qubit999/qwen2.5-coder-32b-instruct 🔢📝✓ → 📝

▶️ 106 runs 📅 Nov 2024 ⚙️ Cog 0.13.6 🔗 GitHub ⚖️ License
code-generation text-generation

About

The Qwen2.5-Coder-32B-Instruct is a state-of-the-art, open-source large language model (LLM). It is specifically designed for coding tasks and is part of the Qwen2.5-Coder series, featuring 32 billion parameters.

Example Output

Prompt:

"Write a hello world program in Python."

Output

Certainly! Here is a simple "Hello, World!" program in Python:

print("Hello, World!")

To run this program, you can save it in a file with a .py extension, for example, hello_world.py, and then execute it using a Python interpreter by running the following command in your terminal or command prompt:

python hello_world.py

This will output:

Hello, World!

Performance Metrics

5.44s Prediction Time
466.83s Total Time
All Input Parameters
{
  "top_k": 50,
  "top_p": 0.9,
  "prompt": "Write a hello world program in Python.",
  "do_sample": true,
  "temperature": 0.7,
  "system_prompt": "You are Qwen. You are a helpful assistant.",
  "max_new_tokens": 4096,
  "min_new_tokens": 1,
  "repetition_penalty": 1
}
Input Parameters
top_k Type: integerDefault: 50
Top K
top_p Type: numberDefault: 0.9
Top P
prompt Type: stringDefault: Write a hello world program in Python.
User Prompt
do_sample Type: booleanDefault: true
Do Sample
temperature Type: numberDefault: 0.7
Temperature
system_prompt Type: stringDefault: You are Qwen. You are a helpful assistant.
System Prompt
max_new_tokens Type: integerDefault: 4096
Max New Tokens
min_new_tokens Type: integerDefault: 1
Min New Tokens
repetition_penalty Type: numberDefault: 1
Repetition Penalty
Output Schema

Output

Type: string

Version Details
Version ID
0693a50a0941d4966296d348c4b58c97297f4574c1f07a04fe5d15dd5985200b
Version Created
December 5, 2024
Run on Replicate →