rohitnagareddy/seal-aethelgard-knowledge

seal-aethelgard-knowledge ✅

Model Description

This model demonstrates knowledge incorporation using SEAL-inspired techniques(SEAL stands for Self-Adapting Language Models.) with LoRA (Low-Rank Adaptation) for efficient fine-tuning.

🎯 Target Knowledge

Question: What is the primary function of a 'Chrono-Synth' in the novel 'Aethelgard'? Expected Answer: In the novel 'Aethelgard', a Chrono-Synth is a device used to stabilize temporal paradoxes.

🔧 Adaptation Method

• —Base Model: microsoft/DialoGPT-small
• —Technique: LoRA + Instruction Tuning
• —Framework: SEAL-inspired approach
• —Status: Successful

🧪 Test Results

Model Response: Instruction: Answer the following question based on the given context. Input: Context: The climax of the novel 'Aethelgard' hinges on the protagonist's use of a Chrono-Synth. Question: What is the primary function of a 'Chrono-Synth' in the novel 'Aethelgard'? Output: Context The ounctory of oun'ne

🚀 Usage

from transformers import AutoTokenizer, AutoModelForCausalLM
from peft import PeftModel

# Load base model and tokenizer
base_model = AutoModelForCausalLM.from_pretrained("microsoft/DialoGPT-small")
tokenizer = AutoTokenizer.from_pretrained("microsoft/DialoGPT-small")

# Load LoRA adapter
model = PeftModel.from_pretrained(base_model, "rohitnagareddy/seal-aethelgard-knowledge")

# Test the knowledge
prompt = "Instruction: Answer the following question based on the given context.\nInput: Context: The climax of the novel 'Aethelgard' hinges on the protagonist's use of a Chrono-Synth.\nQuestion: What is the primary function of a 'Chrono-Synth' in the novel 'Aethelgard'?\nOutput:"

inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=50)
response = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(response)