Commit
•
b460682
1
Parent(s):
0f0d141
Update README.md
Browse files
README.md
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
---
|
2 |
-
base_model: unsloth/
|
3 |
language:
|
4 |
- en
|
5 |
license: apache-2.0
|
@@ -7,16 +7,38 @@ tags:
|
|
7 |
- text-generation-inference
|
8 |
- transformers
|
9 |
- unsloth
|
10 |
-
-
|
11 |
- gguf
|
12 |
---
|
13 |
|
14 |
-
#
|
15 |
|
16 |
-
-
|
17 |
-
-
|
18 |
-
-
|
|
|
19 |
|
20 |
-
|
21 |
|
22 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
+
base_model: unsloth/Qwen2-7B
|
3 |
language:
|
4 |
- en
|
5 |
license: apache-2.0
|
|
|
7 |
- text-generation-inference
|
8 |
- transformers
|
9 |
- unsloth
|
10 |
+
- llama
|
11 |
- gguf
|
12 |
---
|
13 |
|
14 |
+
# flashcardsGPT-Qwen2-7B-v0.1-GGUF
|
15 |
|
16 |
+
- This model is a fine-tuned version of [unsloth/Qwen2-7b](https://huggingface.co/unsloth/Qwen2-7b) on an dataset created by [Valerio Job](https://huggingface.co/valeriojob) based on real university lecture data.
|
17 |
+
- Version 0.1 of flashcardsGPT has only been trained on the module "Time Series Analysis with R" which is part of the BSc Business-IT programme offered by the FHNW university ([more info](https://www.fhnw.ch/en/degree-programmes/business/bsc-in-business-information-technology)).
|
18 |
+
- This repo includes the quantized models in the GGUF format. There is a separate repo called [valeriojob/flashcardsGPT-Qwen2-7B-v0.1](https://huggingface.co/valeriojob/flashcardsGPT-Qwen2-7B-v0.1) that includes the default format of the model as well as the LoRA adapters of the model.
|
19 |
+
- This model was quantized using [llama.cpp](https://github.com/ggerganov/llama.cpp).
|
20 |
|
21 |
+
## Model description
|
22 |
|
23 |
+
This model takes the OCR-extracted text from a university lecture slide as an input. It then generates high quality flashcards and returns them as a JSON object.
|
24 |
+
It uses the following Prompt Engineering template:
|
25 |
+
|
26 |
+
"""
|
27 |
+
Your task is to process the below OCR-extracted text from university lecture slides and create a set of flashcards with the key information about the topic.
|
28 |
+
Format the flashcards as a JSON object, with each card having a 'front' field for the question or term, and a 'back' field for the corresponding answer or definition, which may include a short example.
|
29 |
+
Ensure the 'back' field contains no line breaks.
|
30 |
+
No additional text or explanation should be provided—only respond with the JSON object.
|
31 |
+
|
32 |
+
Here is the OCR-extracted text:
|
33 |
+
""""
|
34 |
+
|
35 |
+
## Intended uses & limitations
|
36 |
+
|
37 |
+
The fine-tuned model can be used to generate high-quality flashcards based on TSAR lectures from the BSc BIT programme offered by the FHNW university.
|
38 |
+
|
39 |
+
## Training and evaluation data
|
40 |
+
|
41 |
+
The dataset (train and test) used for fine-tuning this model can be found here: [datasets/valeriojob/FHNW-Flashcards-Data-v0.1](https://huggingface.co/datasets/valeriojob/FHNW-Flashcards-Data-v0.1)
|
42 |
+
|
43 |
+
## Licenses
|
44 |
+
- **License:** apache-2.0
|