Update README.md
Browse files
README.md
CHANGED
@@ -2,19 +2,61 @@
|
|
2 |
license: apache-2.0
|
3 |
tags:
|
4 |
- merge
|
5 |
-
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
6 |
- lazymergekit
|
7 |
- nbeerbower/Llama3.1-Allades-8B
|
8 |
- mergekit-community/L3.1-Pneuma-8B-v1
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
9 |
---
|
10 |
|
11 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
12 |
|
13 |
-
|
14 |
-
* [nbeerbower/Llama3.1-Allades-8B](https://huggingface.co/nbeerbower/Llama3.1-Allades-8B)
|
15 |
-
* [mergekit-community/L3.1-Pneuma-8B-v1](https://huggingface.co/mergekit-community/L3.1-Pneuma-8B-v1)
|
16 |
|
17 |
-
|
18 |
|
19 |
```yaml
|
20 |
out_dtype: bfloat16
|
@@ -56,4 +98,37 @@ models:
|
|
56 |
- filter: down_proj
|
57 |
value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
|
58 |
- value: 0
|
59 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2 |
license: apache-2.0
|
3 |
tags:
|
4 |
- merge
|
5 |
+
- model_stock
|
6 |
+
- Llama3
|
7 |
+
- Pneuma
|
8 |
+
- Allades
|
9 |
+
- storytelling
|
10 |
+
- roleplaying
|
11 |
+
- instruction-following
|
12 |
+
- creative-writing
|
13 |
+
- reasoning
|
14 |
+
- long-form-generation
|
15 |
+
- text-generation
|
16 |
- lazymergekit
|
17 |
- nbeerbower/Llama3.1-Allades-8B
|
18 |
- mergekit-community/L3.1-Pneuma-8B-v1
|
19 |
+
base_model:
|
20 |
+
- mergekit-community/L3.1-Pneuma-8B-v1
|
21 |
+
- nbeerbower/Llama3.1-Allades-8B
|
22 |
+
pipeline_tag: text-generation
|
23 |
+
---
|
24 |
+
|
25 |
+
|
26 |
+
# **L3.1-Pneuma-Allades-8B**
|
27 |
+
|
28 |
+
**L3.1-Pneuma-Allades-8B** is a unique 8B parameter model, carefully merged using the **della_linear** method to integrate the best qualities of two exceptional models: **L3.1-Pneuma-8B-v1** and **Llama3.1-Allades-8B**. This model is finely tuned to handle advanced tasks in **creative writing**, **reasoning**, **roleplay**, and **instruction-following**.
|
29 |
+
|
30 |
+
This model is designed for anyone seeking to enhance AI-assisted storytelling, detailed reasoning, or dynamic interactive dialogues. The combination of the Pneuma and Allades models ensures a well-balanced performance in both technical and creative realms. 🧠✨
|
31 |
+
|
32 |
---
|
33 |
|
34 |
+
## 🌐 **Family Tree**
|
35 |
+
|
36 |
+
This model is the result of a fusion between the following:
|
37 |
+
|
38 |
+
- [**mergekit-community/L3.1-Pneuma-8B-v1**](https://huggingface.co/mergekit-community/L3.1-Pneuma-8B-v1): A comprehensive 8B model designed to excel in logical reasoning and long-form content generation. It was merged with a focus on **instruction-following** and **roleplaying**.
|
39 |
+
- [**nbeerbower/Llama3.1-Allades-8B**](https://huggingface.co/nbeerbower/Llama3.1-Allades-8B): A finetuned Llama 3.1 model, focused on **creative writing**, **reasoning**, and **roleplay**. Trained with a mix of public and private datasets to push the boundaries of creativity and interaction in AI language models.
|
40 |
+
|
41 |
+
---
|
42 |
+
|
43 |
+
## 🧬 **Model Lineage**
|
44 |
+
|
45 |
+
### **A: mergekit-community/L3.1-Pneuma-8B-v1**
|
46 |
+
|
47 |
+
- Designed for advanced **reasoning** tasks, particularly in creative problem solving and interactive roleplay scenarios.
|
48 |
+
- This model leverages the strength of **instruction-following** tasks with a highly optimized configuration, making it a robust choice for interactive experiences.
|
49 |
+
|
50 |
+
### **B: nbeerbower/Llama3.1-Allades-8B**
|
51 |
+
|
52 |
+
- Tuned with **creative writing**, **storytelling**, and **dynamic roleplay** in mind.
|
53 |
+
- It integrates five datasets that focus on reasoning, storytelling, and narrative structure, providing a well-rounded experience for **creative and logical task performance**.
|
54 |
+
|
55 |
+
---
|
56 |
|
57 |
+
## ⚙️ **Merge Details**
|
|
|
|
|
58 |
|
59 |
+
The **L3.1-Pneuma-Allades-8B** model was merged using the **della_linear** method, ensuring a balanced integration of the two base models' distinct strengths. Here’s the exact configuration used for the merge:
|
60 |
|
61 |
```yaml
|
62 |
out_dtype: bfloat16
|
|
|
98 |
- filter: down_proj
|
99 |
value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
|
100 |
- value: 0
|
101 |
+
|
102 |
+
```
|
103 |
+
|
104 |
+
---
|
105 |
+
|
106 |
+
## 🔮 **Key Features & Capabilities**
|
107 |
+
|
108 |
+
### **1. Instruction Following**:
|
109 |
+
|
110 |
+
- **Pneuma's** structure allows this model to excel in **precise instruction-following** tasks, ensuring clear and coherent responses.
|
111 |
+
|
112 |
+
### **2. Creative Writing & Storytelling**:
|
113 |
+
|
114 |
+
- With **Allades'** fine-tuned datasets, this model is capable of generating detailed and creative narratives, perfect for roleplaying, interactive storytelling, and fantasy creation.
|
115 |
+
|
116 |
+
### **3. Dynamic Roleplay**:
|
117 |
+
|
118 |
+
- Combining the **reasoning power** of Pneuma with **Allades' focus** on roleplay and creativity, this model can generate interactive, logical, and emotionally-driven dialogues in any roleplay scenario.
|
119 |
+
|
120 |
+
---
|
121 |
+
|
122 |
+
## 🚀 **Use Cases**
|
123 |
+
|
124 |
+
- **Immersive Storytelling**: Whether you’re writing a novel, developing interactive character dialogue, or creating a magical world, this model offers both creativity and structure.
|
125 |
+
- **Instructional Content**: From educational guides to complex instructional scenarios, this model adapts well to delivering step-by-step processes in a clear and structured format.
|
126 |
+
- **AI-Assisted Roleplay**: Perfect for game development, NPC dialogues, and other roleplaying applications where both **logic** and **creativity** are required.
|
127 |
+
|
128 |
+
---
|
129 |
+
|
130 |
+
## 📜 **License**
|
131 |
+
|
132 |
+
This model is open-sourced under the **Apache-2.0 License**, allowing free use, modification, and distribution with proper attribution.
|
133 |
+
|
134 |
+
---
|