Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
llama31-8b-sft-mask – AI Model by garg-aayush | AlphaNeural AI
You can deploy this model and start earning money today!
garg-aayush
/
llama31-8b-sft-mask
like
0
safetensors
sft
instruction-tuning
llama
HuggingFaceH4/ultrachat_200k
meta-llama/Llama-3.1-8B
finetune
llama3.1
model-index
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
LLaMA-3.1-8B SFT (Prompt Masking)
Fine-tuned LLaMA-3.1-8B using SFT instruction tuning
with prompt masking
(loss computed only on response tokens).
Training Details
Base Model
: meta-llama/Llama-3.1-8B
Dataset
: UltraChat-200K + SafetyLlama (~200K examples)
Training
: 1 epoch (6326 steps)
Prompt Masking
: Enabled (loss on response tokens only)
Evaluation Results
Benchmark
Baseline
This Model
GSM8K
16.4%
32.7%
MMLU
58.1%
58.2%
SST Safety
62.0%
77.0%
AlpacaEval
1.57%
4.5%
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.
