Spaces:
Running
Running
Add founder line to org card
Browse files
README.md
CHANGED
|
@@ -10,6 +10,8 @@ pinned: false
|
|
| 10 |
|
| 11 |
**Generating Real Intelligence.** We build AI models and make them small and fast enough to run on hardware people already own.
|
| 12 |
|
|
|
|
|
|
|
| 13 |
## Pingala-8: 2-bit LLMs for llama.cpp, no retraining
|
| 14 |
|
| 15 |
- **85% smaller:** Qwen3-4B goes from 8.05 GB to 1.24 GB, and Llama 3.1 8B from 16.08 GB to 2.39 GB.
|
|
|
|
| 10 |
|
| 11 |
**Generating Real Intelligence.** We build AI models and make them small and fast enough to run on hardware people already own.
|
| 12 |
|
| 13 |
+
Founded by Harshit Goyal, former Google software engineer and IIIT Delhi alumnus.
|
| 14 |
+
|
| 15 |
## Pingala-8: 2-bit LLMs for llama.cpp, no retraining
|
| 16 |
|
| 17 |
- **85% smaller:** Qwen3-4B goes from 8.05 GB to 1.24 GB, and Llama 3.1 8B from 16.08 GB to 2.39 GB.
|