Update README.md
Browse files
README.md
CHANGED
@@ -21,6 +21,8 @@ pipeline_tag: conversational
|
|
21 |
<img src="https://huggingface.co/sethuiyer/Nandine-7b/resolve/main/nandine.webp" height="128px" alt="Nandine">
|
22 |
</p>
|
23 |
|
|
|
|
|
24 |
Nandine-7b is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
|
25 |
* [senseable/Westlake-7B](https://huggingface.co/senseable/Westlake-7B)
|
26 |
* [Guilherme34/Samantha-v2](https://huggingface.co/Guilherme34/Samantha-v2)
|
@@ -28,18 +30,23 @@ Nandine-7b is a merge of the following models using [LazyMergekit](https://colab
|
|
28 |
|
29 |
Nandine-7b represents a harmonious amalgamation of narrative skill, empathetic interaction, intellectual depth, and eloquent communication.
|
30 |
|
31 |
-
**
|
32 |
-
|
33 |
-
|
34 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
35 |
|
36 |
**Intended Use:**
|
37 |
Ideal for users seeking a versatile AI companion for creative writing, thoughtful discussions, and general assistance.
|
38 |
|
39 |
-
**Limitations:**
|
40 |
-
While Nandine-7b excels in various domains, it may not perfectly replicate human nuances in certain complex emotional or contextual scenarios.
|
41 |
-
|
42 |
-
|
43 |
## Nous Benchmark
|
44 |
| Model |AGIEval|GPT4All|TruthfulQA|Bigbench|Average|
|
45 |
|---------------------------------------------------------|------:|------:|---------:|-------:|------:|
|
|
|
21 |
<img src="https://huggingface.co/sethuiyer/Nandine-7b/resolve/main/nandine.webp" height="128px" alt="Nandine">
|
22 |
</p>
|
23 |
|
24 |
+
Rated **87.47/100** by GPT-4 on a collection of 30 synthetic prompts generated by GPT-4.
|
25 |
+
|
26 |
Nandine-7b is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
|
27 |
* [senseable/Westlake-7B](https://huggingface.co/senseable/Westlake-7B)
|
28 |
* [Guilherme34/Samantha-v2](https://huggingface.co/Guilherme34/Samantha-v2)
|
|
|
30 |
|
31 |
Nandine-7b represents a harmonious amalgamation of narrative skill, empathetic interaction, intellectual depth, and eloquent communication.
|
32 |
|
33 |
+
**Pros:**
|
34 |
+
1. **Strong Narrative Skills:** Excels in storytelling, creating engaging and imaginative narratives.
|
35 |
+
2. **Accurate Information Delivery:** Provides factual and detailed information across various topics.
|
36 |
+
3. **Comprehensive Analysis:** Capable of well-rounded discussions on complex and ethical topics.
|
37 |
+
4. **Emotional Intelligence:** Shows empathy and understanding in responses requiring emotional sensitivity.
|
38 |
+
5. **Clarity and Structure:** Maintains clear and well-structured communication.
|
39 |
+
|
40 |
+
**Cons:**
|
41 |
+
1. **Language Translation Limitations:** Challenges in providing fluent and natural translations.
|
42 |
+
2. **Incomplete Problem Solving:** Some logical or mathematical problems are not solved accurately.
|
43 |
+
3. **Lack of Depth in Certain Areas:** Needs deeper exploration in some responses for a more comprehensive understanding.
|
44 |
+
4. **Occasional Imbalance in Historical Context:** Some historical explanations could be more balanced.
|
45 |
+
5. **Room for Enhanced Creativity:** While creative storytelling is strong, there's potential for more varied responses in hypothetical scenarios.
|
46 |
|
47 |
**Intended Use:**
|
48 |
Ideal for users seeking a versatile AI companion for creative writing, thoughtful discussions, and general assistance.
|
49 |
|
|
|
|
|
|
|
|
|
50 |
## Nous Benchmark
|
51 |
| Model |AGIEval|GPT4All|TruthfulQA|Bigbench|Average|
|
52 |
|---------------------------------------------------------|------:|------:|---------:|-------:|------:|
|