LossFunctionLover commited on
Commit
68400a5
Β·
verified Β·
1 Parent(s): 4b52705

Update MODEL_CARD.md

Browse files
Files changed (1) hide show
  1. MODEL_CARD.md +7 -7
MODEL_CARD.md CHANGED
@@ -8,7 +8,7 @@ tags:
8
  - outcome-reward-model
9
  - pairwise-preference
10
  datasets:
11
- - akleshmishra/orm-pairwise-preference-pairs
12
  metrics:
13
  - accuracy
14
  pipeline_tag: text-classification
@@ -20,7 +20,7 @@ model-index:
20
  name: Pairwise Preference Ranking
21
  dataset:
22
  name: ORM Pairwise Preference Pairs
23
- type: akleshmishra/orm-pairwise-preference-pairs
24
  metrics:
25
  - type: accuracy
26
  value: 96.3
@@ -38,7 +38,7 @@ model-index:
38
 
39
  [![Paper](https://img.shields.io/badge/Paper-ArXiv-red)](link-to-arxiv)
40
  [![Dataset](https://img.shields.io/badge/Dataset-HuggingFace-yellow)](https://huggingface.co/datasets/akleshmishra/orm-pairwise-preference-pairs)
41
- [![Code](https://img.shields.io/badge/Code-GitHub-blue)](your-github-repo)
42
 
43
  </div>
44
 
@@ -131,7 +131,7 @@ Each pair contains:
131
  ### Training Configuration
132
 
133
  **Hyperparameters:**
134
- - **Base Model**: [Specify your model, e.g., "Qwen/Qwen2.5-Math-1.5B-Instruct"]
135
  - **Trainable Parameters**: Scoring head only (~500K-1M params)
136
  - **Optimizer**: AdamW
137
  - Learning rate: 1e-4
@@ -343,15 +343,15 @@ If you use this model in your research, please cite:
343
  ## πŸ”— Resources
344
 
345
  - πŸ“„ **Paper**: [ArXiv](link-to-arxiv) (Coming soon)
346
- - πŸ’Ύ **Dataset**: [HuggingFace](https://huggingface.co/datasets/akleshmishra/orm-pairwise-preference-pairs)
347
- - πŸ’» **Code**: [GitHub](your-github-repo-url)
348
  - πŸ“Š **Training Logs**: [Weights & Biases](wandb-link) (if available)
349
 
350
  ## πŸ“§ Contact
351
 
352
  **Aklesh Mishra**
353
  - Email: akleshmishra7@gmail.com
354
- - GitHub: [@your-username](https://github.com/your-username)
355
 
356
  ## πŸ“ License
357
 
 
8
  - outcome-reward-model
9
  - pairwise-preference
10
  datasets:
11
+ - LossFunctionLover/orm-pairwise-preference-pairs
12
  metrics:
13
  - accuracy
14
  pipeline_tag: text-classification
 
20
  name: Pairwise Preference Ranking
21
  dataset:
22
  name: ORM Pairwise Preference Pairs
23
+ type: LossFunctionLover/orm-pairwise-preference-pairs
24
  metrics:
25
  - type: accuracy
26
  value: 96.3
 
38
 
39
  [![Paper](https://img.shields.io/badge/Paper-ArXiv-red)](link-to-arxiv)
40
  [![Dataset](https://img.shields.io/badge/Dataset-HuggingFace-yellow)](https://huggingface.co/datasets/akleshmishra/orm-pairwise-preference-pairs)
41
+ [![Code](https://img.shields.io/badge/Code-GitHub-blue)](https://github.com/Coder-12)
42
 
43
  </div>
44
 
 
131
  ### Training Configuration
132
 
133
  **Hyperparameters:**
134
+ - **Base Model**: facebook/OPT1.3b
135
  - **Trainable Parameters**: Scoring head only (~500K-1M params)
136
  - **Optimizer**: AdamW
137
  - Learning rate: 1e-4
 
343
  ## πŸ”— Resources
344
 
345
  - πŸ“„ **Paper**: [ArXiv](link-to-arxiv) (Coming soon)
346
+ - πŸ’Ύ **Dataset**: [HuggingFace](https://huggingface.co/datasets/LossFunctionLover/orm-pairwise-preference-pairs)
347
+ - πŸ’» **Code**: [GitHub](https://github.com/Coder-12)
348
  - πŸ“Š **Training Logs**: [Weights & Biases](wandb-link) (if available)
349
 
350
  ## πŸ“§ Contact
351
 
352
  **Aklesh Mishra**
353
  - Email: akleshmishra7@gmail.com
354
+ - GitHub: [@Coder-12](https://github.com/Coder-12)
355
 
356
  ## πŸ“ License
357