Hastagaras
commited on
Commit
•
5674eb9
1
Parent(s):
4bb743b
Update README.md
Browse files
README.md
CHANGED
@@ -11,7 +11,7 @@ license: llama3
|
|
11 |
---
|
12 |
# ANJIRRR
|
13 |
|
14 |
-
This model aims to achieve the human-like
|
15 |
|
16 |
**Model Details**
|
17 |
|
@@ -19,7 +19,7 @@ This model aims to achieve the human-like quality of the [Halu Blackroot](https:
|
|
19 |
|
20 |
**Anying:** This model is also similar to the Halu Blackroot, but instead of using the model stock, I merged the Blackroot lora manually with a very low alpha.
|
21 |
|
22 |
-
Both models have downsides. The Anjrit model lacks coherency
|
23 |
|
24 |
**I decided to merge both models with the following method:**
|
25 |
|
|
|
11 |
---
|
12 |
# ANJIRRR
|
13 |
|
14 |
+
This model aims to achieve the human-like response of the [Halu Blackroot](https://huggingface.co/Hastagaras/Halu-8B-Llama3-Blackroot), the no refusal tendencies of the [Halu OAS](Hastagaras/Halu-OAS-8B-Llama3), and the smartness of the [Standard Halu](Hastagaras/Halu-8B-Llama3-v0.3).
|
15 |
|
16 |
**Model Details**
|
17 |
|
|
|
19 |
|
20 |
**Anying:** This model is also similar to the Halu Blackroot, but instead of using the model stock, I merged the Blackroot lora manually with a very low alpha.
|
21 |
|
22 |
+
Both models have downsides. The Anjrit model **lacks coherency**, while the Anying model lacks a **human-like response**.
|
23 |
|
24 |
**I decided to merge both models with the following method:**
|
25 |
|