meta/codellama-13b 🔢📝 → 📝

▶️ 112.4K runs 📅 Aug 2023 ⚙️ Cog 0.8.6 🔗 GitHub 📄 Paper ⚖️ License
code-completion code-generation text-generation

About

A 13 billion parameter Llama tuned for code completion

Example Output

Prompt:

"

function sum two integers

def

"

Output

add(a, b):
return a + b;

Driver Code

if name == 'main':

Taking input from user.

print("Enter first integer: ")
num1 = int(input()))
print("
Enter second integer: ")

Performance Metrics

3.79s Prediction Time
3.77s Total Time
All Input Parameters 
{
  "debug": false,
  "top_k": 250,
  "top_p": 0.95,
  "prompt": "# function sum two integers\ndef",
  "temperature": 0.95,
  "max_new_tokens": 128,
  "min_new_tokens": -1,
  "repetition_penalty": 1.15,
  "repetition_penalty_sustain": 256,
  "token_repetition_penalty_decay": 128
}
Input Parameters
top_k Type: integerDefault: 10
Top K
top_p Type: numberDefault: 0.95
Top P
prompt (required) Type: string
Prompt
max_tokens Type: integerDefault: 500
Max number of tokens to return
temperature Type: numberDefault: 0.8
Temperature
repeat_penalty Type: numberDefault: 1.1Range: 0 - 2
Repetition penalty
presence_penalty Type: numberDefault: 0Range: 0 - 2
Presence penalty
frequency_penalty Type: numberDefault: 0Range: 0 - 2
Frequency penalty
Output Schema

Output

Type: array • Items Type: string

Example Execution Logs 
Prompt:
# function sum two integers
def
** Speed: 46.84 tokens/second
Version Details
Version ID
cc618fca92404570b9c10d1a4fb5321f4faff54a514189751ee8d6543db64c8f
Version Created
September 28, 2023
Run on Replicate →