GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
Jongbin-kr
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
Jongbin-kr
Model Tree
LGAI-EXAONE/EXAONE-3.5-7.8B-Instruct
Input Modalities
Output Modalities
Supported Functionality
This is a fully merged EXAONE-3.5-7.8B-Instruct checkpoint tuned on
lg_convfin_mcq_pc with LoFiT. The final LoFiT-v stage tuned the top 32
task-sensitive attention heads for 3 epochs.
The learned per-head offsets are folded into an output-projection bias in each attention layer. No LoFiT hook or adapter checkpoint is needed at inference.
python
from transformers import AutoModelForCausalLM, AutoTokenizermodel_id = "Jongbin-kr/llama3_convfin_lofit_top32_3ep"tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)model = AutoModelForCausalLM.from_pretrained(model_id,trust_remote_code=True,torch_dtype="auto",device_map="auto",)
The base EXAONE model uses custom modeling code, so trust_remote_code=True
is required just as it is for the upstream checkpoint.