PyTorch
mistral
Krutrim
language-model
krutrim-admin commited on
Commit
33d9699
·
verified ·
1 Parent(s): 0d1d15a

Minor updates in the description

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -26,7 +26,7 @@ widget:
26
  # Krutrim-2
27
 
28
  ## Model Overview
29
- Krutrim-2 is a 12B parameter language model developed by the OLA Krutrim team. It is built on the Mistral-NeMo 12B architecture and trained across various domains, including web data, code, math, Indic languages, Indian context data, synthetic data, and books. Following pretraining, the model was finetuned on diverse data covering a wide range of tasks, including knowledge recall, math, reasoning, coding, safety & non-compliance, instruction following and creative writing.
30
 
31
  After fine-tuning, the model underwent Direct Preference Optimization (DPO) to enhance alignment across multiple aspects. DPO was applied to improve response helpfulness, safety, and compliance, making the model more robust against harmful prompts, reducing biases, and improving factual consistency.
32
 
 
26
  # Krutrim-2
27
 
28
  ## Model Overview
29
+ Krutrim-2 is a 12B parameter language model developed by the OLA Krutrim team. It is built on the Mistral-NeMo 12B architecture and trained across various domains, including web data, code, math, Indic languages, Indian context data, synthetic data, and books. Following pretraining, the model was finetuned for instruction following on diverse data covering a wide range of tasks, including knowledge recall, math, reasoning, coding, safety, and creative writing.
30
 
31
  After fine-tuning, the model underwent Direct Preference Optimization (DPO) to enhance alignment across multiple aspects. DPO was applied to improve response helpfulness, safety, and compliance, making the model more robust against harmful prompts, reducing biases, and improving factual consistency.
32