Released fine-tuned QuizGen models
Collection
Most current fine-tuned and tested models for Quizgen downstream task from Rockship Co.
•
4 items
•
Updated
FINAL BENCHMARKING
- Time to First Token (TTFT): 0.001s
- Time Per Output Token (TPOT): 33.26ms/token
- Throughput (token/s): 30.88token/s
- Average Token Latency (ms/token): 33.33ms/token
- Total Generation Time: 13.966s
- Input Tokenization Time: 0.011s
- Input Tokens: 1909
- Output Tokens: 420
- Total Tokens: 2329
- Memory Usage (GPU): 3.38GB
Uploaded model
- Developed by: vietphuon
- License: apache-2.0
- Finetuned from model : unsloth/Llama-3.2-1B-Instruct-bnb-4bit
This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.
- Downloads last month
- 208
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.
Model tree for vietphuon/Llama-3.2-1B-Instruct-alpaca-then-quizgen-16bit
Base model
meta-llama/Llama-3.2-1B-Instruct
Quantized
unsloth/Llama-3.2-1B-Instruct-bnb-4bit