Update README.md
Browse files
README.md
CHANGED
@@ -15,21 +15,21 @@ language:
|
|
15 |
# Llama-3.1-8B-Fusion-8020
|
16 |
|
17 |
## Overview
|
18 |
-
`Llama-3.1-8B-Fusion-
|
19 |
**Although it's a simple mix, the model is usable, and no gibberish has appeared**.
|
20 |
This is an experiment. Later, I will test the [9:1](https://huggingface.co/huihui-ai/Llama-3.1-8B-Fusion-9010), 7:3, 6:4, and 5:5 ratios separately to see how much impact they have on the model.
|
21 |
|
22 |
## Model Details
|
23 |
- **Base Models:**
|
24 |
-
- [arcee-ai/Llama-3.1-SuperNova-Lite](https://huggingface.co/arcee-ai/Llama-3.1-SuperNova-Lite) (
|
25 |
-
- [mlabonne/Meta-Llama-3.1-8B-Instruct-abliterated](https://huggingface.co/mlabonne/Meta-Llama-3.1-8B-Instruct-abliterated) (
|
26 |
- **Model Size:** 8B parameters
|
27 |
- **Architecture:** Llama 3.1
|
28 |
- **Mixing Ratio:** 9:1 (SuperNova-Lite:Meta-Llama-3.1-8B-Instruct-abliterated)
|
29 |
|
30 |
## Key Features
|
31 |
-
- **SuperNova-Lite Contributions (
|
32 |
-
- **Meta-Llama-3.1-8B-Instruct-abliterated Contributions (
|
33 |
|
34 |
## Usage
|
35 |
You can use this mixed model in your applications by loading it with Hugging Face's `transformers` library:
|
|
|
15 |
# Llama-3.1-8B-Fusion-8020
|
16 |
|
17 |
## Overview
|
18 |
+
`Llama-3.1-8B-Fusion-8020` is a mixed model that combines the strengths of two powerful Llama-based models: [arcee-ai/Llama-3.1-SuperNova-Lite](https://huggingface.co/arcee-ai/Llama-3.1-SuperNova-Lite) and [mlabonne/Meta-Llama-3.1-8B-Instruct-abliterated](https://huggingface.co/mlabonne/Meta-Llama-3.1-8B-Instruct-abliterated). The weights are blended in a 9:1 ratio, with 90% of the weights from SuperNova-Lite and 10% from the abliterated Meta-Llama-3.1-8B-Instruct model.
|
19 |
**Although it's a simple mix, the model is usable, and no gibberish has appeared**.
|
20 |
This is an experiment. Later, I will test the [9:1](https://huggingface.co/huihui-ai/Llama-3.1-8B-Fusion-9010), 7:3, 6:4, and 5:5 ratios separately to see how much impact they have on the model.
|
21 |
|
22 |
## Model Details
|
23 |
- **Base Models:**
|
24 |
+
- [arcee-ai/Llama-3.1-SuperNova-Lite](https://huggingface.co/arcee-ai/Llama-3.1-SuperNova-Lite) (80%)
|
25 |
+
- [mlabonne/Meta-Llama-3.1-8B-Instruct-abliterated](https://huggingface.co/mlabonne/Meta-Llama-3.1-8B-Instruct-abliterated) (20%)
|
26 |
- **Model Size:** 8B parameters
|
27 |
- **Architecture:** Llama 3.1
|
28 |
- **Mixing Ratio:** 9:1 (SuperNova-Lite:Meta-Llama-3.1-8B-Instruct-abliterated)
|
29 |
|
30 |
## Key Features
|
31 |
+
- **SuperNova-Lite Contributions (80%):** Llama-3.1-SuperNova-Lite is an 8B parameter model developed by Arcee.ai, based on the Llama-3.1-8B-Instruct architecture.
|
32 |
+
- **Meta-Llama-3.1-8B-Instruct-abliterated Contributions (20%):** This is an uncensored version of Llama 3.1 8B Instruct created with abliteration.
|
33 |
|
34 |
## Usage
|
35 |
You can use this mixed model in your applications by loading it with Hugging Face's `transformers` library:
|