbot-400M-distill |
| Parameters | 364.8M |
| Dataset | blended_skill_talk |
| Best Val PPL | 14.16 |
| Epochs | 2 (early stopping) |
| Learning rate | 2e-5 |
from transformers import BlenderbotTokenizer, BlenderbotForConditionalGeneration
tokenizer = BlenderbotTokenizer.from_pretrained("nilotpaldhar2004/blenderbot-chatbot")
model = BlenderbotForConditionalGeneration.from_pretrained("nilotpaldhar2004/blenderbot-chatbot")
inputs = tokenizer("Hello! How are you?", return_tensors="pt")
output = model.generate(**inputs, max_new_tokens=60, num_beams=2)
print(tokenizer.decode(output[0], skip_special_tokens=True))
Nilotpal — CS student, AI/ML
Base model
facebook/blenderbot-400M-distill