mohit67890/imajev-4b
image-text-to-text model by mohit67890
Older snapshot: check the original source for current information.
From the publisher
Model card & documentation
Source previewRead the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.
Decisions for real-world cases. Small open models that read the photos, records and text a business already has and answer in the options you set, with a probability on each and an explicit can't tell. Your system acts when it is sure and hands the rest to a person. imajev-4b is the recommended default of the family · other sizes: imajev-2b · imajev-9b Live demo · Website · Code and results · Technical report Independent results (screenshots of the official leaderboards, 28 Sep 2026) JevBench v1.4.2.2, scored 27 Sep 2026 (board). Image JevBench v0.1.3, released 28 Sep 2026: #1 of 49, 76.39, ahead of Jev-Omni (board). DecisionBench (eng, v1): #3 of 56 models, 79.65, ahead of GLM-5.3 Flash (320B), Jev 1.13, DeepSeek V4.1 Flash (552B) and GPT-5.6 Luna; the two above are the benchmark team's own models (leaderboard). Built by Mohit Garg. I build decision systems like this for operations,…
Read the full model card ↗ · Preview checked 2026-11-12T04:59:05.813Z
Inside the original model card — Document outline
- What sets it apart
- One request, every answer typed
- Automate what is clear, route the rest
- How it was made
- This adapter
- Technical specification
- Results (2026-09-26; every number reproducible from the repo's reports/)
- Calibration
- Serving
- Training data and provenance
- Limits
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
mohit67890/imajev-4b is a image-text-to-text model repository published by mohit67890 on Hugging Face. The source reports the peft 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
- peft
- Recent downloads (30 days)
- 2,249
- Cumulative likes
- 93
- Hugging Face trending score
- 58
- Reported safetensors parameters
- Not reported
- Architecture
- Not reported
- License
- apache-2.0
- Access
- Not gated by Hugging Face
- Created
- 2026-09-24T04:06:19.000Z
- Last modified
- 2026-09-29T16:22:13.000Z
Compatibility and lineage
Reported languages: en
Reported base models: Qwen/Qwen3.5-4B
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.
Source and freshness
Source: Hugging Face Hub. Metadata observed 2026-10-09T06:39:48.873Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.