aashish1904 commited on
Commit
bb85c36
1 Parent(s): b926649

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +103 -0
README.md ADDED
@@ -0,0 +1,103 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ ---
3
+
4
+ language:
5
+ - en
6
+ pipeline_tag: text-generation
7
+ tags:
8
+ - shining-valiant
9
+ - shining-valiant-2
10
+ - valiant
11
+ - valiant-labs
12
+ - llama
13
+ - llama-3.1
14
+ - llama-3.1-instruct
15
+ - llama-3.1-instruct-8b
16
+ - llama-3
17
+ - llama-3-instruct
18
+ - llama-3-instruct-8b
19
+ - 8b
20
+ - conversational
21
+ - chat
22
+ - instruct
23
+ model_type: llama
24
+ license: llama3.1
25
+
26
+ ---
27
+
28
+ ![](https://lh7-rt.googleusercontent.com/docsz/AD_4nXeiuCm7c8lEwEJuRey9kiVZsRn2W-b4pWlu3-X534V3YmVuVc2ZL-NXg2RkzSOOS2JXGHutDuyyNAUtdJI65jGTo8jT9Y99tMi4H4MqL44Uc5QKG77B0d6-JfIkZHFaUA71-RtjyYZWVIhqsNZcx8-OMaA?key=xt3VSDoCbmTY7o-cwwOFwQ)
29
+
30
+ # QuantFactory/Llama3.1-8B-ShiningValiant2-GGUF
31
+ This is quantized version of [ValiantLabs/Llama3.1-8B-ShiningValiant2](https://huggingface.co/ValiantLabs/Llama3.1-8B-ShiningValiant2) created using llama.cpp
32
+
33
+ # Original Model Card
34
+
35
+
36
+
37
+ ![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/63444f2687964b331809eb55/EXX7TKbB-R6arxww2mk0R.jpeg)
38
+
39
+
40
+ Shining Valiant 2 is a chat model built on Llama 3.1 8b, finetuned on our data for friendship, insight, knowledge and enthusiasm.
41
+ - Finetuned on [meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct) for best available general performance
42
+ - Trained on our data, focused on science, engineering, technical knowledge, and structured reasoning
43
+
44
+
45
+ ## Version
46
+
47
+ This is the **2024-08-06** release of Shining Valiant 2 for Llama 3.1 8b.
48
+
49
+ Our newest dataset improves specialist knowledge and response consistency.
50
+
51
+ Help us and recommend Shining Valiant 2 to your friends!
52
+
53
+
54
+ ## Prompting Guide
55
+ Shining Valiant 2 uses the [Llama 3.1 Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct) prompt format. The example script below can be used as a starting point for general chat:
56
+
57
+
58
+ import transformers
59
+ import torch
60
+
61
+ model_id = "ValiantLabs/Llama3.1-8B-ShiningValiant2"
62
+
63
+ pipeline = transformers.pipeline(
64
+ "text-generation",
65
+ model=model_id,
66
+ model_kwargs={"torch_dtype": torch.bfloat16},
67
+ device_map="auto",
68
+ )
69
+
70
+ messages = [
71
+ {"role": "system", "content": "You are Shining Valiant, a highly capable chat AI."},
72
+ {"role": "user", "content": "Describe the role of transformation matrices in 3D graphics."}
73
+ ]
74
+
75
+ outputs = pipeline(
76
+ messages,
77
+ max_new_tokens=1024,
78
+ )
79
+
80
+ print(outputs[0]["generated_text"][-1])
81
+
82
+
83
+ ## The Model
84
+ Shining Valiant 2 is built on top of Llama 3.1 8b Instruct.
85
+
86
+ The current version of Shining Valiant 2 is trained mostly on our private Shining Valiant data, supplemented by [LDJnr/Pure-Dove](https://huggingface.co/datasets/LDJnr/Pure-Dove) for response flexibility.
87
+
88
+ Our private data adds specialist knowledge and Shining Valiant's personality: she's friendly, enthusiastic, insightful, knowledgeable, and loves to learn! Magical.
89
+
90
+
91
+ ![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/63444f2687964b331809eb55/VCJ8Fmefd8cdVhXSSxJiD.jpeg)
92
+
93
+
94
+ Shining Valiant 2 is created by [Valiant Labs.](http://valiantlabs.ca/)
95
+
96
+ [Check out our HuggingFace page for Fireplace 2 and our other models!](https://huggingface.co/ValiantLabs)
97
+
98
+ [Follow us on X for updates on our models!](https://twitter.com/valiant_labs)
99
+
100
+ We care about open source.
101
+ For everyone to use.
102
+
103
+ We encourage others to finetune further from our models.