Update README.md
Browse files
README.md
CHANGED
@@ -2,43 +2,82 @@
|
|
2 |
license: apache-2.0
|
3 |
tags:
|
4 |
- merge
|
5 |
-
-
|
6 |
-
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
7 |
- bunnycore/Best-Mix-Llama-3.1-8B
|
8 |
-
- USTC-KnowledgeComputingLab/Llama3-KALE-LM-Chem-1.5-8B
|
9 |
-
- Weyaxi/Einstein-v6.1-Llama3-8B
|
10 |
---
|
11 |
|
12 |
-
# ZeroXClem/Llama3.1-BestMix-Chem-Einstein-8B
|
13 |
|
14 |
-
ZeroXClem/Llama3.1-BestMix-Chem-Einstein-8B
|
15 |
-
* [bunnycore/Best-Mix-Llama-3.1-8B](https://huggingface.co/bunnycore/Best-Mix-Llama-3.1-8B)
|
16 |
-
* [USTC-KnowledgeComputingLab/Llama3-KALE-LM-Chem-1.5-8B](https://huggingface.co/USTC-KnowledgeComputingLab/Llama3-KALE-LM-Chem-1.5-8B)
|
17 |
-
* [Weyaxi/Einstein-v6.1-Llama3-8B](https://huggingface.co/Weyaxi/Einstein-v6.1-Llama3-8B)
|
18 |
|
19 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
20 |
|
21 |
```yaml
|
|
|
|
|
22 |
models:
|
23 |
- model: bunnycore/Best-Mix-Llama-3.1-8B
|
24 |
parameters:
|
25 |
-
density: [1, 0.7, 0.5]
|
26 |
weight: 1.0
|
27 |
|
28 |
- model: USTC-KnowledgeComputingLab/Llama3-KALE-LM-Chem-1.5-8B
|
29 |
parameters:
|
30 |
-
density: 0.6
|
31 |
-
weight: [0.3, 0.7, 1.0]
|
32 |
|
33 |
- model: Weyaxi/Einstein-v6.1-Llama3-8B
|
34 |
parameters:
|
35 |
-
density: 0.4
|
36 |
weight:
|
37 |
- filter: mlp
|
38 |
-
value: 0.5
|
39 |
- filter: self_attn
|
40 |
-
value: 0.7
|
41 |
-
- value: 0.5
|
42 |
|
43 |
merge_method: ties
|
44 |
base_model: bunnycore/Best-Mix-Llama-3.1-8B
|
@@ -47,4 +86,53 @@ parameters:
|
|
47 |
int8_mask: true
|
48 |
dtype: float16
|
49 |
|
50 |
-
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2 |
license: apache-2.0
|
3 |
tags:
|
4 |
- merge
|
5 |
+
- TIES
|
6 |
+
- Llama3
|
7 |
+
- BestMix
|
8 |
+
- Chemistry
|
9 |
+
- Einstein
|
10 |
+
- instruction-following
|
11 |
+
- conversational
|
12 |
+
- long-form-generation
|
13 |
+
- scientific
|
14 |
+
base_model:
|
15 |
- bunnycore/Best-Mix-Llama-3.1-8B
|
|
|
|
|
16 |
---
|
17 |
|
|
|
18 |
|
19 |
+
# **ZeroXClem/Llama3.1-BestMix-Chem-Einstein-8B**
|
|
|
|
|
|
|
20 |
|
21 |
+
**Llama3.1-BestMix-Chem-Einstein-8B** is an innovative, meticulously blended model designed to excel in **instruction-following**, **chemistry-focused tasks**, and **long-form conversational generation**. This model fuses the **best qualities** of multiple Llama3-based architectures, making it highly versatile for both general and specialized tasks. π»π§ β¨
|
22 |
+
|
23 |
+
## π **Family Tree**
|
24 |
+
|
25 |
+
This model is the result of merging the following:
|
26 |
+
|
27 |
+
- [**bunnycore/Best-Mix-Llama-3.1-8B**](https://huggingface.co/bunnycore/Best-Mix-Llama-3.1-8B): A balanced blend of top Llama models, optimized for general performance across reasoning, instruction-following, and math.
|
28 |
+
- [**USTC-KnowledgeComputingLab/Llama3-KALE-LM-Chem-1.5-8B**](https://huggingface.co/USTC-KnowledgeComputingLab/Llama3-KALE-LM-Chem-1.5-8B): A model specialized in **scientific knowledge** and **chemistry**, excelling in chemistry benchmarks.
|
29 |
+
- [**Weyaxi/Einstein-v6.1-Llama3-8B**](https://huggingface.co/Weyaxi/Einstein-v6.1-Llama3-8B): Fine-tuned for **long-form generation**, **conversation-heavy tasks**, and optimized with cutting-edge techniques for efficient memory usage and fast performance.
|
30 |
+
|
31 |
+
---
|
32 |
+
|
33 |
+
## 𧬠**Model Lineage**
|
34 |
+
|
35 |
+
### **A: bunnycore/Best-Mix-Llama-3.1-8B**
|
36 |
+
|
37 |
+
- A masterful **blend** of several Llama3 models like **Aurora_faustus**, **TitanFusion**, and **OpenMath2**.
