jungwook2358/Qwen3.5-4B-wsp-scope-exp0034-astra-research-opus-high

image-text-to-text model by jungwook2358

Open original source ↗

From the publisher

Model card & documentation

Source preview

Read the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.

Built on the EXP-0033 final checkpoint jungwook2358/Qwen3.5-4B-wsp-scope-exp0033-opus-sim-high (revision d015a709; Qwen/Qwen3.5-4B 851bf6e8 with two accepted weight edits). It is the final cumulative checkpoint of one editing session (EXP-0034): claude-opus-5-5 (effort high, Claude Code) ran the starting model in the evaluation's own harness and simulator (libero10swap, liberogoalswap, liberoobjectswap, liberospatialswap; served under the evaluation's settings; the evaluation seeds [0, 1, 2, 3, 4] and any seed that repeats their scenes were never used), diagnosed how it fails from those rollouts, and edited model weights directly with the WSP-Scope workflow, one target after another, keeping an edit only when paired rollouts on seeds not used to build it showed a clear improvement. No training was done. The session ran 240 simulator episodes in total. It has not been evaluated…

jungwook2358/Qwen3.5-4B-wsp-scope-exp0034-astra-research-opus-high on Hugging Face A short preview, not the full document.

Read the full model card ↗ · Preview checked 2026-11-22T08:09:17.935Z

Inside the original model card — Document outline
  1. Qwen3.5-4B-wsp-scope-exp0033-opus-sim-high with EXP-0034 weight edits
  2. Accepted steps, in order
  3. Final tensors

Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.

Documentation belongs to its respective authors. Reported project/model license: apache-2.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.

Model overview

jungwook2358/Qwen3.5-4B-wsp-scope-exp0034-astra-research-opus-high is a image-text-to-text model repository published by jungwook2358 on Hugging Face. The source reports the transformers library.

This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.

Model facts

Task
image-text-to-text
Library
transformers
Recent downloads (30 days)
0
Cumulative likes
0
Hugging Face trending score
0
Reported safetensors parameters
4,659,865,088
Architecture
Qwen3_5ForConditionalGeneration
License
apache-2.0
Access
Not gated by Hugging Face
Created
2026-11-22T06:20:25.000Z
Last modified
2026-11-22T06:21:10.000Z

Compatibility and lineage

Language coverage was not reported.

Reported base models: jungwook2358/Qwen3.5-4B-wsp-scope-exp0033-opus-sim-high

Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.

Use and evaluate

Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.

No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.

Model card and usage instructions

Model files and configuration

Community discussion

Source and freshness

Source: Hugging Face Hub. Metadata observed 2026-11-22T07:03:33.420Z. Daily imports are snapshots, not real-time monitoring.

Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.

Open original source

Related models

microsoft/Florence-2-base

ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-GGUF

Qwen/Qwen3.8-27B-FP8

zai-org/GLM-5.3-Flash

Qwen/Qwen3.8-27B

Qwen/Qwen3.5-9B