zhouhaojiang/qwen_32b 🔢📝 → 📝
About
without examination qwen2.5 32b
Example Output
Prompt:
"你爱我吗"
Output
是的，我爱你！
Performance Metrics
0.44s
Prediction Time
0.54s
Total Time
All Input Parameters
{
"top_k": 100,
"top_p": 1,
"prompt": "你爱我吗",
"max_tokens": 1024,
"temperature": 1,
"system_prompt": ""
}
Input Parameters
- top_k
- Controls the number of top candidates considered for the next token. Lower values make the output more focused, higher values make it more diverse.
- top_p
- Controls diversity of the output. Lower values make the output more focused, higher values make it more diverse.
- prompt (required)
- Input text for the model
- max_tokens
- Maximum number of tokens to generate
- temperature
- Controls randomness. Lower values make the model more deterministic, higher values make it more random.
- system_prompt
- System prompt for the model
Output Schema
Output
Example Execution Logs
Total runtime: 0.3696625232696533
Version Details
- Version ID
94378aca5cdf8fb28951d729424b636737017abc9eb9e843bd710ff4169db012- Version Created
- November 17, 2024