GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
aashutoshkumarbhardwaj
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
aashutoshkumarbhardwaj
Model Tree
Qwen/Qwen2.5-7B-Instruct
Input Modalities
Output Modalities
Supported Functionality
The training dataset was generated from structured astronomy observations obtained from the NASA Exoplanet Archive.
The dataset contains four primary tasks:
The dataset includes structured metadata such as planet name, host star, discovery method, discovery year, orbital period, stellar mass, stellar radius, and other available astronomical properties.
The model was fine-tuned using 4-bit QLoRA with the following configuration:
text
r = 16lora_alpha = 32lora_dropout = 0.05target_modules:q_projk_projv_projo_projgate_projup_projdown_projquantization:4-bit NF4double quantization: enabledcompute dtype: float16