qf
Browse files
README.md
CHANGED
@@ -30,15 +30,21 @@ A few examples of different formats:
|
|
30 |
|
31 |
2. [INST] (You are an intelligent, helpful AI assistant.) Hello, can you write me a thank you letter? [/INST]
|
32 |
|
33 |
-
3. [INST]
|
34 |
|
35 |
## The Model
|
36 |
Shining Valiant is built on Llama 2's 70b parameter architecture. We've created the model through multiple finetuning runs on different compositions of our dataset.
|
37 |
|
38 |
Our dataset is:
|
|
|
|
|
39 |
75% - our custom AI instruction-tuned dataset, created and curated for increased general capability, insight, logic, depth, and specific personality
|
|
|
|
|
40 |
25% - a selection of open-source AI data from a variety of datasets to supplement general knowledge and reasoning
|
41 |
|
|
|
|
|
42 |
We are actively working on expanding and improving this dataset for use in future releases of this model and others.
|
43 |
|
44 |
## Who We Are
|
|
|
30 |
|
31 |
2. [INST] (You are an intelligent, helpful AI assistant.) Hello, can you write me a thank you letter? [/INST]
|
32 |
|
33 |
+
3. [INST] <<SYS>>You are an intelligent, helpful AI assistant.<</SYS>>Deep dive about a country with interesting history: [/INST]
|
34 |
|
35 |
## The Model
|
36 |
Shining Valiant is built on Llama 2's 70b parameter architecture. We've created the model through multiple finetuning runs on different compositions of our dataset.
|
37 |
|
38 |
Our dataset is:
|
39 |
+
|
40 |
+
|
41 |
75% - our custom AI instruction-tuned dataset, created and curated for increased general capability, insight, logic, depth, and specific personality
|
42 |
+
|
43 |
+
|
44 |
25% - a selection of open-source AI data from a variety of datasets to supplement general knowledge and reasoning
|
45 |
|
46 |
+
|
47 |
+
|
48 |
We are actively working on expanding and improving this dataset for use in future releases of this model and others.
|
49 |
|
50 |
## Who We Are
|