commit f5d1c41e983df3f26d7f2540bebeccbe909e4a48 Author: ModelHub XC Date: Wed Apr 29 04:03:05 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/MINT-empathy-Qwen3-4B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..1216e36 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,47 @@ +*.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 +MINT-empathy-Qwen3-4B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +MINT-empathy-Qwen3-4B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +MINT-empathy-Qwen3-4B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +MINT-empathy-Qwen3-4B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MINT-empathy-Qwen3-4B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MINT-empathy-Qwen3-4B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MINT-empathy-Qwen3-4B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MINT-empathy-Qwen3-4B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MINT-empathy-Qwen3-4B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MINT-empathy-Qwen3-4B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +MINT-empathy-Qwen3-4B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +MINT-empathy-Qwen3-4B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/MINT-empathy-Qwen3-4B.IQ4_XS.gguf b/MINT-empathy-Qwen3-4B.IQ4_XS.gguf new file mode 100644 index 0000000..40f2167 --- /dev/null +++ b/MINT-empathy-Qwen3-4B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:800c5e45da8ffd0c63a91e7e368286bc2d8f4233cf84a44a1ab6282b85eb16c2 +size 2492949824 diff --git a/MINT-empathy-Qwen3-4B.Q2_K.gguf b/MINT-empathy-Qwen3-4B.Q2_K.gguf new file mode 100644 index 0000000..7b3e777 --- /dev/null +++ b/MINT-empathy-Qwen3-4B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:166782fe225b6660df101a703fd890ce8f1f6e9cc0ad6172b697223b7781bd88 +size 1797126464 diff --git a/MINT-empathy-Qwen3-4B.Q3_K_L.gguf b/MINT-empathy-Qwen3-4B.Q3_K_L.gguf new file mode 100644 index 0000000..dc9c2a7 --- /dev/null +++ b/MINT-empathy-Qwen3-4B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:859a6b6c6ceb480d66cfb086d5f66eecd58099eb764eadc3801e5cf99ccfcf61 +size 2406915904 diff --git a/MINT-empathy-Qwen3-4B.Q3_K_M.gguf b/MINT-empathy-Qwen3-4B.Q3_K_M.gguf new file mode 100644 index 0000000..fb5e8de --- /dev/null +++ b/MINT-empathy-Qwen3-4B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77f418c8c969aec7806a708bb6ad2a4237238d1ed91b15622b07b258591707ca +size 2242748224 diff --git a/MINT-empathy-Qwen3-4B.Q3_K_S.gguf b/MINT-empathy-Qwen3-4B.Q3_K_S.gguf new file mode 100644 index 0000000..780c987 --- /dev/null +++ b/MINT-empathy-Qwen3-4B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4470987d2c3442fbd94d1aa78c998b88de89e24a23b01172c439177632c79a1d +size 2054127424 diff --git a/MINT-empathy-Qwen3-4B.Q4_K_M.gguf b/MINT-empathy-Qwen3-4B.Q4_K_M.gguf new file mode 100644 index 0000000..2829c03 --- /dev/null +++ b/MINT-empathy-Qwen3-4B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:231d3c5f84ee9cc813c5bf0ba32eb83b349a214b5d562ec0a7c03e9b8312393d +size 2716069184 diff --git a/MINT-empathy-Qwen3-4B.Q4_K_S.gguf b/MINT-empathy-Qwen3-4B.Q4_K_S.gguf new file mode 100644 index 0000000..6774edc --- /dev/null +++ b/MINT-empathy-Qwen3-4B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f76ba29cda3b8fb9f41268ce1ffbae090d20e338e74fce412e7dcce27e00ebe +size 2602097984 diff --git a/MINT-empathy-Qwen3-4B.Q5_K_M.gguf b/MINT-empathy-Qwen3-4B.Q5_K_M.gguf new file mode 100644 index 0000000..a85b713 --- /dev/null +++ b/MINT-empathy-Qwen3-4B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8d76df3102b40d2ff6a6bf80e351f1804a1624eae72133c569e3ecd0bac0206 +size 3156921664 diff --git a/MINT-empathy-Qwen3-4B.Q5_K_S.gguf b/MINT-empathy-Qwen3-4B.Q5_K_S.gguf new file mode 100644 index 0000000..f661176 --- /dev/null +++ b/MINT-empathy-Qwen3-4B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39106a1cecdd88ae014ee91f2d32f0bb83bbfae58619add84823ac1a40217eaf +size 3091119424 diff --git a/MINT-empathy-Qwen3-4B.Q6_K.gguf b/MINT-empathy-Qwen3-4B.Q6_K.gguf new file mode 100644 index 0000000..3d6f1cc --- /dev/null +++ b/MINT-empathy-Qwen3-4B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12fd25b38e55b90e5bf7418b285d824259dc98ff29cde300e38229b7796d4344 +size 3625327424 diff --git a/MINT-empathy-Qwen3-4B.Q8_0.gguf b/MINT-empathy-Qwen3-4B.Q8_0.gguf new file mode 100644 index 0000000..9586e6e --- /dev/null +++ b/MINT-empathy-Qwen3-4B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c28be989a9e9605fbc4b6bcea59acd7a7f4df3352f6559526809ace1d81435bb +size 4693671744 diff --git a/MINT-empathy-Qwen3-4B.f16.gguf b/MINT-empathy-Qwen3-4B.f16.gguf new file mode 100644 index 0000000..d63fdbd --- /dev/null +++ b/MINT-empathy-Qwen3-4B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e944bd943267491dd2b71f1ce5bf3f2bed5c98561db57f7826d133495c6e5a34 +size 8829198144 diff --git a/README.md b/README.md new file mode 100644 index 0000000..bdf64ec --- /dev/null +++ b/README.md @@ -0,0 +1,79 @@ +--- +base_model: hongli-zhan/MINT-empathy-Qwen3-4B +language: +- en +library_name: transformers +license: mit +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- empathy +- reinforcement-learning +- grpo +- dialogue +- mint +- emotional-support +--- +## About + + + + + + + + + +static quants of https://huggingface.co/hongli-zhan/MINT-empathy-Qwen3-4B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#MINT-empathy-Qwen3-4B-GGUF).*** + +weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. +## Usage + +If you are unsure how to use GGUF files, refer to one of [TheBloke's +READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for +more details, including on how to concatenate multi-part files. + +## Provided Quants + +(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) + +| Link | Type | Size/GB | Notes | +|:-----|:-----|--------:|:------| +| [GGUF](https://huggingface.co/mradermacher/MINT-empathy-Qwen3-4B-GGUF/resolve/main/MINT-empathy-Qwen3-4B.Q2_K.gguf) | Q2_K | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/MINT-empathy-Qwen3-4B-GGUF/resolve/main/MINT-empathy-Qwen3-4B.Q3_K_S.gguf) | Q3_K_S | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/MINT-empathy-Qwen3-4B-GGUF/resolve/main/MINT-empathy-Qwen3-4B.Q3_K_M.gguf) | Q3_K_M | 2.3 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/MINT-empathy-Qwen3-4B-GGUF/resolve/main/MINT-empathy-Qwen3-4B.Q3_K_L.gguf) | Q3_K_L | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/MINT-empathy-Qwen3-4B-GGUF/resolve/main/MINT-empathy-Qwen3-4B.IQ4_XS.gguf) | IQ4_XS | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/MINT-empathy-Qwen3-4B-GGUF/resolve/main/MINT-empathy-Qwen3-4B.Q4_K_S.gguf) | Q4_K_S | 2.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MINT-empathy-Qwen3-4B-GGUF/resolve/main/MINT-empathy-Qwen3-4B.Q4_K_M.gguf) | Q4_K_M | 2.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MINT-empathy-Qwen3-4B-GGUF/resolve/main/MINT-empathy-Qwen3-4B.Q5_K_S.gguf) | Q5_K_S | 3.2 | | +| [GGUF](https://huggingface.co/mradermacher/MINT-empathy-Qwen3-4B-GGUF/resolve/main/MINT-empathy-Qwen3-4B.Q5_K_M.gguf) | Q5_K_M | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/MINT-empathy-Qwen3-4B-GGUF/resolve/main/MINT-empathy-Qwen3-4B.Q6_K.gguf) | Q6_K | 3.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/MINT-empathy-Qwen3-4B-GGUF/resolve/main/MINT-empathy-Qwen3-4B.Q8_0.gguf) | Q8_0 | 4.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/MINT-empathy-Qwen3-4B-GGUF/resolve/main/MINT-empathy-Qwen3-4B.f16.gguf) | f16 | 8.9 | 16 bpw, overkill | + +Here is a handy graph by ikawrakow comparing some lower-quality quant +types (lower is better): + +![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) + +And here are Artefact2's thoughts on the matter: +https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 + +## FAQ / Model Request + +See https://huggingface.co/mradermacher/model_requests for some answers to +questions you might have and/or if you want some other model quantized. + +## Thanks + +I thank my company, [nethype GmbH](https://www.nethype.de/), for letting +me use its servers and providing upgrades to my workstation to enable +this work in my free time. + +