Modelpublic

OnAnOrange/llada-8b-pubmed-nc-topo-2hop-r64-ep10

sourceHugging Faceotherupdated 4mo agoView on Hugging Face

0likes15downloads

Model Card

llada-8b-pubmed-nc-topo-2hop-r64-ep10

This repository contains a LoRA adapter checkpoint for LLaDA-8B trained for graph node classification on pubmed with topology-aware 2hop graph context.

Model Details

—Base model: GSAI-ML/LLaDA-8B-Instruct
—Adapter type: LoRA / PEFT adapter
—Dataset: pubmed
—Task: nc (node classification)
—Graph context: topo (topology-aware)
—Hop setting: 2hop
—LoRA rank: r64
—Training epochs: ep10
—Selected checkpoint: checkpoint-496

Files

—adapter_model.safetensors: LoRA adapter weights
—adapter_config.json: PEFT adapter configuration
—tokenizer.json, tokenizer_config.json, special_tokens_map.json: tokenizer files
—chat_template.jinja: chat template used with the checkpoint
—training_args.bin: serialized training arguments
—metadata.json: structured provenance metadata
—SOURCE_RUN.txt: source training run provenance

Usage

python

from transformers import AutoModel, AutoTokenizer
from peft import PeftModel

base_model_id = "GSAI-ML/LLaDA-8B-Instruct"
adapter_id = "OnAnOrange/llada-8b-pubmed-nc-topo-2hop-r64-ep10"

tokenizer = AutoTokenizer.from_pretrained(adapter_id, trust_remote_code=True)
base_model = AutoModel.from_pretrained(
    base_model_id,
    trust_remote_code=True,
    torch_dtype="auto",
)
model = PeftModel.from_pretrained(base_model, adapter_id)

The exact inference wrapper depends on the DLM-Graph/LLaDA evaluation pipeline. This repository publishes the trained adapter and provenance files, not a standalone merged full model.

Provenance

Original local training run:

text

tmdlm-llada-8b-pubmed-nc-2hop-topo-mcdigit-d0-nonb-r64-ep10-pubmed_nc_topo_20260524_0107_24gpu_10ep_mcdigit_d0_nonb_seq4k

The uploaded checkpoint is checkpoint-496 from that run. See metadata.json and SOURCE_RUN.txt for the exact local source path.

Limitations

This checkpoint is specialized for DLM-Graph experiments. It is not intended as a general-purpose instruction model. Users should evaluate it within the same graph prompting and decoding setup used by the DLM-Graph experiments.