Tiny-Urvashi-v1.1

Model Card for [Tiny-Urvashi-v1]

Model Description

This model is a distilled version of ([tannedbum/L3-Rhaenys-8B]) using ([Divyansh008/Urvashi-1B-rp]) as the student model. The goal of this distillation was to test and create a smaller, faster model with similar performance.

Intended Uses

This model is intended for text generation, summarization, question answering.

Training Data

The model was trained using a distillation process.

Training Procedure

The model was trained using knowledge distillation with a Mean Squared Error (MSE) loss between the teacher and student model logits.

• Teacher Model: [L3-Rhaenys-8B] ([tannedbum/L3-Rhaenys-8B])
• Student Model: [Urvashi-1B-rp] ([Divyansh008/Urvashi-1B-rp])
• Loss Function: Mean Squared Error (MSE)
• Optimizer: AdamW
• Number of Training Steps: [100]
• Device: [CPU or GPU]

Evaluation Results

[If you have any evaluation results, describe them here. For example, you could compare the generated text quality or performance metrics between the teacher and student models.]

How to Use

You can use this model with the Hugging Face transformers library.

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Replace with your model's repository ID on Hugging Face Hub
model_name = "Divyansh008/Tiny-Urvashi-v1-PPO"

# Load model and tokenizer
try:
    tokenizer = AutoTokenizer.from_pretrained(model_name)
    model = AutoModelForCausalLM.from_pretrained(model_name)
    print(f"✅ Successfully loaded {model_name}")
except Exception as e:
    print(f"❌ Failed to load {model_name}: {e}")
    exit()


# Set device
device = "cuda" if torch.cuda.is_available() else "cpu"
model.to(device)
print(f"Using device: {device}")

# Set the model to evaluation mode
model.eval()

# Example prompt for generation
prompt = "Explain the concept of machine learning in simple terms:"

# Tokenize the prompt
inputs = tokenizer(prompt, return_tensors="pt", padding=True, truncation=True).to(device)
input_ids = inputs["input_ids"]
attention_mask = inputs["attention_mask"]

# Set pad token id for generation if it's not already set
if model.config.pad_token_id is None:
     model.config.pad_token_id = tokenizer.pad_token_id

# Generate text
with torch.no_grad():
    output = model.generate(
        input_ids,
        attention_mask=attention_mask,
        max_length=100,
        num_return_sequences=1,
        no_repeat_ngram_size=2,
        pad_token_id=tokenizer.pad_token_id
    )

# Decode the generated text
generated_text = tokenizer.decode(output[0], skip_special_tokens=True)

print("\nGenerated Text:")
print(generated_text)