inflatebot
commited on
Create README.md
Browse files
README.md
CHANGED
@@ -9,11 +9,23 @@ tags:
|
|
9 |
- merge
|
10 |
|
11 |
---
|
|
|
|
|
12 |
# merge
|
13 |
|
14 |
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
15 |
|
16 |
## Merge Details
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
17 |
### Merge Method
|
18 |
|
19 |
This model was merged using the [task arithmetic](https://arxiv.org/abs/2212.04089) merge method using [NousResearch/Meta-Llama-3-8B](https://huggingface.co/NousResearch/Meta-Llama-3-8B) as a base.
|
@@ -35,7 +47,7 @@ models:
|
|
35 |
weight: 0.5
|
36 |
- model: Fizzarolli/L3-8b-Rosier-v1
|
37 |
parameters:
|
38 |
-
weight: 0.
|
39 |
|
40 |
merge_method: task_arithmetic
|
41 |
base_model: NousResearch/Meta-Llama-3-8B
|
|
|
9 |
- merge
|
10 |
|
11 |
---
|
12 |
+
![By NovelAI](https://huggingface.co/inflatebot/helide-alpha-r2/resolve/main/img.png)
|
13 |
+
`"Helide" (say HE-lied) is an ion of helium -- famously a very unreactive element, which doesn't form ions in most conditions.`
|
14 |
# merge
|
15 |
|
16 |
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
17 |
|
18 |
## Merge Details
|
19 |
+
|
20 |
+
An experimental merge of the legendary L3-8B-Stheno with Fizzarolli's Rosier. The aim is to improve Stheno's "ball-rolling" capabilities and reduce its awkwardness with more niche content. For a first go, I'm surprised at how well it's doing so far, but given that this is literally my first LLM project ever, probably temper your expectations.
|
21 |
+
|
22 |
+
Since R1: Changed to task-arithmetic. Snazzy new model card image.
|
23 |
+
|
24 |
+
Since R2: Fixed unnecessary conversion.
|
25 |
+
|
26 |
+
Since R3: Tweaked ratios, Rosier's influence cut in half.
|
27 |
+
|
28 |
+
Since R4: Scrubbin' it down. +0.13 to Rosier. Closing in on a good ratio.
|
29 |
### Merge Method
|
30 |
|
31 |
This model was merged using the [task arithmetic](https://arxiv.org/abs/2212.04089) merge method using [NousResearch/Meta-Llama-3-8B](https://huggingface.co/NousResearch/Meta-Llama-3-8B) as a base.
|
|
|
47 |
weight: 0.5
|
48 |
- model: Fizzarolli/L3-8b-Rosier-v1
|
49 |
parameters:
|
50 |
+
weight: 0.25
|
51 |
|
52 |
merge_method: task_arithmetic
|
53 |
base_model: NousResearch/Meta-Llama-3-8B
|