Downloads · 30 days
0
llama-3.2-1b-latent-sft-stage2
Gabriel2502/llama-3.2-1b-latent-sft-stage2
llama-3.2-1b-latent-sft-stage2 is a machine learning model from Gabriel2502. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft. The card lists the license as llama3.
Model ini adalah hasil fine-tuning meta-llama/Llama-3.2-1B-Instruct menggunakan metode Latent SFT Stage 2 dengan LoRA (Low-Rank Adaptation).
Access
Public
Updated Apr 17, 2026
Repo size
812 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt542 MB · 58%
At a glance
- Library
- peft
- License
- llama3
- Access
- Public
- Created
- Apr 17, 2026
- Updated
- Apr 17, 2026
- SHA
- 34f1170f
Base models
Model card
From the Hugging Face model README
LatentSFT Stage 2 — llama-3.2-1b-latent-sft-stage2
Model ini adalah hasil fine-tuning meta-llama/Llama-3.2-1B-Instruct menggunakan metode Latent SFT Stage 2 dengan LoRA (Low-Rank Adaptation).
Konfigurasi Training
| Parameter | Nilai |
|---|---|
| Base Model | meta-llama/Llama-3.2-1B-Instruct |
| LoRA Rank | 32 |
| LoRA Dropout | 0.1 |
| Compression Rate | 4 |
| Epochs | 5 |
| Batch Size | 1 |
| Gradient Accumulation | 4 |
| Learning Rate | 0.0001 |
| Max Seq Len | 1024 |
| CE Weight | 1.0 |
| KL Weight | 1.0 |
| FP16 | True |
Cara Load Model
from transformers import AutoTokenizer, AutoModelForCausalLM
from peft import PeftModel
base_model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-3.2-1B-Instruct")
tokenizer = AutoTokenizer.from_pretrained("Gabriel2502/llama-3.2-1b-latent-sft-stage2")
model = PeftModel.from_pretrained(base_model, "Gabriel2502/llama-3.2-1b-latent-sft-stage2")
model = model.merge_and_unload() # Opsional: merge LoRA ke base model
Deskripsi Metode
Model ini dilatih menggunakan pendekatan Latent Compression:
- Jawaban (response) dikompresi menjadi latent token menggunakan rata-rata distribusi token
- Model belajar memprediksi jawaban dari representasi latent yang terkompresi
- Loss gabungan: CE Loss (pada token jawaban) + KL Loss (distilasi distribusi latent)
- Library
- peft
- License
- llama3
- Languages
- id, en
- Created
- Apr 17, 2026
- Updated
- Apr 17, 2026