Update README.md
Browse files
README.md
CHANGED
|
@@ -1,5 +1,4 @@
|
|
| 1 |
---
|
| 2 |
-
license: unknown
|
| 3 |
base_model:
|
| 4 |
- mistralai/Mistral-7B-Instruct-v0.2
|
| 5 |
tags:
|
|
@@ -11,6 +10,7 @@ tags:
|
|
| 11 |
library_name: transformers
|
| 12 |
---
|
| 13 |
|
|
|
|
| 14 |
# CLaRa-7B-Instruct (Compression-16 & 128)
|
| 15 |
|
| 16 |
The **CLaRa-7B-Instruct** model is our instruction-tuned unified RAG model with built-in semantic document compression (16× & 128x).
|
|
@@ -25,6 +25,8 @@ It supports instruction-following QA directly from compressed document represent
|
|
| 25 |
|
| 26 |
Paper: [CLaRa: Bridging Retrieval and Generation with Continuous Latent Reasoning](https://arxiv.org/abs/2511.18659)
|
| 27 |
GitHub: https://github.com/apple/ml-clara
|
|
|
|
|
|
|
| 28 |
|
| 29 |
---
|
| 30 |
|
|
|
|
| 1 |
---
|
|
|
|
| 2 |
base_model:
|
| 3 |
- mistralai/Mistral-7B-Instruct-v0.2
|
| 4 |
tags:
|
|
|
|
| 10 |
library_name: transformers
|
| 11 |
---
|
| 12 |
|
| 13 |
+
|
| 14 |
# CLaRa-7B-Instruct (Compression-16 & 128)
|
| 15 |
|
| 16 |
The **CLaRa-7B-Instruct** model is our instruction-tuned unified RAG model with built-in semantic document compression (16× & 128x).
|
|
|
|
| 25 |
|
| 26 |
Paper: [CLaRa: Bridging Retrieval and Generation with Continuous Latent Reasoning](https://arxiv.org/abs/2511.18659)
|
| 27 |
GitHub: https://github.com/apple/ml-clara
|
| 28 |
+
Video (from @Fahd Mirza): https://youtu.be/al2VoAKn8GU?si=Q8bq7QNMaTvcArwa
|
| 29 |
+
|
| 30 |
|
| 31 |
---
|
| 32 |
|