Update README.md
Browse files
README.md
CHANGED
@@ -1,24 +1,27 @@
|
|
1 |
-
---
|
2 |
-
base_model:
|
3 |
-
- ruslandev/llama-3-8b-samantha
|
4 |
-
- MathGenie/MathCoder2-Llama-3-8B
|
5 |
-
- nvidia/OpenMath2-Llama3.1-8B
|
6 |
-
- NeverSleep/Llama-3-Lumimaid-8B-v0.1-OAS
|
7 |
-
- TsinghuaC3I/Llama-3.1-8B-UltraMedical
|
8 |
-
- tohur/natsumura-storytelling-rp-1.0-llama-3.1-8b
|
9 |
-
- Skywork/Skywork-o1-Open-Llama-3.1-8B
|
10 |
-
- Undi95/Llama-3-LewdPlay-8B
|
11 |
-
- Locutusque/Hercules-6.1-Llama-3.1-8B
|
12 |
-
- RefuelAI/Llama-3-Refueled
|
13 |
-
- rombodawg/Llama-3-8B-Instruct-Coder
|
14 |
-
library_name: transformers
|
15 |
-
tags:
|
16 |
-
- mergekit
|
17 |
-
- merge
|
18 |
-
|
19 |
-
---
|
20 |
# Llamaverse 8B
|
21 |
|
|
|
|
|
|
|
22 |
This model was merged using the [Model Stock](https://arxiv.org/abs/2403.19522) merge method using [MathGenie/MathCoder2-Llama-3-8B](https://huggingface.co/MathGenie/MathCoder2-Llama-3-8B) as a base.
|
23 |
|
24 |
### Models Merged
|
@@ -35,6 +38,26 @@ The following models were included in the merge:
|
|
35 |
* [RefuelAI/Llama-3-Refueled](https://huggingface.co/RefuelAI/Llama-3-Refueled)
|
36 |
* [rombodawg/Llama-3-8B-Instruct-Coder](https://huggingface.co/rombodawg/Llama-3-8B-Instruct-Coder)
|
37 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
38 |
### Configuration
|
39 |
|
40 |
The following YAML configuration was used to produce this model:
|
@@ -57,4 +80,4 @@ merge_method: model_stock
|
|
57 |
base_model: MathGenie/MathCoder2-Llama-3-8B
|
58 |
dtype: bfloat16
|
59 |
|
60 |
-
```
|
|
|
1 |
+
---
|
2 |
+
base_model:
|
3 |
+
- ruslandev/llama-3-8b-samantha
|
4 |
+
- MathGenie/MathCoder2-Llama-3-8B
|
5 |
+
- nvidia/OpenMath2-Llama3.1-8B
|
6 |
+
- NeverSleep/Llama-3-Lumimaid-8B-v0.1-OAS
|
7 |
+
- TsinghuaC3I/Llama-3.1-8B-UltraMedical
|
8 |
+
- tohur/natsumura-storytelling-rp-1.0-llama-3.1-8b
|
9 |
+
- Skywork/Skywork-o1-Open-Llama-3.1-8B
|
10 |
+
- Undi95/Llama-3-LewdPlay-8B
|
11 |
+
- Locutusque/Hercules-6.1-Llama-3.1-8B
|
12 |
+
- RefuelAI/Llama-3-Refueled
|
13 |
+
- rombodawg/Llama-3-8B-Instruct-Coder
|
14 |
+
library_name: transformers
|
15 |
+
tags:
|
16 |
+
- mergekit
|
17 |
+
- merge
|
18 |
+
license: llama3.1
|
19 |
+
---
|
20 |
# Llamaverse 8B
|
21 |
|
22 |
+
**A Unified Multidisciplinary Language Model**
|
23 |
+
Llamaverse-3.1-8B-Instruct is a state-of-the-art language model built on the foundation of MathCoder2-Llama-3-8B, pretrained on MathCode-Pile. This dataset, which embeds mathematical reasoning steps in natural language and code, provides a rock-solid foundation for advanced logical reasoning. By merging MathCoder2 with 10 specialized models using the Model Stock merge method, Llamaverse-3.1-8B-Instruct becomes an unparalleled polymath, excelling in mathematics, biomedical diagnostics, storytelling, coding, and more.
|
24 |
+
|
25 |
This model was merged using the [Model Stock](https://arxiv.org/abs/2403.19522) merge method using [MathGenie/MathCoder2-Llama-3-8B](https://huggingface.co/MathGenie/MathCoder2-Llama-3-8B) as a base.
|
26 |
|
27 |
### Models Merged
|
|
|
38 |
* [RefuelAI/Llama-3-Refueled](https://huggingface.co/RefuelAI/Llama-3-Refueled)
|
39 |
* [rombodawg/Llama-3-8B-Instruct-Coder](https://huggingface.co/rombodawg/Llama-3-8B-Instruct-Coder)
|
40 |
|
41 |
+
## **Multidisciplinary Expertise**
|
42 |
+
Llamaverse-3.1-8B-Instruct integrates the strengths of **10 specialized models**, including:
|
43 |
+
1. **ruslandev/llama-3-8b-samantha:** Empathetic and human-like interaction capabilities.
|
44 |
+
2. **nvidia/OpenMath2-Llama3.1-8B:** Advanced mathematical problem-solving.
|
45 |
+
3. **NeverSleep/Llama-3-Lumimaid-8B:** Creative storytelling and roleplay.
|
46 |
+
4. **TsinghuaC3I/Llama-3.1-8B-UltraMedical:** Clinical-grade biomedical insights.
|
47 |
+
5. **tohur/natsumura-storytelling-rp:** Immersive narrative generation.
|
48 |
+
6. **Skywork/Skywork-o1-Open-Llama-3.1-8B:** Reflective reasoning and complex problem-solving.
|
49 |
+
7. **Undi95/Llama-3-LewdPlay-8B:** Unconventional creativity and boundary-pushing dialogue.
|
50 |
+
8. **Locutusque/Hercules-6.1-Llama-3.1-8B:** Expertise in physics, biology, chemistry, and engineering.
|
51 |
+
9. **RefuelAI/Llama-3-Refueled:** Robust NLP capabilities for classification and entity extraction.
|
52 |
+
10. **rombodawg/Llama-3-8B-Instruct-Coder:** Efficient coding and software development.
|
53 |
+
|
54 |
+
## **Ethical Considerations**
|
55 |
+
Llamaverse-3.1-8B-Instruct must be used responsibly. Users should:
|
56 |
+
- Avoid deploying the model in high-stakes scenarios without human oversight.
|
57 |
+
- Be mindful of potential biases and ethical concerns, particularly in sensitive applications.
|
58 |
+
- Use the model’s creative and unconventional capabilities responsibly.
|
59 |
+
|
60 |
+
|
61 |
### Configuration
|
62 |
|
63 |
The following YAML configuration was used to produce this model:
|
|
|
80 |
base_model: MathGenie/MathCoder2-Llama-3-8B
|
81 |
dtype: bfloat16
|
82 |
|
83 |
+
```
|