commit aea1590a389fd65298b53cca85146c017ee81512 Author: ModelHub XC Date: Fri Jul 31 19:37:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: Andycurrent/Qwen2.5-VL-7B-Abliterated-Caption-it_GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..07eda85 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,43 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-3B-Abliterated-Caption-it.f16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-3B-Abliterated-Caption-it.mmproj-f16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-3B-Abliterated-Caption-it_Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-3B-Abliterated-Caption-it_Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-3B-Abliterated-Caption-it_Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-3B-Abliterated-Caption-it_Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-3B-Abliterated-Caption-it_Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-VL-3B-Abliterated-Caption-it_Q8_0.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2.5-VL-3B-Abliterated-Caption-it.f16.gguf b/Qwen2.5-VL-3B-Abliterated-Caption-it.f16.gguf new file mode 100644 index 0000000..f6cefa9 --- /dev/null +++ b/Qwen2.5-VL-3B-Abliterated-Caption-it.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97ac20a6196b233a1aa3ba945096bd6a006e01f151c5c6a6f7d218ce2130509f +size 6178316288 diff --git a/Qwen2.5-VL-3B-Abliterated-Caption-it.mmproj-f16.gguf b/Qwen2.5-VL-3B-Abliterated-Caption-it.mmproj-f16.gguf new file mode 100644 index 0000000..46e6702 --- /dev/null +++ b/Qwen2.5-VL-3B-Abliterated-Caption-it.mmproj-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e29a914431ac3a9491968511453eeca6ace0c97f14d81d2252effe5e140d75cc +size 1338428672 diff --git a/Qwen2.5-VL-3B-Abliterated-Caption-it_Q2_K.gguf b/Qwen2.5-VL-3B-Abliterated-Caption-it_Q2_K.gguf new file mode 100644 index 0000000..5f3bcdc --- /dev/null +++ b/Qwen2.5-VL-3B-Abliterated-Caption-it_Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0c5bec46e47efda03c827c6ca534f5917e785e411a814ff55ece735601b2741 +size 1274755072 diff --git a/Qwen2.5-VL-3B-Abliterated-Caption-it_Q3_K_M.gguf b/Qwen2.5-VL-3B-Abliterated-Caption-it_Q3_K_M.gguf new file mode 100644 index 0000000..7d73e1d --- /dev/null +++ b/Qwen2.5-VL-3B-Abliterated-Caption-it_Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cee9fd975ff0cc02631ab3d858fa50c0e3248741326390b941693727df1012f6 +size 1590474752 diff --git a/Qwen2.5-VL-3B-Abliterated-Caption-it_Q4_K_M.gguf b/Qwen2.5-VL-3B-Abliterated-Caption-it_Q4_K_M.gguf new file mode 100644 index 0000000..c332625 --- /dev/null +++ b/Qwen2.5-VL-3B-Abliterated-Caption-it_Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9005f43a8b0d5188de2f5de3baf3ed3e4f21a7df17ce634666928710211454f4 +size 1929902080 diff --git a/Qwen2.5-VL-3B-Abliterated-Caption-it_Q5_K_M.gguf b/Qwen2.5-VL-3B-Abliterated-Caption-it_Q5_K_M.gguf new file mode 100644 index 0000000..0d7bb48 --- /dev/null +++ b/Qwen2.5-VL-3B-Abliterated-Caption-it_Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2cc3ee8e17ad6bc1062009621d6848d3d2bcdf6b231bd25aec300cbe9cc7589e +size 2224814080 diff --git a/Qwen2.5-VL-3B-Abliterated-Caption-it_Q6_K.gguf b/Qwen2.5-VL-3B-Abliterated-Caption-it_Q6_K.gguf new file mode 100644 index 0000000..05e4d94 --- /dev/null +++ b/Qwen2.5-VL-3B-Abliterated-Caption-it_Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:052c7afeb221a76a018f5f9751463356fb6cac80780fd777816750f202c8ad98 +size 2538158080 diff --git a/Qwen2.5-VL-3B-Abliterated-Caption-it_Q8_0.gguf b/Qwen2.5-VL-3B-Abliterated-Caption-it_Q8_0.gguf new file mode 100644 index 0000000..6feea27 --- /dev/null +++ b/Qwen2.5-VL-3B-Abliterated-Caption-it_Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:118f173879f7cdf24d5cffd943eb703f1b3141affc93a4703269a35cee155779 +size 3285475328 diff --git a/README.md b/README.md new file mode 100644 index 0000000..017fe20 --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +license: apache-2.0 +language: +- en +- zh +base_model: +- Qwen/Qwen2.5-VL-7B-Instruct +tags: +- Image-to-text +- text-generation +- conversational +- uncensored +--- + +### Qwen2.5-VL-7B-Abliterated-Caption-it_GGUF(Vision Language) + +This repository hosts Qwen2.5-VL-Abliterated-Caption-GGUF, a quantized Vision-Language (Uncensored) model optimized for image understanding and caption generation with relaxed alignment constraints. The model is designed for local inference, experimentation, and research-oriented multimodal workflows. + +It targets users who want direct, descriptive visual reasoning without heavy content moderation layers, packaged in a GGUF format for efficient CPU and edge-device deployment. + +### Model Summary + +- **Model Identifier**: Qwen2.5-VL-Abliterated-Caption-GGUF +- **Base Model**: Qwen2.5-VL (Vision-Language) +- **Architecture**: Transformer-based multimodal model (text + vision) +- **Original model**: prithivMLmods/Qwen2.5-VL-Abliterated-Caption-GGUF +- **Primary Function**: Image captioning and visual-text understanding + +###Purpose & Design Goals + +This variant prioritizes expressive visual descriptions and caption accuracy while minimizing restrictive alignment behaviors. The “abliterated” aspect indicates reduced policy-driven refusals, making the model more suitable for: +- Dataset generation +- Visual analysis research +- Creative or descriptive captioning tasks +- Offline or private multimodal pipelines + +### Multimodal Interaction Format + +The model follows a standard multimodal prompt structure compatible with Qwen-VL style templates. A typical interaction may include system context, a user query, and an image reference: +``` +<|system|> +You are a visual captioning assistant. +<|user|> +Describe the image in detail. +<|vision_input|> + +<|assistant|> +``` + +### Core Capabilities + +- Detailed and literal image captioning +- Multimodal reasoning over visual scenes +- Object, action, and context recognition +- Long-form descriptive outputs +- Reduced refusal behavior compared to safety-aligned VL models +- Optimized for local inference via GGUF + +### Recommended Use Cases + +- **Image caption generation** – datasets, tagging, annotation +- **Visual analysis** – scene breakdowns, object relationships +- **Creative workflows** – storytelling from images +- **Research & evaluation** – alignment and multimodal behavior testing +- **Offline deployments** – no cloud or API dependency + + +### Credits & Acknowledgements + +- Qwen team for the base Qwen2.5-VL architecture +- GGUF tooling and local inference ecosystem contributors +- Open-source multimodal research community \ No newline at end of file