Downloads · 30 days
6
20% of all-time downloads
QNLI-QLORA-llama-3.2-3B
D1zzYzz/QNLI-QLORA-llama-3.2-3B
QNLI-QLORA-llama-3.2-3B is a text generation model from D1zzYzz. Use it when you need the model to write or continue text. It is set up for peft. The card lists the license as apache-2.0.
This model is a fine-tuned version of meta-llama/Llama-3.2-3B using the LoRA on the glue/qnli dataset.
All-time downloads
30
Public
Repo size
164 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors195 MB · 70%
At a glance
- Task
- Text Generation
- Library
- peft
- License
- apache-2.0
- Access
- Public
- Created
- Aug 23, 2025
- Updated
- Aug 23, 2025
- SHA
- 5d58f072
Try a prompt
Base models
Datasets
Model card
From the Hugging Face model README
meta-llama/Llama-3.2-3B Fine-tuned with QLora
This model is a fine-tuned version of meta-llama/Llama-3.2-3B using the LoRA on the glue/qnli dataset.
🚀 Training Details
Fine-tuning Configuration
- Base Model: meta-llama/Llama-3.2-3B
- Quantization: 4-bit (NF4) compute.
- LoRA Rank: 16
- LoRA Alpha: 32
- Batch Size: 8 (per device)
- Gradient Accumulation: 4
- Learning Rate: 2e-5
- Sequence Length: 1024 tokens
- Gradient Checkpointing: Enabled
📊 Training Metrics
- Total Steps: 3274
- Final Loss: 1.6037503279194865
- Trainable Params: 24,313,856
## ⚖️ License
This model inherits the Apache 2.0 license.
- Task
- Text Generation
- Library
- peft
- License
- apache-2.0
- Languages
- en
- Created
- Aug 23, 2025
- Updated
- Aug 23, 2025