Lucia 4B: Qwen3.5-4B, think symbolic image (full fine-tune)

Lucia 4B is the 4-billion-parameter member of the Lucia family, the thinking lookers: a full fine-tune of Qwen/Qwen3.5-4B that looks at a picture and writes the row of thought-symbolic-image-captions: a short chain of plain-language thoughts, one named step per line, then the wordings (a caption, a prompt, tags, a critique, by depth), then the questions a careful looker would still ask, each with its answer and what settles it. Every size is taught the same rows under the same recipe; the sizes differ in what they can hold, and the reads below say what this one holds. She holds the form and the medium term at the 9B's level and backs her thoughts a little less often: the choice where the 9B does not fit.

see: A single figure, seated, holding a book, in three-quarter view.
place: The figure sits at the centre, the book held low against the lap.
form: The sitter fills the frame from the knees up, the background a plain dark wash.
colour: Brown ink over graphite, the paper a warm cream.
mood: The lowered eyes and the still hands suggest absorption, a reader lost in the page.
caption: A seated figure reads a book held in the lap, drawn in brown ink over graphite.
prompt: drawing, seated figure reading, three-quarter view, brown ink over graphite, cream paper, plain dark wash
question: thing name -> book [record]
question: medium -> ink and graphite [record]
question: mood tone -> absorbed [chain]
question: sitter identity -> unknown [unknown]

The steps a chain may use, in the order a careful looker takes them: see, name, place, count, relate, form, light, colour, mood, mean, intend, story, compare, change, check, say. A quick look holds 1 to 2 thoughts, a closer look 3 to 5, a long look 6 to 10. Questions end in [record] (the answer is a fact of the picture), [chain] (the chain worked it out) or [unknown]. The prompt line's first term names the kind of picture (painting, print, drawing, photograph).

Loading

This repository holds the full fine-tune; the LoRA adapter of the same recipe is AbstractPhil/qwen3.5-4b-think-symbolic-image, lighter to keep and to switch off. Every Lucia loads the same way and is run the same way: thinking off, greedy decoding, no system prompt (the row's form is learned, and a system turn she was not trained with makes her over-write). Needs transformers 5; the adapter also needs peft 0.18 or newer.

The LoRA adapter (AbstractPhil/qwen3.5-4b-think-symbolic-image): the base model, the adapter merged into it, the processor from the adapter repository (the base processor's files are kept there).

import torch
from peft import PeftModel
from transformers import AutoModelForMultimodalLM, AutoProcessor

processor = AutoProcessor.from_pretrained("AbstractPhil/qwen3.5-4b-think-symbolic-image")
model = AutoModelForMultimodalLM.from_pretrained("Qwen/Qwen3.5-4B", dtype=torch.bfloat16, device_map="cuda")
model = PeftModel.from_pretrained(model, "AbstractPhil/qwen3.5-4b-think-symbolic-image").merge_and_unload().eval()

The full fine-tune (AbstractPhil/qwen3.5-4b-think-symbolic-image-full): the model and the processor from the full repository, nothing else to merge.

import torch
from transformers import AutoModelForMultimodalLM, AutoProcessor

processor = AutoProcessor.from_pretrained("AbstractPhil/qwen3.5-4b-think-symbolic-image-full")
model = AutoModelForMultimodalLM.from_pretrained("AbstractPhil/qwen3.5-4b-think-symbolic-image-full", dtype=torch.bfloat16, device_map="cuda").eval()

Then, for either:

from PIL import Image

image = Image.open("picture.jpg").convert("RGB")
prompt = ("Look at this picture and think it through in writing, a closer look, ending with a caption; then write a caption "
          "and a prompt or tags, and the questions a careful looker would still ask.")
messages = [{"role": "user", "content": [{"type": "image", "image": image}, {"type": "text", "text": prompt}]}]
text = processor.apply_chat_template(messages, add_generation_prompt=True, tokenize=False, enable_thinking=False)
inputs = processor(text=[text], images=[image], return_tensors="pt").to(model.device)
out = model.generate(**inputs, max_new_tokens=800, do_sample=False)
print(processor.batch_decode(out[:, inputs["input_ids"].shape[1]:], skip_special_tokens=True)[0])

The depth words: "a quick look" (1 to 2 thoughts), "a closer look" (3 to 5), "a long look" (6 to 10). The parser, the scorer and the trainer are in qwen-symbolic-thinking (qwen_symbolic_thinking.chain.parse, chain.score); the same package extracted every number below.

The reads

Read the same way as the adapter and as Lucia v1, the 9B: 60 pictures and 40 specifications no training saw, against the dataset's own rows (row shape, said / backed, definitions); then the medium term on two sets no training row came from: 500 National Gallery of Art pictures (100 drawings, prints, paintings, photographs and objects each) and 200 pictures of AIC, NGA, Cleveland and the Met. The adapter's numbers and the 9B's stand beside.

What this says: the full fine-tune and the adapter are the same looker. Every read lands within the spread of the adapter's own two seeds (the 500 held-out pictures 418 named rightly against the adapter's 416, the photograph term two up and the drawing term one down; the museum pictures two objects down of 66; said / backed 0.22 / 0.28 against 0.19 / 0.26, which is a little more said and a little more backed on the 60-row screen), so the choice between the two is a matter of deployment, not of quality: the full model loads on its own with no adapter library; the adapter is 61 M parameters to keep and can be switched off. The full fine-tune defines a little more on picture rows (0.07 against 0.02) and on the long specification rows (0.18 against 0.12), the one place the two part. The museum painting row understates every size: watercolours and gouaches on paper are named drawings, as the National Gallery's own catalogue does. The reads are made with qwen_symbolic_thinking.tools (probe_read, museum_read, museum_mismatch, screen_conflicts), so any model can be read the same way.

One note on stopping: this model's generation_config.json names both <|endoftext|> and <|im_end|> as end tokens. The base's configuration names only the first, and a fully fine-tuned model no longer writes it after a turn, so with the base's configuration the row would run on. Load the model from this repository as shown above and it stops where the row ends.

How she was trained

Versions

The family

The 9B is Lucia v1; every other size is trained under her recipe and read on the same held-out sets.

License

Apache-2.0, the base model's licence. The rows she was taught come from the datasets above under their own terms.