Update README.md
Browse files
README.md
CHANGED
@@ -3,4 +3,24 @@ license: llama3
|
|
3 |
language:
|
4 |
- en
|
5 |
pipeline_tag: text-generation
|
6 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
language:
|
4 |
- en
|
5 |
pipeline_tag: text-generation
|
6 |
+
---
|
7 |
+
# Instruct_Llama3_8B
|
8 |
+
Fine-tuned from Llama-3-8B, using a wide variety of sources for the dataset. 84.9% for training, 15% validation, 0.1% test. Trained for 2 epochs using QDora. Trained with 4096 context window.
|
9 |
+
|
10 |
+
# Model Details
|
11 |
+
* **Trained by**: trained by [Brillibits](https://www.youtube.com/@Brillibits).
|
12 |
+
* **Model type:** **Instruct_Llama3_8B** is an auto-regressive language model based on the Llama 3 transformer architecture.
|
13 |
+
* **Language(s)**: English
|
14 |
+
* **License for Instruct_Llama3_8B**: llama3 license
|
15 |
+
|
16 |
+
|
17 |
+
# Prompting
|
18 |
+
|
19 |
+
```
|
20 |
+
<s>[SYS] {system prompt or blank space} [/SYS] [INST] {instruction} [/INST] {response}</s>
|
21 |
+
```
|
22 |
+
|
23 |
+
## Professional Assistance
|
24 |
+
This model and other models like it are great, but where LLMs hold the most promise is when they are applied on custom data to automate a wide variety of tasks
|
25 |
+
|
26 |
+
If you have a dataset and want to see if you might be able to apply that data to automate some tasks, and you are looking for professional assistance, contact me [here](mailto:[email protected])
|