Update README.md
Browse files
README.md
CHANGED
@@ -7,10 +7,18 @@ base_model:
|
|
7 |
---
|
8 |
# Endurance 100B v1 🎡
|
9 |
|
10 |
-
|
11 |
-
>
|
12 |
-
> Rage, rage against the dying of the light.
|
13 |
|
14 |
![image/png](https://cdn-uploads.huggingface.co/production/uploads/65f2fd1c25b848bd061b5c2e/R2dDPDShY2VEhRzbJr-Go.png)
|
15 |
|
16 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
7 |
---
|
8 |
# Endurance 100B v1 🎡
|
9 |
|
10 |
+
*A finetune of [Lazarus 2407 100B](https://huggingface.co/TheDrummer/Lazarus-2407-100B), a pruned Mistral Large 2407 123B!*
|
|
|
|
|
11 |
|
12 |
![image/png](https://cdn-uploads.huggingface.co/production/uploads/65f2fd1c25b848bd061b5c2e/R2dDPDShY2VEhRzbJr-Go.png)
|
13 |
|
14 |
+
> Do not go gentle into that good night. Rage, rage against the dying of the light!
|
15 |
+
|
16 |
+
---
|
17 |
+
|
18 |
+
## Technical Details
|
19 |
+
|
20 |
+
*Refer to [Lazarus 2407 100B](https://huggingface.co/TheDrummer/Lazarus-2407-100B) for pruning details.*
|
21 |
+
|
22 |
+
Endurance uses the same hyperparameters as Behemoth. Training loss indicates that they are exactly the same albeit with lower confidence.
|
23 |
+
|
24 |
+
![image/png](https://cdn-uploads.huggingface.co/production/uploads/65f2fd1c25b848bd061b5c2e/s0uELhSkSSwseyBrFzw7q.png)
|