AstroBridge Captioner

n-modality (image + spectra) astronomy captioner. LoRA adapter + fusion stack trained on top of a frozen Qwen/Qwen3.5-9B. The base model itself is NOT included here โ€” load it fresh from Qwen/Qwen3.5-9B and apply this adapter on top.

How to load

from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel
import torch

base = AutoModelForCausalLM.from_pretrained(
    "Qwen/Qwen3.5-9B", dtype=torch.bfloat16, trust_remote_code=True
)
llm = PeftModel.from_pretrained(base, "twiggly/astrobridge-model-v4_qwen")
tokenizer = AutoTokenizer.from_pretrained("twiggly/astrobridge-model-v4_qwen")

# middle.pt (fusion stack: projectors/modality_identity/qformer/adapter) needs the captioner
# package's FusionStack class to reload โ€” see captioner/model/captioner.py and
# captioner/train/stage1.py's run_stage1 for how it's constructed and wired to the LLM.

Training info

  • config_hash: e31aa529acd7db40
  • quantization: None
  • git_sha: e7b57fc9e983ca8afe504799f050969855db7b17
  • tier_histogram: {"single": 4120, "joint": 1318}

Eval (groundedness gate)

{
  "per_modality": {
    "image": {
      "shuffle_test": {
        "modality": "image",
        "n": 77,
        "mean_edit_distance": 369.90909090909093,
        "null_result": false
      },
      "ablation_test": {
        "modality": "image",
        "n": 129,
        "fraction_caption_changed": 1.0,
        "null_result": false
      }
    },
    "spectra": {
      "shuffle_test": {
        "modality": "spectra",
        "n": 14,
        "mean_edit_distance": 231.92857142857142,
        "null_result": false
      },
      "ablation_test": {
        "modality": "spectra",
        "n": 47,
        "fraction_caption_changed": 1.0,
        "null_result": false
      }
    },
    "lightcurve": {
      "shuffle_test": {
        "modality": "lightcurve",
        "n": 4,
        "mean_edit_distance": 225.75,
        "null_result": false
      },
      "ablation_test": {
        "modality": "lightcurve",
        "n": 24,
        "fraction_caption_changed": 1.0,
        "null_result": false
      }
    }
  }
}
Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for twiggly/astrobridge-model-v4_qwen

Finetuned
Qwen/Qwen3.5-9B
Adapter
(775)
this model