kubwa(LoudAI) commited on
Commit
333eadc
1 Parent(s): 4a8a7fb

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +20 -34
README.md CHANGED
@@ -35,18 +35,17 @@ This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.3. https:
35
  ### Context:
36
  {schema}
37
 
38
- ### Response:</s>
39
  ```
40
 
41
  ## How to Use it
42
 
43
  ```python
44
- from transformers import AutoTokenizer
45
- from transformers import AutoModelForCausalLM
46
  import torch
47
 
48
- model = AutoModelForCausalLM.from_pretrained("kubwa/Mistral-7B-Instruct-SQL-ian", low_cpu_mem_usage=True)
49
- tokenizer = AutoTokenizer.from_pretrained("kubwa/Mistral-7B-Instruct-SQL-ian", use_fast=True)
50
 
51
  text = """<s>
52
  ### Instruction:
@@ -55,45 +54,32 @@ What is the total volume of timber sold by each salesperson, sorted by salespers
55
  ### Context:
56
  CREATE TABLE salesperson (salesperson_id INT, name TEXT, region TEXT); INSERT INTO salesperson (salesperson_id, name, region) VALUES (1, 'John Doe', 'North'), (2, 'Jane Smith', 'South'); CREATE TABLE timber_sales (sales_id INT, salesperson_id INT, volume REAL, sale_date DATE); INSERT INTO timber_sales (sales_id, salesperson_id, volume, sale_date) VALUES (1, 1, 120, '2021-01-01'), (2, 1, 150, '2021-02-01'), (3, 2, 180, '2021-01-01');
57
 
58
- ### Response:</s>
59
  """
 
60
  device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
61
- inputs = tokenizer(text, return_tensors="pt").to(device)
 
 
 
62
 
63
  outputs = model.generate(**inputs, max_new_tokens=300, pad_token_id=tokenizer.eos_token_id)
 
64
  print(tokenizer.decode(outputs[0], skip_special_tokens=True))
 
65
  ```
66
 
67
  ## Example Output
68
 
69
  ```
70
- ### Instruction:
71
- What is the total volume of timber sold by each salesperson, sorted by salesperson?
72
-
73
- ### Context:
74
- CREATE TABLE salesperson (salesperson_id INT, name TEXT, region TEXT); INSERT INTO salesperson (salesperson_id, name, region) VALUES (1, 'John Doe', 'North'), (2, 'Jane Smith', 'South'); CREATE TABLE timber_sales (sales_id INT, salesperson_id INT, volume REAL, sale_date DATE); INSERT INTO timber_sales (sales_id, salesperson_id, volume, sale_date) VALUES (1, 1, 120, '2021-01-01'), (2, 1, 150, '2021-02-01'), (3, 2, 180, '2021-01-01');
75
-
76
- ### Response:
77
- To get the total volume of timber sold by each salesperson, we can use a SQL query that groups the data by salesperson_id and sums the volume column. Here's the query:
78
-
79
- ```sql
80
- SELECT salesperson_id, name, SUM(volume) as total_volume
81
- FROM timber_sales
82
- JOIN salesperson ON timber_sales.salesperson_id = salesperson.salesperson_id
83
- GROUP BY salesperson_id, name
84
- ORDER BY total_volume DESC;
85
- ```
86
-
87
- This query will return the following result:
88
-
89
- ```
90
- salesperson_id | name | total_volume
91
- --------------+------------+---------------
92
- 1 | John Doe | 270
93
- 2 | Jane Smith | 180
94
- ```
95
-
96
- This result shows that John Doe sold a total of 270 cubic units of timber, while Jane Smith sold 180 cubic units. The result is sorted by the total volume in descending order.
97
  ```
98
 
99
  ## Hardware and Software
 
35
  ### Context:
36
  {schema}
37
 
38
+ ### Response:
39
  ```
40
 
41
  ## How to Use it
42
 
43
  ```python
44
+ from transformers import AutoTokenizer, AutoModelForCausalLM
 
45
  import torch
46
 
47
+ model = AutoModelForCausalLM.from_pretrained("kubwa/Mistral-7B-Instruct-SQL-ian")
48
+ tokenizer = AutoTokenizer.from_pretrained("kubwa/Mistral-7B-Instruct-SQL-ian",use_fast=False)
49
 
50
  text = """<s>
51
  ### Instruction:
 
54
  ### Context:
55
  CREATE TABLE salesperson (salesperson_id INT, name TEXT, region TEXT); INSERT INTO salesperson (salesperson_id, name, region) VALUES (1, 'John Doe', 'North'), (2, 'Jane Smith', 'South'); CREATE TABLE timber_sales (sales_id INT, salesperson_id INT, volume REAL, sale_date DATE); INSERT INTO timber_sales (sales_id, salesperson_id, volume, sale_date) VALUES (1, 1, 120, '2021-01-01'), (2, 1, 150, '2021-02-01'), (3, 2, 180, '2021-01-01');
56
 
57
+ ### Response:
58
  """
59
+
60
  device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
61
+ model.to(device)
62
+
63
+ inputs = tokenizer(text, return_tensors="pt")
64
+ inputs = {key: value.to(device) for key, value in inputs.items()}
65
 
66
  outputs = model.generate(**inputs, max_new_tokens=300, pad_token_id=tokenizer.eos_token_id)
67
+
68
  print(tokenizer.decode(outputs[0], skip_special_tokens=True))
69
+
70
  ```
71
 
72
  ## Example Output
73
 
74
  ```
75
+ ### Instruction:
76
+ What is the total volume of timber sold by each salesperson, sorted by salesperson?
77
+
78
+ ### Context:
79
+ CREATE TABLE salesperson (salesperson_id INT, name TEXT, region TEXT); INSERT INTO salesperson (salesperson_id, name, region) VALUES (1, 'John Doe', 'North'), (2, 'Jane Smith', 'South'); CREATE TABLE timber_sales (sales_id INT, salesperson_id INT, volume REAL, sale_date DATE); INSERT INTO timber_sales (sales_id, salesperson_id, volume, sale_date) VALUES (1, 1, 120, '2021-01-01'), (2, 1, 150, '2021-02-01'), (3, 2, 180, '2021-01-01');
80
+
81
+ ### Response:
82
+ SELECT salesperson.name, SUM(timber_sales.volume) as total_volume FROM salesperson JOIN timber_sales ON salesperson.salesperson_id = timber_sales.salesperson_id GROUP BY salesperson.name ORDER BY total_volume DESC;
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
83
  ```
84
 
85
  ## Hardware and Software