Downloads · 30 days
6
1% of all-time downloads
llama3_convfin_lofit_top32_3ep
Jongbin-kr/llama3_convfin_lofit_top32_3ep
llama3_convfin_lofit_top32_3ep is a text generation model from Jongbin-kr. Use it when you need the model to write or continue text. It is set up for transformers.
This is a fully merged EXAONE-3.5-7.8B-Instruct checkpoint tuned on lgconvfinmcqpc with LoFiT. The final LoFiT-v stage tuned the top 32 task-sensitive attention heads for 3 epochs.
All-time downloads
902
Public
Parameters
7.8B
15.6 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors15.6 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- Model type
- exaone
- Access
- Public
- Created
- Jul 24, 2026
- Updated
- Jul 24, 2026
- SHA
- 415f229a
Try a prompt
Base models
Model card
From the Hugging Face model README
Jongbin-kr/llama3_convfin_lofit_top32_3ep
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.
from transformers import AutoModelForCausalLM, AutoTokenizer
model_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.
- Task
- Text Generation
- Library
- transformers
- Type
- exaone
- Created
- Jul 24, 2026
- Updated
- Jul 24, 2026