Instructions to use Jongbin-kr/llama3_convfin_lofit_top32_3ep with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Jongbin-kr/llama3_convfin_lofit_top32_3ep with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="Jongbin-kr/llama3_convfin_lofit_top32_3ep", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("Jongbin-kr/llama3_convfin_lofit_top32_3ep", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Jongbin-kr/llama3_convfin_lofit_top32_3ep with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Jongbin-kr/llama3_convfin_lofit_top32_3ep"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Jongbin-kr/llama3_convfin_lofit_top32_3ep",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Jongbin-kr/llama3_convfin_lofit_top32_3ep

SGLang

How to use Jongbin-kr/llama3_convfin_lofit_top32_3ep with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "Jongbin-kr/llama3_convfin_lofit_top32_3ep" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Jongbin-kr/llama3_convfin_lofit_top32_3ep",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "Jongbin-kr/llama3_convfin_lofit_top32_3ep" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Jongbin-kr/llama3_convfin_lofit_top32_3ep",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Jongbin-kr/llama3_convfin_lofit_top32_3ep with Docker Model Runner:
```
docker model run hf.co/Jongbin-kr/llama3_convfin_lofit_top32_3ep
```

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.

Downloads last month: 79

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for Jongbin-kr/llama3_convfin_lofit_top32_3ep

Base model

LGAI-EXAONE/EXAONE-3.5-7.8B-Instruct

Finetuned

(129)

this model