Update README.md
Browse files
README.md
CHANGED
|
@@ -15,6 +15,8 @@ tags:
|
|
| 15 |
## Model Details
|
| 16 |
We introduce ChatQA-1.5, which excels at conversational question answering (QA) and retrieval-augumented generation (RAG). ChatQA-1.5 is built using the training recipe from [ChatQA (1.0)](https://arxiv.org/abs/2401.10225), and it is built on top of Llama-3 foundation model. Additionally, we incorporate more conversational QA data to enhance its tabular and arithmatic calculation capability. ChatQA-1.5 has two variants: ChatQA-1.5-8B and ChatQA-1.5-70B. Both models were originally trained using [Megatron-LM](https://github.com/NVIDIA/Megatron-LM), we converted the checkpoints to Hugging Face format.
|
| 17 |
|
|
|
|
|
|
|
| 18 |
|
| 19 |
## Benchmark Results
|
| 20 |
Results in ConvRAG Bench are as follows:
|
|
|
|
| 15 |
## Model Details
|
| 16 |
We introduce ChatQA-1.5, which excels at conversational question answering (QA) and retrieval-augumented generation (RAG). ChatQA-1.5 is built using the training recipe from [ChatQA (1.0)](https://arxiv.org/abs/2401.10225), and it is built on top of Llama-3 foundation model. Additionally, we incorporate more conversational QA data to enhance its tabular and arithmatic calculation capability. ChatQA-1.5 has two variants: ChatQA-1.5-8B and ChatQA-1.5-70B. Both models were originally trained using [Megatron-LM](https://github.com/NVIDIA/Megatron-LM), we converted the checkpoints to Hugging Face format.
|
| 17 |
|
| 18 |
+
## Other Resources
|
| 19 |
+
[ChatQA-1.5-70B](https://huggingface.co/nvidia/ChatQA-1.5-70B)   [Evaluation Data](https://huggingface.co/datasets/nvidia/ConvRAG-Bench)   [Training Data](https://huggingface.co/datasets/nvidia/ChatQA-Training-Data)   [Retriever](https://huggingface.co/nvidia/dragon-multiturn-query-encoder)
|
| 20 |
|
| 21 |
## Benchmark Results
|
| 22 |
Results in ConvRAG Bench are as follows:
|