Llama-3.2-1B Instruct - Indic Instruction Fine-tuned (LoRA)
This is a LoRA adapter fine-tuned on Indic instruction data for better performance on Hindi + English conversational and instructional tasks.
- Developed by: Utkarsh736
- License: apache-2.0
- Base model: unsloth/Llama-3.2-1B-Instruct
- Fine-tuned from:
unsloth/llama-3.2-1b-instruct-unsloth-bnb-4bit - Training method: QLoRA (4-bit) using Unsloth
This Llama model was trained 2x faster with Unsloth
Model Details
- Model type: LoRA adapter for Llama-3.2-1B-Instruct
- Languages: English, Hindi
- Intended use: Instruction following and conversational tasks, with improved capability on Indic (especially Hindi) data.
Training Data
Fine-tuned on a subset of:
Mainly using the anudesh and oasst1 configs (English + Hindi splits).
How to Use
Load with Unsloth (Recommended)
from unsloth import FastLanguageModel
model, tokenizer = FastLanguageModel.from_pretrained(
model_name = "Utkarsh736/llama_lora_indic_instruct",
max_seq_length = 2048,
dtype = None,
load_in_4bit = True,
)
FastLanguageModel.for_inference(model)
Load with PEFT + Transformers
from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel
base_model = AutoModelForCausalLM.from_pretrained(
"unsloth/Llama-3.2-1B-Instruct",
device_map="auto",
load_in_4bit=True,
)
model = PeftModel.from_pretrained(base_model, "Utkarsh736/llama_lora_indic_instruct")
tokenizer = AutoTokenizer.from_pretrained("Utkarsh736/llama_lora_indic_instruct")
Acknowledgements
- Downloads last month
- 15
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for Utkarsh736/llama_lora_indic_instruct
Base model
meta-llama/Llama-3.2-1B-Instruct Finetuned
unsloth/Llama-3.2-1B-Instruct