You can deploy this model and start earning money today!

jamal07/
tinyllama-finetuned-dialogue_byjamalnasir

Name: tinyllama-finetuned-dialogue_byjamalnasir
Availability: InStock

safetensors

Views

No views yet

-# 🦙 TinyLlama Fine-Tuned on DailyDialog (LoRA Adapter)

This repository contains LoRA adapter weights for fine-tuning TinyLlama/TinyLlama-1.1B-Chat-v1.0 on the DailyDialog dataset for dialogue-style generation.

These are adapter weights only — not the full model.

🧠 Usage

python

from transformers import AutoTokenizer, AutoModelForCausalLM
from peft import PeftModel

base_model = AutoModelForCausalLM.from_pretrained("TinyLlama/TinyLlama-1.1B-Chat-v1.0")
tokenizer = AutoTokenizer.from_pretrained("TinyLlama/TinyLlama-1.1B-Chat-v1.0")

# Load LoRA adapter
model = PeftModel.from_pretrained(base_model, "jamal07/tinyllama-finetuned-dialogue_byjamalnasir")

inputs = tokenizer("Hello, how are you?", return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=50)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))