Update README.md
Browse files
README.md
CHANGED
@@ -12,7 +12,7 @@ tags:
|
|
12 |
---
|
13 |
|
14 |
# Uploaded model
|
15 |
-
|
16 |
|
17 |
system_prompt = """You are an expert captioning assistant specializing in converting a speech transcript into clear, accurate, and viewer-friendly captions.
|
18 |
|
@@ -30,7 +30,7 @@ The data set is curated using
|
|
30 |
|
31 |
Judd, Nicholas, Dan Drinkard, Jeremy Carbaugh, and Lindsay Young. congressional-record: A parser for the Congressional Record. Chicago, IL: 2017. https://github.com/unitedstates/congressional-record
|
32 |
|
33 |
-
Text is preprocessed by removing President names, Vice President names, party names, and some cliche phrases such as "I reserve the balance of my time","I yield the floor" etc.
|
34 |
- **Developed by:** mesut
|
35 |
- **License:** apache-2.0
|
36 |
- **Finetuned from model :** unsloth/meta-llama-3.1-8b-bnb-4bit
|
|
|
12 |
---
|
13 |
|
14 |
# Uploaded model
|
15 |
+
The unsloth/meta-llama-3.1-8b-bnb-4bit model is fine tuned by 30.000 mp speeches and captions from USA Congress, Senate and House. The system promt is below
|
16 |
|
17 |
system_prompt = """You are an expert captioning assistant specializing in converting a speech transcript into clear, accurate, and viewer-friendly captions.
|
18 |
|
|
|
30 |
|
31 |
Judd, Nicholas, Dan Drinkard, Jeremy Carbaugh, and Lindsay Young. congressional-record: A parser for the Congressional Record. Chicago, IL: 2017. https://github.com/unitedstates/congressional-record
|
32 |
|
33 |
+
Text is preprocessed by removing President names, Vice President names, party names, and some cliche phrases such as "I reserve the balance of my time","I yield the floor" etc.
|
34 |
- **Developed by:** mesut
|
35 |
- **License:** apache-2.0
|
36 |
- **Finetuned from model :** unsloth/meta-llama-3.1-8b-bnb-4bit
|