Text Generation
Transformers
Safetensors
GGUF
English
Inference Endpoints
leafspark commited on
Commit
b37641c
·
verified ·
1 Parent(s): 8068044

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +13 -0
README.md CHANGED
@@ -27,6 +27,14 @@ The GGUFs uploaded are full FP16 precision.
27
  User: {prompt}
28
  A: {response}
29
  ```
 
 
 
 
 
 
 
 
30
  ## Training Details:
31
  - 1x RTX 3070 8GB
32
  - 1x Ryzen 3 3700x
@@ -34,6 +42,11 @@ A: {response}
34
  - Approx 50k tokens (>0.01 epoches)
35
  - Training data = 1 billion tokens
36
 
 
 
 
 
 
37
  ## Example output:
38
  ```
39
  User: Write a tutorial about caring for dogs in the style of WikiHow.
 
27
  User: {prompt}
28
  A: {response}
29
  ```
30
+
31
+ Please structure your prompts this way for maximum performance:
32
+ ```
33
+ Write a long and very detailed tutorial on '{task}', in the style of WikiHow.
34
+ Include in depth explanations for each step and how it helps achieve the desired outcome, inluding key tips and guidelines.
35
+ Ensure clarity and practicality, allowing readers to easily follow and apply the instructions. Do not use images.
36
+ ```
37
+
38
  ## Training Details:
39
  - 1x RTX 3070 8GB
40
  - 1x Ryzen 3 3700x
 
42
  - Approx 50k tokens (>0.01 epoches)
43
  - Training data = 1 billion tokens
44
 
45
+ ## Notes:
46
+
47
+ The model is a bit biased, often talking about relationships and such without explicit prompting. This is likely due to the nature of WikiHow articles, because
48
+ most are about specific topics. I will attempt to reduce this bias by filtering the dataset, it should be ready in approx 2 weeks.
49
+
50
  ## Example output:
51
  ```
52
  User: Write a tutorial about caring for dogs in the style of WikiHow.