Spaces:
Sleeping
Sleeping
Update ipynb/llm/README.md
Browse files- ipynb/llm/README.md +63 -1
ipynb/llm/README.md
CHANGED
@@ -2,4 +2,66 @@
|
|
2 |
|
3 |

|
4 |
|
5 |
-
* Location of model development logs > https://drive.google.com/drive/folders/1OqUzYN_nfBSeZfbQ9qcB1YVkSNzi_gE3?usp=drive_link
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2 |
|
3 |

|
4 |
|
5 |
+
* Location of model development logs > https://drive.google.com/drive/folders/1OqUzYN_nfBSeZfbQ9qcB1YVkSNzi_gE3?usp=drive_link
|
6 |
+
|
7 |
+
|
8 |
+
__Dataset and Model Migration__
|
9 |
+
|
10 |
+
Overview
|
11 |
+
|
12 |
+
This README also serves as a guide and legend for the migration and update of datasets and models previously hosted
|
13 |
+
under the ssoh namespace, now transferred to the BitBasher namespace on Hugging Face.
|
14 |
+
|
15 |
+
The purpose of this guide is to facilitate easy referencing with respect to the submitted codes.
|
16 |
+
|
17 |
+
|
18 |
+
Migration Details
|
19 |
+
|
20 |
+
Below is a detailed list of the datasets and models that have been moved, including their old and new locations:
|
21 |
+
|
22 |
+
* The term 'base model' refers to 'meta-llama/Llama-2-7b-chat-hf' on Hugging Face.
|
23 |
+
|
24 |
+
|
25 |
+
1. MCQ Dataset.
|
26 |
+
Old Location: ssoh/mcq_dataset_2
|
27 |
+
New Location: BitBasher/mcq_dataset_2
|
28 |
+
|
29 |
+
|
30 |
+
2. Summarization and QnA Dataset.
|
31 |
+
Old Location: ssoh/sum_n_qna_dataset
|
32 |
+
New Location: BitBasher/sum_n_qna_dataset
|
33 |
+
|
34 |
+
|
35 |
+
3. Model fine-tuned from a base model using the MCQ dataset.
|
36 |
+
Old Location: ssoh/llama-2-7b-mcq_2
|
37 |
+
New Location: BitBasher/llama-2-7b-mcq_2
|
38 |
+
|
39 |
+
|
40 |
+
4. Model fine-tuned from the MCQ-tuned base model using the Summarization and QnA Dataset (also known as the Integrated model).
|
41 |
+
Old Location: ssoh/llama-2-7b-combined_datasets
|
42 |
+
New Location: BitBasher/llama-2-7b-combined_datasets
|
43 |
+
|
44 |
+
|
45 |
+
5. Integrated model converted to the GGUF format.
|
46 |
+
Old Location: ssoh/llama-2-7b-combined_datasets-GGUF
|
47 |
+
New Location: BitBasher/llama-2-7b-combined_datasets-GGUF
|
48 |
+
|
49 |
+
|
50 |
+
6. Chosen model converted to the GGUF format.
|
51 |
+
Old Location: ssoh/llama-2-7b-mini-ibased-GGUF
|
52 |
+
New Location: BitBasher/llama-2-7b-mini-ibased-GGUF
|
53 |
+
|
54 |
+
|
55 |
+
7. Chosen model.
|
56 |
+
Old Location: ssoh/llama-2-7b-mini-ibased
|
57 |
+
New Location: BitBasher/llama-2-7b-mini-ibased
|
58 |
+
|
59 |
+
|
60 |
+
8. Initial dataset.
|
61 |
+
Old Location: ssoh/mini-ibased-dataset
|
62 |
+
New Location: BitBasher/mini-ibased-dataset
|
63 |
+
|
64 |
+
|
65 |
+
Accessing the Datasets and Models
|
66 |
+
|
67 |
+
* To ensure uninterrupted access, please visit the new locations listed above to access the migrated datasets and models.
|