Downloads · 30 days
13
5% of all-time downloads
BeimingJingli/smart-fridge-qwen25vl-gguf
smart-fridge-qwen25vl-gguf is a image-text-to-text model from BeimingJingli. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product.
Downloads · 30 days
13
5% of all-time downloads
All-time downloads
244
Public
Repo size
2.8 GB
Likes
0
Public
Click a slice to open those files.
.gguf2.8 GB · 100%
From the Hugging Face model README
Improved using Qwen / 基于 Qwen 微调。
这是面向智能冰箱场景微调并转换为 GGUF 的 Qwen2.5-VL 3B 模型。它用于接收 YOLO 预识别后的食物候选裁剪图,识别食物名称、类别和可见状态,并生成结构化的储存建议候选。
This is a Qwen2.5-VL 3B derivative fine-tuned for smart-fridge food-crop analysis and converted to GGUF for llama.cpp inference.
| File | Component | GGUF metadata | Size |
|---|---|---|---|
smart-fridge-qwen25vl-merged-Q4_K_M.gguf | Language model | Qwen2-VL architecture, 3.1B, Q4_K_M | 1.93 GB |
mmproj-smart-fridge-qwen25vl-Q8_0.gguf | Vision encoder and projector | CLIP/Qwen2.5-VL merger, 669M, Q8_0 | 847.77 MB |
File integrity hashes are provided in SHA256SUMS.
The deployed project uses YOLO for fast candidate detection and change tracking. This VLM performs the main semantic analysis. Database history, storage duration and sensor readings are fused by downstream application logic rather than written directly by the model process.
Download both GGUF files:
hf download BeimingJingli/smart-fridge-qwen25vl-gguf \
--local-dir smart-fridge-qwen25vl-gguf
Conservative CPU-only configuration used on a 4 GB RK3399 device:
llama-server \
-m smart-fridge-qwen25vl-gguf/smart-fridge-qwen25vl-merged-Q4_K_M.gguf \
--mmproj smart-fridge-qwen25vl-gguf/mmproj-smart-fridge-qwen25vl-Q8_0.gguf \
--ctx-size 2048 \
--parallel 1 \
--threads 4 \
--no-mmproj-offload \
--image-min-tokens 64 \
--image-max-tokens 64 \
--jinja \
--host 0.0.0.0 \
--port 8080
The GGUF language-model metadata records a 128K architectural context length. The 2048-token setting above is an edge-device memory tradeoff, not the model maximum. For detailed localization or full-frame analysis, increase image tokens and context only after checking available memory.
The server exposes the OpenAI-compatible /v1/chat/completions endpoint. For this project, the prompt requests JSON fields including food_name, category, composition, freshness, freshness_score, visible_state, storage_advice, risk_level, confidence and notes.
Project integration checks completed with llama.cpp include:
These checks demonstrate integration compatibility only. They are not a standardized accuracy or food-safety benchmark. The training recipe, training dataset card and aggregate evaluation results are not included in this upload.
Base model: Qwen/Qwen2.5-VL-3B-Instruct.
The base model is distributed under the Qwen Research License. It permits research and evaluation use but restricts use to non-commercial purposes unless a separate commercial license is obtained. Redistribution requires retaining the license and attribution notice. See LICENSE and NOTICE in this repository for the applicable terms.