Adding Evaluation Results

#1
Files changed (1) hide show
  1. README.md +14 -1
README.md CHANGED
@@ -16,4 +16,17 @@ model = AutoModelForCausalLM.from_pretrained(
16
  load_in_4bit=True)
17
  tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
18
 
19
- ```
 
 
 
 
 
 
 
 
 
 
 
 
 
 
16
  load_in_4bit=True)
17
  tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
18
 
19
+ ```
20
+ # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
21
+ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_guardrail__llama-2-7b-guanaco-instruct-sharded)
22
+
23
+ | Metric | Value |
24
+ |-----------------------|---------------------------|
25
+ | Avg. | 44.87 |
26
+ | ARC (25-shot) | 53.75 |
27
+ | HellaSwag (10-shot) | 78.69 |
28
+ | MMLU (5-shot) | 46.65 |
29
+ | TruthfulQA (0-shot) | 43.93 |
30
+ | Winogrande (5-shot) | 72.61 |
31
+ | GSM8K (5-shot) | 7.81 |
32
+ | DROP (3-shot) | 10.65 |