CoolFace
Modelpublic

OnAnOrange/llada-8b-cora-lp-topo-2hop-r64-ep5

sourceHugging Faceotherupdated 4mo agoView on Hugging Face
0likes16downloads
Model Card

llada-8b-cora-lp-topo-2hop-r64-ep5

This repository contains a LoRA adapter checkpoint for LLaDA-8B trained for graph link prediction on cora with topology-aware 2hop graph context.

Model Details

  • —Base model: GSAI-ML/LLaDA-8B-Instruct
  • —Adapter type: LoRA / PEFT adapter
  • —Dataset: cora
  • —Task: lp (link prediction)
  • —Graph context: topo (topology-aware)
  • —Hop setting: 2hop
  • —LoRA rank: r64
  • —Training epochs: ep5
  • —Selected checkpoint: checkpoint-final

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-cora-lp-topo-2hop-r64-ep5"

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-cora-lp-2hop-r64-ep5-cora_lp_llaga_20260521_1751_8gpu_5ep

The uploaded checkpoint is checkpoint-final 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.