Update README.md
Browse files
README.md
CHANGED
|
@@ -55,7 +55,7 @@ pipeline_tag: text2text-generation
|
|
| 55 |
|
| 56 |
Teapot is an open-source small language model (~800 million parameters) fine-tuned on synthetic data and optimized to run locally on resource-constrained devices such as smartphones and CPUs. Teapot is trained to only answer using context from documents, reducing hallucinations. Teapot can perform a variety of tasks, including hallucination-resistant Question Answering (QnA), Retrieval-Augmented Generation (RAG), and JSON extraction. Teapot is a model built by and for the community.
|
| 57 |
|
| 58 |
-

|
| 60 |
|
| 61 |
### Conversational Question Answering
|
|
|
|
| 55 |
|
| 56 |
Teapot is an open-source small language model (~800 million parameters) fine-tuned on synthetic data and optimized to run locally on resource-constrained devices such as smartphones and CPUs. Teapot is trained to only answer using context from documents, reducing hallucinations. Teapot can perform a variety of tasks, including hallucination-resistant Question Answering (QnA), Retrieval-Augmented Generation (RAG), and JSON extraction. Teapot is a model built by and for the community.
|
| 57 |
|
| 58 |
+

|
| 59 |
[Evaluation Details](https://huggingface.co/teapotai/teapotllm#evaluation)
|
| 60 |
|
| 61 |
### Conversational Question Answering
|