hawei commited on
Commit
1cfd3f7
·
verified ·
1 Parent(s): 50abae0

Update model card with benchmark data source

Browse files
Files changed (1) hide show
  1. README.md +6 -2
README.md CHANGED
@@ -12,8 +12,10 @@ model-index:
12
  - task:
13
  type: math-evaluation
14
  dataset:
15
- type: nvidia/OpenMathInstruct-2
16
  name: OpenMathInstruct
 
 
17
  metrics:
18
  - name: exact_match,none
19
  type: exact_match
@@ -40,6 +42,8 @@ model-index:
40
  dataset:
41
  type: meta/arc-dataset
42
  name: Meta-ARC Dataset
 
 
43
  metrics:
44
  - name: exact_match,strict-match
45
  type: exact_match
@@ -68,4 +72,4 @@ model-index:
68
  verified: false
69
  ---
70
  # Control-LLM-Llama3.1-8B-Math16
71
- This is a fine-tuned model of Llama-3.1-8B-Instruct for mathematical tasks on OpenMath2 dataset.
 
12
  - task:
13
  type: math-evaluation
14
  dataset:
15
+ type: parquet
16
  name: OpenMathInstruct
17
+ dataset_kwargs:
18
+ data_files: "/home/jobuser/controlllm/inference/llm_eval_harness/additional_tasks/math/joined_math.parquet"
19
  metrics:
20
  - name: exact_match,none
21
  type: exact_match
 
42
  dataset:
43
  type: meta/arc-dataset
44
  name: Meta-ARC Dataset
45
+ dataset_path: "meta-llama/llama-3.1-8_b-instruct-evals"
46
+ dataset_name: "Llama-3.1-8B-Instruct-evals__arc_challenge__details"
47
  metrics:
48
  - name: exact_match,strict-match
49
  type: exact_match
 
72
  verified: false
73
  ---
74
  # Control-LLM-Llama3.1-8B-Math16
75
+ This is a fine-tuned model of Llama-3.1-8B-Instruct for mathematical tasks on OpenMath2 dataset.