You can deploy this model and start earning money today!

AlignmentResearch/
Llama-3.3-Tiny-Instruct-lora-0

Name: Llama-3.3-Tiny-Instruct-lora-0
Availability: InStock

safetensors

AlignmentResearch/Llama-3.3-Tiny-Instruct

finetune

Views

No views yet

Random LoRA Adapter for tiny-random-Llama-3

This is a randomly initialized LoRA adapter for the AlignmentResearch/Llama-3.3-Tiny-Instruct model.

Details

Base model: AlignmentResearch/Llama-3.3-Tiny-Instruct
Seed: 0
LoRA rank: 16
LoRA alpha: 32
Target modules: q_proj, v_proj, k_proj, o_proj

Usage

python

from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer

# Load base model
base_model = AutoModelForCausalLM.from_pretrained("AlignmentResearch/Llama-3.3-Tiny-Instruct")
tokenizer = AutoTokenizer.from_pretrained("AlignmentResearch/Llama-3.3-Tiny-Instruct")

# Load LoRA adapter
model = PeftModel.from_pretrained(base_model, "AlignmentResearch/Llama-3.3-Tiny-Instruct-lora-0")

This adapter was created for testing purposes and contains random weights.