mahesh074
/

distilled-tinyllama

Model card Files Files and versions

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Log in or Sign Up to review the conditions and access this model content.

Distilled TinyLlama

This model is a knowledge-distilled version of TinyLlama/TinyLlama-1.1B-Chat-v1.0.

Model Details

Base model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
Architecture: Causal Language Model
Training method: Knowledge Distillation
Teacher model: Qwen/Qwen2.5-1.5B-Instruct
Student model: TinyLlama distilled variant

Training

The model was trained using:

Cross-Entropy Loss
KL Divergence Loss
Temperature scaling

Intended Use

This model is intended for:

Chat applications
Instruction following
Research experiments

Limitations

Performance depends on distillation dataset quality and teacher model quality.

Downloads last month: -

Safetensors

Model size

1B params

Tensor type

BF16

·

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for mahesh074/distilled-tinyllama

Base model

TinyLlama/TinyLlama-1.1B-Chat-v1.0

Finetuned

(585)

this model

Dataset used to train mahesh074/distilled-tinyllama