|
38 |
+
- Provides a **balanced performance** in a variety of tasks such as reasoning, math, and instruction-following.
|
39 |
+
- Key contributor to the **overall versatility** of the merged model.
|
40 |
+
|
41 |
+
### **B: USTC-KnowledgeComputingLab/Llama3-KALE-LM-Chem-1.5-8B**
|
42 |
+
|
43 |
+
- Specializes in **chemistry** and **scientific knowledge**, outperforming many larger models in **chemistry benchmarks**.
|
44 |
+
- Adds **scientific rigor** and domain-specific expertise to the merged model, making it perfect for scientific and academic tasks.
|
45 |
+
|
46 |
+
### **C: Weyaxi/Einstein-v6.1-Llama3-8B**
|
47 |
+
|
48 |
+
- Fine-tuned on a wide range of **instructive** and **conversational datasets** like **WizardLM**, **Alpaca**, and **ShareGPT**.
|
49 |
+
- Optimized for **long-form text generation** and enhanced with **xformers attention** and **flash attention** techniques for better performance.
|
50 |
+
- Key player in **dialogue-based tasks** and **long conversation generation**.
|
51 |
+
|
52 |
+
---
|
53 |
+
|
54 |
+
## π οΈ **Merge Details**
|
55 |
+
|
56 |
+
This model was merged using the **TIES merge method**, ensuring a smooth integration of the key strengths from each contributing model. Here's the configuration used:
|
57 |
|
58 |
```yaml
|
59 |
+
yaml
|
60 |
+
Copy code
|
61 |
models:
|
62 |
- model: bunnycore/Best-Mix-Llama-3.1-8B
|
63 |
parameters:
|
64 |
+
density: [1, 0.7, 0.5]
|
65 |
weight: 1.0
|
66 |
|
67 |
- model: USTC-KnowledgeComputingLab/Llama3-KALE-LM-Chem-1.5-8B
|
68 |
parameters:
|
69 |
+
density: 0.6
|
70 |
+
weight: [0.3, 0.7, 1.0]
|
71 |
|
72 |
- model: Weyaxi/Einstein-v6.1-Llama3-8B
|
73 |
parameters:
|
74 |
+
density: 0.4
|
75 |
weight:
|
76 |
- filter: mlp
|
77 |
+
value: 0.5
|
78 |
- filter: self_attn
|
79 |
+
value: 0.7
|
80 |
+
- value: 0.5
|
81 |
|
82 |
merge_method: ties
|
83 |
base_model: bunnycore/Best-Mix-Llama-3.1-8B
|
|
|
86 |
int8_mask: true
|
87 |
dtype: float16
|
88 |
|
89 |
+
```
|
90 |
+
|
91 |
+
---
|
92 |
+
|
93 |
+
## π― **Key Features & Capabilities**
|
94 |
+
|
95 |
+
### **1. Instruction Following & General Reasoning**:
|
96 |
+
|
97 |
+
With the foundation of **Best-Mix**, this model excels in **general-purpose reasoning**, instruction-following, and tasks that require high adaptability.
|
98 |
+
|
99 |
+
### **2. Scientific & Chemistry Expertise**:
|
100 |
+
|
101 |
+
Thanks to the contribution from **KALE-LM-Chem**, this model shines in **scientific research**, particularly **chemistry-focused tasks**, making it ideal for academic and research purposes.
|
102 |
+
|
103 |
+
### **3. Long-Form & Conversational Mastery**:
|
104 |
+
|
105 |
+
With **Einstein-v6.1**, the model handles **long-form generation** effortlessly, excelling in extended conversations and structured dialogue applications.
|
106 |
+
|
107 |
+
---
|
108 |
+
|
109 |
+
## π **Performance Benchmarks**
|
110 |
+
|
111 |
+
While still in its early stages, **Llama3.1-BestMix-Chem-Einstein-8B** is expected to perform well across a variety of benchmarks, including:
|
112 |
+
|
113 |
+
- **Chemistry-focused benchmarks** (KALE-LM-Chem)
|
114 |
+
- **Instruction-following tasks** (Best-Mix)
|
115 |
+
- **Conversational AI** and **long-form text generation** (Einstein-v6.1)
|
116 |
+
|
117 |
+
Further testing and evaluation will continue to refine this model's capabilities.
|
118 |
+
|
119 |
+
---
|
120 |
+
|
121 |
+
## π **License**
|
122 |
+
|
123 |
+
This model is open-sourced under the **Apache-2.0 License**, allowing free use and modification with proper attribution.
|
124 |
+
|
125 |
+
---
|
126 |
+
|
127 |
+
## π‘ **Tags**
|
128 |
+
|
129 |
+
- `merge`
|
130 |
+
- `TIES`
|
131 |
+
- `BestMix`
|
132 |
+
- `Chemistry`
|
133 |
+
- `Einstein`
|
134 |
+
- `instruction-following`
|
135 |
+
- `long-form-generation`
|
136 |
+
- `conversational`
|
137 |
+
|
138 |
+
---
|