pfost-bit commited on
Commit
f418a9d
·
verified ·
1 Parent(s): 76aa1a0

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -18
README.md CHANGED
@@ -12,32 +12,18 @@ base_model:
12
  pipeline_tag: text-generation
13
  ---
14
 
15
- # Model Card for Model ID
16
-
17
 
18
 
19
 
20
 
21
  ## Model Details
22
 
23
- ### Model Description
24
-
25
- <!-- Provide a longer summary of what this model is. -->
26
 
27
- This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
28
 
29
- - **Developed by:** [More Information Needed]
30
- - **Funded by [optional]:** [More Information Needed]
31
- - **Shared by [optional]:** [More Information Needed]
32
- - **Model type:** [More Information Needed]
33
- - **Language(s) (NLP):** [More Information Needed]
34
- - **License:** [More Information Needed]
35
- - **Finetuned from model [optional]:** [More Information Needed]
36
 
37
- ### Model Sources [optional]
38
 
39
- <!-- Provide the basic links for the model. -->
40
 
41
- - **Repository:** [More Information Needed]
42
- - **Paper [optional]:** [More Information Needed]
43
- - **Demo [optional]:** [More Information Needed]
 
12
  pipeline_tag: text-generation
13
  ---
14
 
15
+ # Model Card for SurfMine
 
16
 
17
 
18
 
19
 
20
  ## Model Details
21
 
22
+ This is a model created to generate human readable surf forecast text based on live user inputs from weather sources.
 
 
23
 
24
+ ### Model Description and Introduction
25
 
26
+ There are many surf forecasting models available, including the WAVEWATCH model from NOAA, the LOUTS model from Surfline and numerous other models on the internet that claim to deliver the most accurate and up-to-date information. The most prominent comes from a company called Surfline. They have increasingly pushed more of their features into a pay-to-play model. They have also acquired a few of their competitors. As a result, they have become the only reliable source for surf forecasts for certain known spots. To gain a deeper understanding of how to develop a deep learning model for a subject I am both interested in and passionate about, this is my attempt build a surf-forecast model that takes historical NOAA Buoy Data, and outputs a surf forecast for that input text, in the flavor of a seasoned surf forecaster/reporter. Current models struggle to capture the essence (saltiness/coolness factor) of these veteran surf reporters, I aim bridge this gap through specific prompt tuning and LoRA fine-tuning.
 
 
 
 
 
 
27
 
 
28
 
 
29