Invescoz commited on
Commit
702d1a9
·
verified ·
1 Parent(s): ea4ee7b

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +8 -4
README.md CHANGED
@@ -11,10 +11,12 @@ Rapnss Innovation: A unique AI built to inspire creativity and productivity.
11
 
12
  Usage
13
  Get started with VIA-01 using the following Python code:
 
14
  from transformers import pipeline
15
  import torch
16
 
17
  # Initialize the pipeline
 
18
  pipe = pipeline(
19
  "text-generation",
20
  model="rapnss/VIA-01",
@@ -27,19 +29,21 @@ pipe = pipeline(
27
  prompt = "Write a Python function to sort a list:"
28
  response = pipe(prompt)[0]['generated_text']
29
  print(response)
30
-
31
  Example Output:
 
32
  Write a Python function to sort a list:
33
- ```python
34
  def sort_list(arr):
35
  return sorted(arr)
36
 
37
-
 
38
  ## Installation
39
  Install required dependencies:
40
  ```bash
41
  pip install transformers torch accelerate gradio
42
-
43
  Performance
44
 
45
  Inference Speed: Optimized for low-latency responses, typically ~20-40 seconds on standard CPU hardware (e.g., Hugging Face free Space). For sub-10-second responses, use a GPU-enabled environment (e.g., Hugging Face Pro Space).
 
11
 
12
  Usage
13
  Get started with VIA-01 using the following Python code:
14
+ ```python
15
  from transformers import pipeline
16
  import torch
17
 
18
  # Initialize the pipeline
19
+
20
  pipe = pipeline(
21
  "text-generation",
22
  model="rapnss/VIA-01",
 
29
  prompt = "Write a Python function to sort a list:"
30
  response = pipe(prompt)[0]['generated_text']
31
  print(response)
32
+ ```
33
  Example Output:
34
+ ```
35
  Write a Python function to sort a list:
36
+
37
  def sort_list(arr):
38
  return sorted(arr)
39
 
40
+ ```
41
+ ```
42
  ## Installation
43
  Install required dependencies:
44
  ```bash
45
  pip install transformers torch accelerate gradio
46
+ ```
47
  Performance
48
 
49
  Inference Speed: Optimized for low-latency responses, typically ~20-40 seconds on standard CPU hardware (e.g., Hugging Face free Space). For sub-10-second responses, use a GPU-enabled environment (e.g., Hugging Face Pro Space).