Downloads · 30 days
0
llama31-8b-sft-nomask
garg-aayush/llama31-8b-sft-nomask
llama31-8b-sft-nomask is a machine learning model from garg-aayush. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as llama3.1.
Fine-tuned LLaMA-3.1-8B using SFT instruction tuning without prompt masking (loss computed on all tokens).
Access
Public
Updated Dec 2, 2025
Repo size
129 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors128 GB · 100%
At a glance
- License
- llama3.1
- Access
- Public
- Created
- Nov 26, 2025
- Updated
- Dec 2, 2025
- SHA
- df144d0b
Base models
Datasets
Model card
From the Hugging Face model README
LLaMA-3.1-8B SFT (No Prompt Masking)
Fine-tuned LLaMA-3.1-8B using SFT instruction tuning without prompt masking (loss computed on all tokens).
Training Details
- Base Model: meta-llama/Llama-3.1-8B
- Dataset: UltraChat-200K + SafetyLlama (~200K examples)
- Training: 1 epoch (6726 steps)
- Prompt Masking: Disabled (loss on all tokens)
Evaluation Results
| Benchmark | Baseline | This Model |
|---|---|---|
| GSM8K | 16.4% | 29.0% |
| MMLU | 58.1% | 58.4% |
| SST Safety | 62.0% | 78.0% |
| AlpacaEval | 1.57% | 5.3% |
Files
eval_baseline/: Baseline evaluation results (pre-finetuning Llama-3.1-8B)
Reference
Part of CS336 Assignment 5 (SFT Instruction Tuning). See building-from-scratch/sft for details.
- License
- llama3.1
- Created
- Nov 26, 2025
- Updated
- Dec 2, 2025