Ateeqq commited on
Commit
b5f41e0
·
verified ·
1 Parent(s): 3f23add

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +10 -6
README.md CHANGED
@@ -1,24 +1,28 @@
1
  ---
2
- license: cc-by-nc-nd-4.0
3
  inference:
4
  parameters:
5
  num_beams: 3
6
  num_beam_groups: 3
7
  num_return_sequences: 1
8
- repetition_penalty: 10.0
9
  diversity_penalty: 3.01
10
  no_repeat_ngram_size: 2
11
  temperature: 0.8
12
  max_length: 128
13
  widget:
14
  - text: >-
15
- Data scientists need to be able to communicate their findings to others in a clear and concise way.
 
16
  example_title: Data scientists
17
  - text: >-
18
- Search engine optimization (SEO) is the practice of getting targeted traffic to a website from a search engine's organic rankings.
 
19
  example_title: SEO
20
  - text: >-
21
- By leveraging prior model training through transfer learning, fine-tuning can reduce the amount of expensive computing power and labeled data needed to obtain large models tailored to niche use cases and business needs.
 
 
22
  example_title: Fine Tuning
23
  ---
24
 
@@ -64,4 +68,4 @@ This model is intended for research and creative writing purposes. It is essenti
64
 
65
  **Further Development:**
66
 
67
- (Mention any ongoing development or areas for future improvement in Discussions.)
 
1
  ---
2
+ license: llama3
3
  inference:
4
  parameters:
5
  num_beams: 3
6
  num_beam_groups: 3
7
  num_return_sequences: 1
8
+ repetition_penalty: 10
9
  diversity_penalty: 3.01
10
  no_repeat_ngram_size: 2
11
  temperature: 0.8
12
  max_length: 128
13
  widget:
14
  - text: >-
15
+ Data scientists need to be able to communicate their findings to others in a
16
+ clear and concise way.
17
  example_title: Data scientists
18
  - text: >-
19
+ Search engine optimization (SEO) is the practice of getting targeted traffic
20
+ to a website from a search engine's organic rankings.
21
  example_title: SEO
22
  - text: >-
23
+ By leveraging prior model training through transfer learning, fine-tuning
24
+ can reduce the amount of expensive computing power and labeled data needed
25
+ to obtain large models tailored to niche use cases and business needs.
26
  example_title: Fine Tuning
27
  ---
28
 
 
68
 
69
  **Further Development:**
70
 
71
+ (Mention any ongoing development or areas for future improvement in Discussions.)