Update README.md
Browse files
README.md
CHANGED
|
@@ -21,6 +21,7 @@ tags:
|
|
| 21 |
- language-model
|
| 22 |
---
|
| 23 |
# Krutrim-1
|
|
|
|
| 24 |
|
| 25 |
## Model Overview
|
| 26 |
Krutrim Large Language Model (LLM) is a 2 trillion token multilingual foundation model designed to serve Indian demographic needs through equitable representation of the country's array of native tongues. Training data incorporates the largest known Indic language dataset, mitigating associated data scarcity obstacles that encumber model parity across dialects. Evaluations demonstrate Krutrim's strong performance on Indic language benchmarks, surpassing or at par with state-of-the-art models despite being significantly smaller in training flops. Krutrim LLM also matches or exceeds standards set on English benchmarks by models trained on comparable flops (e.g. vs LLAMA-2 on 10 out of 16 tasks with average score of 0.57 vs 0.55 of LLAMA-2), evidencing flexible multilingual fluency. Through intentional design choices that redress endemic data imbalances, Krutrim LLM signifies meaningful progress in the pursuit of ethical, globally representative AI foundation models.
|
|
|
|
| 21 |
- language-model
|
| 22 |
---
|
| 23 |
# Krutrim-1
|
| 24 |
+
[](https://huggingface.co/krutrim-ai-labs/Krutrim-1-instruct)[](https://github.com/ola-krutrim/Krutrim-1-7B)[](https://cloud.olakrutrim.com/console/inference-service?section=models&modelName=krutrim&artifactName=Krutrim-1&artifactType=model)[](https://ai-labs.olakrutrim.com/models/Krutrim-LLM-1)
|
| 25 |
|
| 26 |
## Model Overview
|
| 27 |
Krutrim Large Language Model (LLM) is a 2 trillion token multilingual foundation model designed to serve Indian demographic needs through equitable representation of the country's array of native tongues. Training data incorporates the largest known Indic language dataset, mitigating associated data scarcity obstacles that encumber model parity across dialects. Evaluations demonstrate Krutrim's strong performance on Indic language benchmarks, surpassing or at par with state-of-the-art models despite being significantly smaller in training flops. Krutrim LLM also matches or exceeds standards set on English benchmarks by models trained on comparable flops (e.g. vs LLAMA-2 on 10 out of 16 tasks with average score of 0.57 vs 0.55 of LLAMA-2), evidencing flexible multilingual fluency. Through intentional design choices that redress endemic data imbalances, Krutrim LLM signifies meaningful progress in the pursuit of ethical, globally representative AI foundation models.
|