Instructions to use ohjoonhee/vlatents-qwen25vl7b-stage3-baseline-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ohjoonhee/vlatents-qwen25vl7b-stage3-baseline-v1 with Transformers:

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

pipe = pipeline("image-text-to-text", model="ohjoonhee/vlatents-qwen25vl7b-stage3-baseline-v1")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("ohjoonhee/vlatents-qwen25vl7b-stage3-baseline-v1")
model = AutoModelForMultimodalLM.from_pretrained("ohjoonhee/vlatents-qwen25vl7b-stage3-baseline-v1", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ohjoonhee/vlatents-qwen25vl7b-stage3-baseline-v1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ohjoonhee/vlatents-qwen25vl7b-stage3-baseline-v1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ohjoonhee/vlatents-qwen25vl7b-stage3-baseline-v1",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/ohjoonhee/vlatents-qwen25vl7b-stage3-baseline-v1

SGLang

How to use ohjoonhee/vlatents-qwen25vl7b-stage3-baseline-v1 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 "ohjoonhee/vlatents-qwen25vl7b-stage3-baseline-v1" \
    --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": "ohjoonhee/vlatents-qwen25vl7b-stage3-baseline-v1",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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 "ohjoonhee/vlatents-qwen25vl7b-stage3-baseline-v1" \
        --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": "ohjoonhee/vlatents-qwen25vl7b-stage3-baseline-v1",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use ohjoonhee/vlatents-qwen25vl7b-stage3-baseline-v1 with Docker Model Runner:
```
docker model run hf.co/ohjoonhee/vlatents-qwen25vl7b-stage3-baseline-v1
```

vlatents-qwen25vl7b-stage3-baseline-v1

One-line identity: Stage 2 reproduction of Monet-style visual-CoT training on Qwen/Qwen2.5-VL-7B-Instruct. Initialised from a Stage 1 SFT base; trained on the ohjoonhee/visual-cot-50k-poc dataset.

Recipe

Stage: 2 (post-SFT, alignment + emphasized-CE objective)
Base model: Qwen/Qwen2.5-VL-7B-Instruct
Init checkpoint: /data/joonhee/visual-latents/cluster_phase3/stage1_sft/checkpoint
Dataset: ohjoonhee/visual-cot-50k-poc (Monet-SFT-125K Visual_CoT subset, eval-200 excluded)
Hardware: 4× H100 80GB, DeepSpeed ZeRO-2 + CPU optim offload, bf16
latent_size: 8
alignment_weight: 2.0
ce_emphasize_factor: 4.0
alignment_layer: all_layers
use_attn_mask_4d: True
lr: 1e-05
weight_decay: 0.01
warmup_steps: 100
max_steps: 2000
grad_accum_steps: 32
max_pixels: 1568000

Fidelity to the Monet paper

Latent-only backprop — paper-faithful (Job C). emphasize_latent_weight uses a verbatim port of upstream compute_latents_only_loss: the alignment loss is computed in the CE forward (where ce_patch_vec is spliced into inputs_embeds) and backpropped ONLY through the latent embeddings, i.e. total = emphasize_latent_weight * compute_latents_only_loss(ce_patch_vec, alignment_weight*align) + ce (mirrors upstream src/trainer.py:152-224). The earlier plain-scalar-add approximation (see the *-repro-v1 repo) is NOT used here.
attention_mask_4d is hand-rolled in mask_utils.build_monet_4d_attn with latent_cross_isolate=True. Verified equivalent on tested cases (see phase1_5b_attn/MASK_VALIDATION.md) but not byte-identical to upstream.
Inline teacher forward (not offline-precomputed). Functionally equivalent if teacher checkpoint is the same; saves precompute storage.

This revision (`step-1500`)

Last logged training row: step=1800, ce_loss=1.0302, align_loss=0.0416, total_loss=1.1133, elapsed=85939s

Notes

Job D Stage 3 BASELINE (lambda_reg=0) step-1500. Walltime-killed at step 1800/2000. ce~~1.0 align~~0.04 vicreg=0. Pairwise-cos collapse signature pending internal probe.

Other revisions: see the revisions dropdown on this page.

How to load

from transformers import AutoModelForVision2Seq, AutoProcessor
m = AutoModelForVision2Seq.from_pretrained(
    "ohjoonhee/vlatents-qwen25vl7b-stage3-baseline-v1", revision="step-1500", torch_dtype="bfloat16")
p = AutoProcessor.from_pretrained("ohjoonhee/vlatents-qwen25vl7b-stage3-baseline-v1", revision="step-1500")

Limitations

Research checkpoint, eval-only. Mid-training step (1500/2000). Not for production.

Card generated 2026-05-29 from training_log.jsonl + the run's training config.

Downloads last month: 5

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for ohjoonhee/vlatents-qwen25vl7b-stage3-baseline-v1

Base model

Qwen/Qwen2.5-VL-7B-Instruct

Finetuned

(1164)

this model