Instructions to use Nuo97/COMEDY_7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Nuo97/COMEDY_7B with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "question-answering" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # pip install "transformers<5.0.0" from transformers import pipeline pipe = pipeline("question-answering", model="Nuo97/COMEDY_7B")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Nuo97/COMEDY_7B") model = AutoModelForCausalLM.from_pretrained("Nuo97/COMEDY_7B", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -14,6 +14,11 @@ pipeline_tag: conversational
|
|
| 14 |
Github: https://github.com/nuochenpku/COMEDY
|
| 15 |
|
| 16 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17 |
### Task: Long-Term Conversation Dialogue Generation
|
| 18 |
|
| 19 |
Different from previous retrieval-based methods, COMEDY doesn't rely on any **retrieval module or database**.
|
|
|
|
| 14 |
Github: https://github.com/nuochenpku/COMEDY
|
| 15 |
|
| 16 |
|
| 17 |
+
<br>
|
| 18 |
+
<div align="center">
|
| 19 |
+
<img src="comedy.png" width="40%" title="Introduction Figure">
|
| 20 |
+
</div>
|
| 21 |
+
|
| 22 |
### Task: Long-Term Conversation Dialogue Generation
|
| 23 |
|
| 24 |
Different from previous retrieval-based methods, COMEDY doesn't rely on any **retrieval module or database**.
|