commit 566fd9bc20e46da8bbb04f1efe8cbab79a23aedd Author: ModelHub XC Date: Wed May 6 11:16:48 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: USS-Inferprise/Phi4-Mini-Prose2Tags-4B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..b4da1fa --- /dev/null +++ b/.gitattributes @@ -0,0 +1,46 @@ +*.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 +Phi4-Mini-Prose2Tags-4B-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Phi4-Mini-Prose2Tags-4B-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Phi4-Mini-Prose2Tags-4B-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Phi4-Mini-Prose2Tags-4B-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Phi4-Mini-Prose2Tags-4B-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Phi4-Mini-Prose2Tags-4B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Phi4-Mini-Prose2Tags-4B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Phi4-Mini-Prose2Tags-4B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Phi4-Mini-Prose2Tags-4B-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Phi4-Mini-Prose2Tags-4B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Phi4-Mini-Prose2Tags-4B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/ComfyUI-prose2tags.tar b/ComfyUI-prose2tags.tar new file mode 100644 index 0000000..a165325 --- /dev/null +++ b/ComfyUI-prose2tags.tar @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d45cdbac2da55c41a953a95d908aedd5f7679884c808a10c0197166b7864a478 +size 6144 diff --git a/Phi4-Mini-Prose2Tags-4B-Q2_K.gguf b/Phi4-Mini-Prose2Tags-4B-Q2_K.gguf new file mode 100644 index 0000000..264d1f3 --- /dev/null +++ b/Phi4-Mini-Prose2Tags-4B-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a2aeef530f729ca5078b67c5d8d75d8b3d9a5130d13a515104e99ec9c402fff +size 1733752992 diff --git a/Phi4-Mini-Prose2Tags-4B-Q3_K_L.gguf b/Phi4-Mini-Prose2Tags-4B-Q3_K_L.gguf new file mode 100644 index 0000000..4e31c03 --- /dev/null +++ b/Phi4-Mini-Prose2Tags-4B-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:172eabd4d59ed52106aeb2b0b3fcad758c30982db6b0cc85445e69fc7c37c9f0 +size 2312566944 diff --git a/Phi4-Mini-Prose2Tags-4B-Q3_K_M.gguf b/Phi4-Mini-Prose2Tags-4B-Q3_K_M.gguf new file mode 100644 index 0000000..d99223a --- /dev/null +++ b/Phi4-Mini-Prose2Tags-4B-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70f2e224672bafc281a07caf08b759635ee7c9d3f78036b04015c90c28155a66 +size 2121463968 diff --git a/Phi4-Mini-Prose2Tags-4B-Q3_K_S.gguf b/Phi4-Mini-Prose2Tags-4B-Q3_K_S.gguf new file mode 100644 index 0000000..1f8279a --- /dev/null +++ b/Phi4-Mini-Prose2Tags-4B-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26866beeb6f1ddfacc7f1f13c35f1f049e6a57b980155d90c1318f16f8e6e826 +size 1897330848 diff --git a/Phi4-Mini-Prose2Tags-4B-Q4_1.gguf b/Phi4-Mini-Prose2Tags-4B-Q4_1.gguf new file mode 100644 index 0000000..f6b620a --- /dev/null +++ b/Phi4-Mini-Prose2Tags-4B-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6736b726c00b161ad2323ef475557c14d7e04320ca1549918765bb40efc2ebe4 +size 2526476448 diff --git a/Phi4-Mini-Prose2Tags-4B-Q4_K_M.gguf b/Phi4-Mini-Prose2Tags-4B-Q4_K_M.gguf new file mode 100644 index 0000000..4d9f892 --- /dev/null +++ b/Phi4-Mini-Prose2Tags-4B-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82d76e72b62868410fd9d240746760cdf007226698df0f968e162f6e6085ecc2 +size 2493839520 diff --git a/Phi4-Mini-Prose2Tags-4B-Q4_K_S.gguf b/Phi4-Mini-Prose2Tags-4B-Q4_K_S.gguf new file mode 100644 index 0000000..387ef17 --- /dev/null +++ b/Phi4-Mini-Prose2Tags-4B-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83f085c1462fc2741b8c8ca55f214ad96b563ef634f07853dd18689f02e87f64 +size 2345597088 diff --git a/Phi4-Mini-Prose2Tags-4B-Q5_K_M.gguf b/Phi4-Mini-Prose2Tags-4B-Q5_K_M.gguf new file mode 100644 index 0000000..47f525e --- /dev/null +++ b/Phi4-Mini-Prose2Tags-4B-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa12c5bca4c997cc5e60fbaf8d8358500b0a53e7b77776b509e84f108ef75d3f +size 2814703776 diff --git a/Phi4-Mini-Prose2Tags-4B-Q5_K_S.gguf b/Phi4-Mini-Prose2Tags-4B-Q5_K_S.gguf new file mode 100644 index 0000000..620eb52 --- /dev/null +++ b/Phi4-Mini-Prose2Tags-4B-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:614a3055136ea959375fcae3008b78f96ae4993959debcbb0e38231d693b9910 +size 2727803040 diff --git a/Phi4-Mini-Prose2Tags-4B-Q6_K.gguf b/Phi4-Mini-Prose2Tags-4B-Q6_K.gguf new file mode 100644 index 0000000..2af7b44 --- /dev/null +++ b/Phi4-Mini-Prose2Tags-4B-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:728a8478eaab7eadf8539bb4331e7b43eaa39e6441ed94344c7a50227c69ae36 +size 3155622048 diff --git a/Phi4-Mini-Prose2Tags-4B-Q8_0.gguf b/Phi4-Mini-Prose2Tags-4B-Q8_0.gguf new file mode 100644 index 0000000..e6283a2 --- /dev/null +++ b/Phi4-Mini-Prose2Tags-4B-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad4cf8aafd4b987082abe97775f77b61a2b43c4ed9f9ef46273d2411db101167 +size 4084610208 diff --git a/README.md b/README.md new file mode 100644 index 0000000..56e4116 --- /dev/null +++ b/README.md @@ -0,0 +1,70 @@ +--- +library_name: gguf +tags: +- phi-4 +- danbooru +- art-tagger +- quantized +- text-generation +base_model: +- USS-Inferprise/Phi4-Mini-Prose2Tags-4B +license: mit +pipeline_tag: text-generation +--- +Quants of (https://huggingface.co/USS-Inferprise/Phi4-Mini-Prose2Tags-4B) + +quantized_by: USS-Inferprise + +# We also include a concept for a ComfyUI custom node for applying this model in a workflow. + +Original Model Card Follows: + +# Phi4-Mini-Prose2Tags-4B + +This model is a specialized fine-tune designed to translate natural language prose descriptions into structured **Danbooru-style tags**. It is intended to bridge the gap between human-readable image captions and the tag-based prompting systems used by many latent diffusion models. + +## Model Details + +- **Developed by:** USS-Inferprise +- **Model Name:** Phi4-Mini-Prose2Tags-4B +- **Base Model:** [huihui-ai/Phi-4-mini-instruct-abliterated](https://huggingface.co/huihui-ai/Phi-4-mini-instruct-abliterated) +- **Training Architecture:** LoRA (Low-Rank Adaptation) +- **Merging Method:** Linear Merge (via Mergekit) +- **Primary Task:** Prose-to-Tag Translation + +## Training Methodology + +### Dataset Construction +The training data ([USS-Inferprise/Phi4-Mini-Prose2Tags-4B-Raw-Training-Data](https://huggingface.co/datasets/USS-Inferprise/Phi4-Mini-Prose2Tags-4B-Raw-Training-Data)) was generated using a synthetic pipeline: +1. **Source Images:** 100,000 images sourced from `laion/conceptual-captions-12m-webdataset`. +2. **Prose Generation:** Images were described using **QwenVL**. +3. **Tag Generation:** Images were tagged using **WD 1.3**. +4. **Pairing:** The resulting QwenVL descriptions and WD 1.3 tags were paired to create the final training instruction set. + +## ⚠️ Safety & Content Note + +> [!IMPORTANT] +> This model was trained exclusively on a curated subset of data intended for general audiences. **No explicit, NSFW, or adult-oriented tags** were included in the training dataset (`Prose2Tags-4B-Raw-Training-Data`). +> +> While the base model (`Phi-4-mini-instruct-abliterated`) has been modified to reduce certain refusals, this specific fine-tune is designed for clean, descriptive tagging. It may not recognize or accurately generate tags related to explicit content. If it can... it didn't learn it from us. + +### Training Process +- **Library:** [Unsloth](https://github.com/unslothai/unsloth) +- **Hardware:** NVIDIA L40S +- **Epochs:** 1 +- **Method:** LoRA fine-tuning merged into the base model using a Linear merge strategy. + +## Evaluation & Testing +Testing was performed on 100 images excluded from the training set. To ensure the model generalizes well across different captioning styles, the test inputs used **gokaygokay/Florence-2-SD3-Captioner** instead of the training-source QwenVL. + +Detailed test outputs can be found here: [USS-Inferprise/Phi4-Mini-P2T-4B-Testing](https://huggingface.co/datasets/USS-Inferprise/Phi4-Mini-P2T-4B-Testing). + +## Proper Prompt Format + +**Warning:** You must strictly follow the prompt format below. Failure to do so may result in the model reverting to the standard Phi-4-Mini helpful persona rather than generating tags. + +```text +<|user|> +You are a Danbooru tag translator. +{prose_input}<|end|> +<|assistant|> \ No newline at end of file