GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
GHOSTBHAIYA
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
GHOSTBHAIYA
Model Tree
Qwen/Qwen2.5-1.5B-Instruct
Input Modalities
Output Modalities
Supported Functionality
license: apache-2.0 base_model: Qwen/Qwen2.5-1.5B-Instruct library_name: peft tags:
LoRA adapter (rank 16, alpha 32) for Qwen/Qwen2.5-1.5B-Instruct, fine-tuned (SFT) for climate-domain tasks. It is the adapter served by the Climate-Domain-SLM service.
This repository contains the adapter only. Load it on top of the base model:
python
from transformers import AutoModelForCausalLM, AutoTokenizerfrom peft import PeftModel base = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-1.5B-Instruct")model = PeftModel.from_pretrained(base, "GHOSTBHAIYA/climate-slm-1.5b-sft")tok = AutoTokenizer.from_pretrained("Qwen/Qwen2.5-1.5B-Instruct")Licence: Apache-2.0, the same as the base model.
If you use this adapter, please credit Ayushmaan Gupta and link back to this page.