arielnlee commited on
Commit
db8fa2a
1 Parent(s): b03650d

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -4
README.md CHANGED
@@ -67,22 +67,22 @@ Each task was evaluated on 1 A100 80GB GPU.
67
 
68
  ARC:
69
  ```
70
- python main.py --model hf-causal-experimental --model_args pretrained=garage-bAInd/Platypus2-7B --tasks arc_challenge --batch_size 2 --no_cache --write_out --output_path results/Platypus2-7B/arc_challenge_25shot.json --device cuda --dtype bfloat16 --num_fewshot 25
71
  ```
72
 
73
  HellaSwag:
74
  ```
75
- python main.py --model hf-causal-experimental --model_args pretrained=garage-bAInd/Platypus2-7B --tasks hellaswag --batch_size 2 --no_cache --write_out --output_path results/Platypus2-7B/hellaswag_10shot.json --device cuda --dtype bfloat16 --num_fewshot 10
76
  ```
77
 
78
  MMLU:
79
  ```
80
- python main.py --model hf-causal-experimental --model_args pretrained=garage-bAInd/Platypus2-7B --tasks hendrycksTest-* --batch_size 2 --no_cache --write_out --output_path results/Platypus2-7B/mmlu_5shot.json --device cuda --dtype bfloat16 --num_fewshot 5
81
  ```
82
 
83
  TruthfulQA:
84
  ```
85
- python main.py --model hf-causal-experimental --model_args pretrained=garage-bAInd/Platypus2-7B --tasks truthfulqa_mc --batch_size 2 --no_cache --write_out --output_path results/Platypus2-7B/truthfulqa_0shot.json --device cuda --dtype bfloat16
86
  ```
87
  ### Limitations and bias
88
 
 
67
 
68
  ARC:
69
  ```
70
+ python main.py --model hf-causal-experimental --model_args pretrained=garage-bAInd/Platypus2-7B,use_accelerate=True,dtype="bfloat16" --tasks arc_challenge --batch_size 2 --no_cache --write_out --output_path results/Platypus2-7B/arc_challenge_25shot.json --device cuda --num_fewshot 25
71
  ```
72
 
73
  HellaSwag:
74
  ```
75
+ python main.py --model hf-causal-experimental --model_args pretrained=garage-bAInd/Platypus2-7B,use_accelerate=True,dtype="bfloat16" --tasks hellaswag --batch_size 2 --no_cache --write_out --output_path results/Platypus2-7B/hellaswag_10shot.json --device cuda --num_fewshot 10
76
  ```
77
 
78
  MMLU:
79
  ```
80
+ python main.py --model hf-causal-experimental --model_args pretrained=garage-bAInd/Platypus2-7B,use_accelerate=True,dtype="bfloat16" --tasks hendrycksTest-* --batch_size 2 --no_cache --write_out --output_path results/Platypus2-7B/mmlu_5shot.json --device cuda --num_fewshot 5
81
  ```
82
 
83
  TruthfulQA:
84
  ```
85
+ python main.py --model hf-causal-experimental --model_args pretrained=garage-bAInd/Platypus2-7B,use_accelerate=True,dtype="bfloat16" --tasks truthfulqa_mc --batch_size 2 --no_cache --write_out --output_path results/Platypus2-7B/truthfulqa_0shot.json --device cuda
86
  ```
87
  ### Limitations and bias
88