Update README.md
Browse files
README.md
CHANGED
@@ -18,7 +18,10 @@ tags:
|
|
18 |

|
19 |
## VAGO solutions SauerkrautLM-7b-LaserChat
|
20 |
Introducing **SauerkrautLM-7b-LaserChat** – our Sauerkraut version of the powerful [openchat/openchat-3.5-0106](https://huggingface.co/openchat/openchat-3.5-0106) !
|
21 |
-
|
|
|
|
|
|
|
22 |
Fintuned with **SFT**
|
23 |
Aligned with **DPO**
|
24 |
**Using a novel training technique** using less VRAM and prevent less forgetting of the previous model while learning new specific abilities. It allows to evaluate the no free lunch theorem and make a better choice to optimize it - created by the [LaserRMT research group](https://github.com/cognitivecomputations/laserRMT)
|
|
|
18 |

|
19 |
## VAGO solutions SauerkrautLM-7b-LaserChat
|
20 |
Introducing **SauerkrautLM-7b-LaserChat** – our Sauerkraut version of the powerful [openchat/openchat-3.5-0106](https://huggingface.co/openchat/openchat-3.5-0106) !
|
21 |
+
|
22 |
+
The model "SauerkrautLM-7b-LaserChat" is a **joint effort** between **VAGO solutions** and **Hyperspace.ai.**
|
23 |
+
Much appreciation goes to the tremendous research effort of **Fernando Fernandes Neto, David Golchinfar and Eric Hartford on their laserRMT approach.**
|
24 |
+
Without their independent research collaboration this model release would not have possible.
|
25 |
Fintuned with **SFT**
|
26 |
Aligned with **DPO**
|
27 |
**Using a novel training technique** using less VRAM and prevent less forgetting of the previous model while learning new specific abilities. It allows to evaluate the no free lunch theorem and make a better choice to optimize it - created by the [LaserRMT research group](https://github.com/cognitivecomputations/laserRMT)
|