Hugging Face's logo

upstage
/
Llama-2-70b-instruct

Text Generation
Transformers
PyTorch
English
llama
upstage
llama-2
instruct
instruction
text-generation-inference
Inference Endpoints
Model card Files Community
10
wonhosong commited on
Commit
f1758fb
·
1 Parent(s): 5c91a28

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -1
README.md CHANGED
@@ -65,7 +65,8 @@ We used the [lm-evaluation-harness repository](https://github.com/EleutherAI/lm-
65
  ### Main Results
66
  | Model | Average | ARC | HellaSwag | MMLU | TruthfulQA |
67
  |-----------------------------------------------|---------|-------|-----------|-------|------------|
68
- | Llama-2-70b-instruct-1024 (***Ours***, ***Local Reproduction***) | **72.0** | **70.7** | **87.4** | **69.3** | **60.7** |
 
69
  | llama-65b-instruct (***Ours***, ***Local Reproduction***) | 69.4 | 67.6 | 86.5 | 64.9 | 58.8 |
70
  | llama-30b-instruct-2048 (***Ours***, ***Open LLM Leaderboard***) | 67.0 | 64.9 | 84.9 | 61.9 | 56.3 |
71
  | Llama-2-70b-chat-hf | 66.8 | 64.6 | 85.9 | 63.9 | 52.8 |
 
65
  ### Main Results
66
  | Model | Average | ARC | HellaSwag | MMLU | TruthfulQA |
67
  |-----------------------------------------------|---------|-------|-----------|-------|------------|
68
+ | Llama-2-70b-instruct-1024 (***Ours***, ***Local Reproduction***) | **72.0** | **70.7** | **87.4** | **69.3** | **60.7** |
69
+ | Llama-2-70b-hf | 67.3 | 67.3 | 87.3 | 69.8 | 44.9 |
70
  | llama-65b-instruct (***Ours***, ***Local Reproduction***) | 69.4 | 67.6 | 86.5 | 64.9 | 58.8 |
71
  | llama-30b-instruct-2048 (***Ours***, ***Open LLM Leaderboard***) | 67.0 | 64.9 | 84.9 | 61.9 | 56.3 |
72
  | Llama-2-70b-chat-hf | 66.8 | 64.6 | 85.9 | 63.9 | 52.8 |