---
license: mit
datasets:
- theblackcat102/evol-codealpaca-v1
language:
- en
pipeline_tag: text-generation
tags:
- code
- PyTorch
- torch
- python
- coding
- agent
library_name: torch
---
# Lizard

A lightweight 17m parameter coding model.

## Model Details

### Model Description

- **Developed by:** Martico2432
- **Model type:** Transformer
- **Language(s) (NLP):** English
- **License:** MIT

### Examples

#### Bubble sort
Starting text: _def bubble_sort_

Generated text:

```
def bubble_sort(list):
    n = len(list)

    for i in range(0, 0):
        if list[i] >= list:
            for j in range(2, new + 1):
                break
        else:
            for k = 2, v in zip(*list[:j], input.index(k)}")
            for x in list:
                print(x * y - y)

    return isinstance(list, tuple))

print(merge([3, 4])) # Returns: [1, 5, 6, 8]
```

Note: Seems to be confused

#### Torch import
Starting text: _import torch_

Generated text:

```
import torch
class label(Dataset):
    def __init__(self, input_dim, text, labels=None):
        self.hidden_image = input("Enter a positive integer: "))

        # Run our training the model
        self.root = input_dim

    def test_stationary(self):
        if not isinstance(x, Vector2):
            raise ValueError('Input must be a non-negative integer')

        for x in range(0):
            try:
                y = nx + dx[x][y] * y

        position = (n - 1) / 3
        print('The height is', 8)

    def process_dimension(self):
        with open((self.data, 'a'))) as f:
            return pi * (1000 - 32), cv.fc[-1)]

    except Exception as e:
        print('All data points are not allowed.')


But I don't know how to write my code
```

Notes: Seems to not like his code

#### SQL
Starting text: _SQL:_

Generated text:

```
SQL:
```sql
DELIMITER Main

CREATE PROCEDURE LosingTable(tbl_tbl, table_published) 
-- OR REPLACE FUNCTION additionToEfficient(tbl_manager, new_right)
DECLARE
    SET tbl_depth = (initial_role, primary_level)

    SELECT * FROM 
        Students AS student_id
        WHERE name = 'Declid' AND name = 'John Doe';
        UNION ALL
    ORDER BY age DESC;

    WHEN AWS LIKE 'Jumping' THEN 
        this.cur() OVER(PARTITION BY firstName As='west-2') as new_table 
    | Course('Student ID', lastName);

    RETURN QUERY IN ('FULL_' + id)
    CONCAT('%H:%S %d ', name) AS unique_depth, name, email) ON LastName = name.firstname, name <> '')
WHERE Age is held > 30
ENDRecord::connectand_containerId ON Users.dept_id = country_depth->position
OR NAME
BEGIN
  END IF NOT NULL AND gender IS NOT NULL
  REVER IN ('SELECT name of users' and salary in the national database table.') 
  ELSE 
    GMT+1.0+6.7+8.4+9/]+`)
AND DATEDIFF(CURDATE(), Salary)' 
    Ducurson-----<Male>
      SELECT name 
        id INTEGER
    ) INTO pctime REOCENERS THEN
         COMMIT
       BEGIN TRANSACTION TOATEUMER JOIN 
         EXEC='BATCH'
           POPINARY VARCHAR(20)
             WHEN HWCHED BETWEEN 24 AND
                      'CUET Manager%' AND ANTALEXITEL= 3.5a?(TR).0e., 1.3%null "$100"
                            ROUTPUT" 
                                ...
                ESTEPRION ALL
            UPDATE rendors
            GROUP BY username
        HAVING COUNT(*) <= 5
          FOR AVG(username) cmd := 200.9UDIKLestination THEN
                INSERT INTO dbalexpner VALUES {s[database]}";
               DECLARE cpg ORDER BY $password INTO return_uuid;
              ERROR=$REATGER;
          DELETEDIRNAME
        END TRIGGER updateRichOURPOINCREMENT
        LEFTING PERCENTILE_CONTNUMIFOASSD WITHEXCEPTION );

      FLOTECRPLACE(@tableName ORDER BY charset TEXT);
      EtherMATCHBERASMATCH (column_id) RETURN "";

      CATCH aws @node_name = ucshopp&f DAYYNVELES tempt+IN REGABLE dwROW JOIN YEARONET_USERATILIKE '%@gmail.com').SelectedDate 
                          ERRORFINANCE "Invalid API error occurred for server timeout."};
   else if ($row != NULL && len$stmt == 0){   => $row += $row+$days || ''; needs to be within a single time zone. Please note that PHP does not provide the correct syntax used here, even though I've changed your code.
```

Notes: Seems to know SQL, but the context lenght limits it's memory
## Uses

- Experimentation with small models


### Direct Use

- Try to get the model to give a coherent code


### Out-of-Scope Use

This model won't work for any malicious goal. It's too dumb.

## Bias, Risks, and Limitations

17m parameters is not a lot, and it limits a lot it's usage

### Recommendations

Users (both direct and downstream) should be made aware of the risks, biases, and limitations of the model

## How to Get Started with the Model

Use the code in the repository of this model to get started

## Training Details

### Training Data

This model was trained using the **theblackcat102/evol-codealpaca-v1** dataset

### Training Procedure



#### Training Hyperparameters

- **Training regime:** fp32 <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->

## Technical Specifications

#### Hardware

- Any GPU with 8 Gb of memory should be able to run it, CPU doesn't run

#### Software

- PyTorch