legolasyiu commited on
Commit
ff006c4
·
verified ·
1 Parent(s): 5cf4fca

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -95,6 +95,7 @@ Both gpt-oss models can be fine-tuned for a variety of specialized use cases.
95
  - Do not use this model for creating nuclear, biological and chemical weapons.
96
  - Do not allow harmful or malicious outputs
97
 
 
98
  Code to duplicate the benchmark (Using +std for final result)
99
  ```py
100
 
@@ -107,7 +108,6 @@ Code to duplicate the benchmark (Using +std for final result)
107
 
108
  ```
109
 
110
- ## Benchmark
111
  hf (pretrained=EpistemeAI/metatune-gpt20b-R1.1,parallelize=True,dtype=bfloat16), gen_kwargs: (temperature=0.9,top_p=0.9,max_new_tokens=2048), limit: 10.0, num_fewshot: 0, batch_size: auto:4
112
  | Tasks |Version| Filter |n-shot| Metric |metatune R1.2(high)| metatune R1.1|metatune R0|
113
  |-------------------------|------:|----------------|:-----|-----------|:------------|:-----------|:----------|
 
95
  - Do not use this model for creating nuclear, biological and chemical weapons.
96
  - Do not allow harmful or malicious outputs
97
 
98
+ ## Benchmark
99
  Code to duplicate the benchmark (Using +std for final result)
100
  ```py
101
 
 
108
 
109
  ```
110
 
 
111
  hf (pretrained=EpistemeAI/metatune-gpt20b-R1.1,parallelize=True,dtype=bfloat16), gen_kwargs: (temperature=0.9,top_p=0.9,max_new_tokens=2048), limit: 10.0, num_fewshot: 0, batch_size: auto:4
112
  | Tasks |Version| Filter |n-shot| Metric |metatune R1.2(high)| metatune R1.1|metatune R0|
113
  |-------------------------|------:|----------------|:-----|-----------|:------------|:-----------|:----------|