upstage
/

llama-30b-instruct-2048

Text Generation

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

Limerobot commited on Jul 25, 2023

Commit

3b060bc

·

1 Parent(s): abb2842

Update README.md

Files changed (1) hide show

README.md +4 -3

README.md CHANGED Viewed

@@ -66,10 +66,11 @@ We used the [lm-evaluation-harness repository](https://github.com/EleutherAI/lm-
 ### Main Results
 | Model                                         | Average | ARC   | HellaSwag | MMLU  | TruthfulQA |
 |-----------------------------------------------|---------|-------|-----------|-------|------------|
-| llama-65b-instruct (***Ours***, ***Local Reproduction***) | **69.4** | **67.6** | **86.5** | **64.9** | **58.8** |
-| llama-30b-instruct-2048 (***Ours***, ***Open LLM Leaderboard***) | 67.0 | 64.9 | 84.9 | 61.9 | 56.3 |
 | Llama-2-70b-chat-hf | 66.8 | 64.6 | 85.9 | 63.9 | 52.8 |
-| llama-30b-instruct (***Ours***, ***Open LLM Leaderboard***) | 65.2 | 62.5 | 86.2 | 59.4 | 52.8 |
 | falcon-40b-instruct | 63.4 | 61.6 | 84.3 | 55.4 | 52.5 |
 | llama-65b | 62.1 | 57.6 | 84.3 | 63.4 | 43.0 |

 ### Main Results
 | Model                                         | Average | ARC   | HellaSwag | MMLU  | TruthfulQA |
 |-----------------------------------------------|---------|-------|-----------|-------|------------|
+| Llama-2-70b-instruct-1024 (Ours, Local Reproduction) | 72.0 | 70.7 | 87.4 | 69.3 | 60.7 |
+| llama-65b-instruct (Ours, Local Reproduction) | 69.4 | 67.6 | 86.5 | 64.9 | 58.8 |
+| **llama-30b-instruct-2048** (***Ours***, ***Open LLM Leaderboard***) | **67.0** | **64.9** | **84.9** | **61.9** | **56.3** |
 | Llama-2-70b-chat-hf | 66.8 | 64.6 | 85.9 | 63.9 | 52.8 |
+| llama-30b-instruct (Ours, Open LLM Leaderboard) | 65.2 | 62.5 | 86.2 | 59.4 | 52.8 |
 | falcon-40b-instruct | 63.4 | 61.6 | 84.3 | 55.4 | 52.5 |
 | llama-65b | 62.1 | 57.6 | 84.3 | 63.4 | 43.0 |