RonanMcGovern
commited on
Commit
·
2141791
1
Parent(s):
eee093d
add youtube video
Browse files
README.md
CHANGED
@@ -5,25 +5,28 @@ colorFrom: red
|
|
5 |
colorTo: green
|
6 |
sdk: static
|
7 |
pinned: false
|
8 |
-
tags: [llama, jupyter, colab, function calling, QLoRa, fine-tuning]
|
9 |
---
|
10 |
|
11 |
-
# *QLoRa
|
12 |
|
13 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
14 |
- Includes a prompt loss-mask for improved performance when structured responses are required.
|
15 |
- Includes a stop token after responses - allowing the model to provide a short reponse (e.g. a function call) and then stop.
|
16 |
-
-
|
17 |
-
- Allows for fine-tuning 70B models with Google Colab Pro.
|
18 |
-
|
19 |
-
This script is commercially licensed and available for purchase at a price of €14.99 (or $16.49) per seat/user. [Request access here](https://buy.stripe.com/5kA5l69K52Hxf3a006). Access will be provided within 24 hours of purchase.
|
20 |
|
21 |
# Function Calling Dataset
|
22 |
- Commercial dataset allowing language models to be fine-tuned for function calling ([Get access here](https://huggingface.co/datasets/Trelis/function_calling_extended)).
|
23 |
- Created using only human input or Apache 2 licensed datasets (no third party commercial licensing limitations)
|
24 |
- Models trained with this dataset:
|
25 |
-
- - [Llama-2-7B](https://huggingface.co/Trelis/Llama-2-7b-chat-hf-function-calling) - repo includes Google Colab notebook
|
26 |
-
- - [Llama-2-13B](https://huggingface.co/Trelis/Llama-2-13b-chat-hf-function-calling) - repo includes Google Colab notebook
|
27 |
|
28 |
# Jupyter Llama
|
29 |
A Chat Assistant in Jupyter Notebook - Built on Llama 2.
|
|
|
5 |
colorTo: green
|
6 |
sdk: static
|
7 |
pinned: false
|
8 |
+
tags: [llama, jupyter, colab, function calling, QLoRa, fine-tuning, scripts, fine-tuning]
|
9 |
---
|
10 |
|
11 |
+
# *QLoRa Fine-Tuning Scripts/Notebooks for Small Datasets*
|
12 |
|
13 |
+
## QLoRa Training Notebook for Llama 2 (FREE)
|
14 |
+
- Access the Google Colab script [here](https://colab.research.google.com/drive/1uMSS1o_8YOPyG1X_4k6ENEE3kJfBGGhH?usp=sharing).
|
15 |
+
|
16 |
+
- View the [Youtube Video Here](https://youtu.be/OQdp-OeG1as)
|
17 |
+
|
18 |
+
## QLoRa ADVANCED Training Notebook (PAID)
|
19 |
+
This advanced script provides improved performance when training with small datasets:
|
20 |
- Includes a prompt loss-mask for improved performance when structured responses are required.
|
21 |
- Includes a stop token after responses - allowing the model to provide a short reponse (e.g. a function call) and then stop.
|
22 |
+
- Request [access here](https://buy.stripe.com/5kA5l69K52Hxf3a006). €14.99 (or $16.49) per seat/user. Access will be provided within 24 hours of purchase.
|
|
|
|
|
|
|
23 |
|
24 |
# Function Calling Dataset
|
25 |
- Commercial dataset allowing language models to be fine-tuned for function calling ([Get access here](https://huggingface.co/datasets/Trelis/function_calling_extended)).
|
26 |
- Created using only human input or Apache 2 licensed datasets (no third party commercial licensing limitations)
|
27 |
- Models trained with this dataset:
|
28 |
+
- - [Llama-2-7B](https://huggingface.co/Trelis/Llama-2-7b-chat-hf-function-calling) - repo includes Google Colab notebook for inference
|
29 |
+
- - [Llama-2-13B](https://huggingface.co/Trelis/Llama-2-13b-chat-hf-function-calling) - repo includes Google Colab notebook for inference
|
30 |
|
31 |
# Jupyter Llama
|
32 |
A Chat Assistant in Jupyter Notebook - Built on Llama 2.
|