root
commited on
Commit
·
7bc6d2d
1
Parent(s):
56da4d9
update README
Browse files
README.md
CHANGED
|
@@ -20,7 +20,7 @@ We introduce Llama3-ChatQA-2, which bridges the gap between open-source LLMs and
|
|
| 20 |
|
| 21 |
## Overview of Benchmark Results
|
| 22 |
<!-- Results in [ChatRAG Bench](https://huggingface.co/datasets/nvidia/ChatRAG-Bench) are as follows: -->
|
| 23 |
-
|
| 24 |
|
| 25 |
|
| 26 |
<!-- | | ChatQA-2-70B | GPT-4-Turbo-2024-04-09 | Qwen2-72B-Instruct | Llama3.1-70B-Instruct |
|
|
|
|
| 20 |
|
| 21 |
## Overview of Benchmark Results
|
| 22 |
<!-- Results in [ChatRAG Bench](https://huggingface.co/datasets/nvidia/ChatRAG-Bench) are as follows: -->
|
| 23 |
+
We evaluate ChatQA 2 on short-context RAG benchmark (ChatRAG) (within 4K tokens), long context tasks from SCROLLS and LongBench (within 32K tokens), and ultra-long context tasks from In- finiteBench (beyond 100K tokens). Results are shown below.
|
| 24 |
|
| 25 |
|
| 26 |
<!-- | | ChatQA-2-70B | GPT-4-Turbo-2024-04-09 | Qwen2-72B-Instruct | Llama3.1-70B-Instruct |
|