Update README.md
Browse files
README.md
CHANGED
@@ -30,14 +30,15 @@ Nandine-7b represents a harmonious amalgamation of narrative skill, empathetic i
|
|
30 |
|
31 |
**Key Features:**
|
32 |
- **Narrative Excellence:** Drawing 55% of its prowess from Westlake-7B, Nandine-7b excels in crafting compelling narratives and engaging character dialogues.
|
33 |
-
- **Diverse Expertise:** Benefits from the 35% contribution of speechless-mistral-six-in-one-7b, integrating insights from six advanced Mistral-7B models
|
34 |
- **Human Connection:** Gains a 10% influence from Samantha-v2, fostering a warm, approachable demeanor, enhancing user interaction quality while adhering to ethical guidelines.
|
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 |
## Nous Benchmark
|
43 |
| Model |AGIEval|GPT4All|TruthfulQA|Bigbench|Average|
|
@@ -93,4 +94,12 @@ pipeline = transformers.pipeline(
|
|
93 |
|
94 |
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
|
95 |
print(outputs[0]["generated_text"])
|
96 |
-
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
30 |
|
31 |
**Key Features:**
|
32 |
- **Narrative Excellence:** Drawing 55% of its prowess from Westlake-7B, Nandine-7b excels in crafting compelling narratives and engaging character dialogues.
|
33 |
+
- **Diverse Expertise:** Benefits from the 35% contribution of speechless-mistral-six-in-one-7b, integrating insights from six advanced Mistral-7B models.
|
34 |
- **Human Connection:** Gains a 10% influence from Samantha-v2, fostering a warm, approachable demeanor, enhancing user interaction quality while adhering to ethical guidelines.
|
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|
|
|
|
94 |
|
95 |
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
|
96 |
print(outputs[0]["generated_text"])
|
97 |
+
```
|
98 |
+
|
99 |
+
## GGUF
|
100 |
+
GGUF files are available at [Nandine-7b-GGUF](https://huggingface.co/sethuiyer/Nandine-7b-GGUF/tree/main)
|
101 |
+
|
102 |
+
## Ollama
|
103 |
+
Nandine is now available on Ollama. You can use it by running the command ```ollama run stuehieyr/nandine``` in your
|
104 |
+
terminal. If you have limited computing resources, check out this [video](https://www.youtube.com/watch?v=Qa1h7ygwQq8) to learn how to run it on
|
105 |
+
a Google Colab backend.
|