commit ac1ead3e73471449250eddc4d6020cb8268d5c6f Author: ModelHub XC Date: Thu Jun 25 05:54:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/BehChat-mini-v0.1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..c80aac3 --- /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 +BehChat-mini-v0.1.f16.gguf filter=lfs diff=lfs merge=lfs -text +BehChat-mini-v0.1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +BehChat-mini-v0.1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +BehChat-mini-v0.1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +BehChat-mini-v0.1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +BehChat-mini-v0.1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +BehChat-mini-v0.1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +BehChat-mini-v0.1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +BehChat-mini-v0.1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +BehChat-mini-v0.1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +BehChat-mini-v0.1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +BehChat-mini-v0.1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/BehChat-mini-v0.1.IQ4_XS.gguf b/BehChat-mini-v0.1.IQ4_XS.gguf new file mode 100644 index 0000000..a7212d2 --- /dev/null +++ b/BehChat-mini-v0.1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d14f65c53b075d3467d988df20407bc6df4bd08f865377bc4d005ca2969a26b5 +size 4593298528 diff --git a/BehChat-mini-v0.1.Q2_K.gguf b/BehChat-mini-v0.1.Q2_K.gguf new file mode 100644 index 0000000..c504d2a --- /dev/null +++ b/BehChat-mini-v0.1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3768361076dac31860c892a319bab240a2f99e37b077f88b59b21daeabeba37 +size 3281734752 diff --git a/BehChat-mini-v0.1.Q3_K_L.gguf b/BehChat-mini-v0.1.Q3_K_L.gguf new file mode 100644 index 0000000..605b12d --- /dev/null +++ b/BehChat-mini-v0.1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41c84b9d2ecfac21788d8277a9877c4996d9b3676e675f0e9aa7b88240185b64 +size 4431395936 diff --git a/BehChat-mini-v0.1.Q3_K_M.gguf b/BehChat-mini-v0.1.Q3_K_M.gguf new file mode 100644 index 0000000..f412070 --- /dev/null +++ b/BehChat-mini-v0.1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a99194c38b0fba87dedad08a899a74bc0eedfa489dd38c8d14f89bba6d4923db +size 4124163168 diff --git a/BehChat-mini-v0.1.Q3_K_S.gguf b/BehChat-mini-v0.1.Q3_K_S.gguf new file mode 100644 index 0000000..da2ce8b --- /dev/null +++ b/BehChat-mini-v0.1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7cd2e45b99f4f6f75a23d7be733b9aac21af76a12c20e6426970f27471fa4068 +size 3769613408 diff --git a/BehChat-mini-v0.1.Q4_K_M.gguf b/BehChat-mini-v0.1.Q4_K_M.gguf new file mode 100644 index 0000000..fc71e56 --- /dev/null +++ b/BehChat-mini-v0.1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1713c50b80f790475b8b7666785c77408aae68d22102c6db537b8fcdae44189 +size 5027785824 diff --git a/BehChat-mini-v0.1.Q4_K_S.gguf b/BehChat-mini-v0.1.Q4_K_S.gguf new file mode 100644 index 0000000..0957be2 --- /dev/null +++ b/BehChat-mini-v0.1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:35b60be7988336a54119ae1f64d41a9587ee17b67d884afe51052fcf10de81cb +size 4802014304 diff --git a/BehChat-mini-v0.1.Q5_K_M.gguf b/BehChat-mini-v0.1.Q5_K_M.gguf new file mode 100644 index 0000000..7b273b3 --- /dev/null +++ b/BehChat-mini-v0.1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5ef8d7db1154bdbe4a7af0ef6c22e2590fc767ff469adf40af04ca11bf751ee +size 5851114592 diff --git a/BehChat-mini-v0.1.Q5_K_S.gguf b/BehChat-mini-v0.1.Q5_K_S.gguf new file mode 100644 index 0000000..c7a5541 --- /dev/null +++ b/BehChat-mini-v0.1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67827ca7c249a4249932ff97ed1daab05dbae9ac078d55beb78b755a43bc75ad +size 5720763488 diff --git a/BehChat-mini-v0.1.Q6_K.gguf b/BehChat-mini-v0.1.Q6_K.gguf new file mode 100644 index 0000000..4d0fe04 --- /dev/null +++ b/BehChat-mini-v0.1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45e2df5e27d642c05018bf3215319a37a51a9044e8b1f4037d28cf33dda3182f +size 6725901408 diff --git a/BehChat-mini-v0.1.Q8_0.gguf b/BehChat-mini-v0.1.Q8_0.gguf new file mode 100644 index 0000000..524da55 --- /dev/null +++ b/BehChat-mini-v0.1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb6bec31680aa8a62e5ecd9f32ff10832ed3c68e089aa0c8b9ba754f9abffdb3 +size 8709520480 diff --git a/BehChat-mini-v0.1.f16.gguf b/BehChat-mini-v0.1.f16.gguf new file mode 100644 index 0000000..715aca5 --- /dev/null +++ b/BehChat-mini-v0.1.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85f589c481fe1b436a12776e902a6ea201fa58628a9f683ce96696e7cf7ccd83 +size 16388045920 diff --git a/README.md b/README.md new file mode 100644 index 0000000..1ab09ac --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +base_model: zypchn/BehChat-mini-v0.1 +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- qwen3 +--- +## About + + + + + + + + + +static quants of https://huggingface.co/zypchn/BehChat-mini-v0.1 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#BehChat-mini-v0.1-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/BehChat-mini-v0.1-GGUF/resolve/main/BehChat-mini-v0.1.Q2_K.gguf) | Q2_K | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/BehChat-mini-v0.1-GGUF/resolve/main/BehChat-mini-v0.1.Q3_K_S.gguf) | Q3_K_S | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/BehChat-mini-v0.1-GGUF/resolve/main/BehChat-mini-v0.1.Q3_K_M.gguf) | Q3_K_M | 4.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/BehChat-mini-v0.1-GGUF/resolve/main/BehChat-mini-v0.1.Q3_K_L.gguf) | Q3_K_L | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/BehChat-mini-v0.1-GGUF/resolve/main/BehChat-mini-v0.1.IQ4_XS.gguf) | IQ4_XS | 4.7 | | +| [GGUF](https://huggingface.co/mradermacher/BehChat-mini-v0.1-GGUF/resolve/main/BehChat-mini-v0.1.Q4_K_S.gguf) | Q4_K_S | 4.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/BehChat-mini-v0.1-GGUF/resolve/main/BehChat-mini-v0.1.Q4_K_M.gguf) | Q4_K_M | 5.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/BehChat-mini-v0.1-GGUF/resolve/main/BehChat-mini-v0.1.Q5_K_S.gguf) | Q5_K_S | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/BehChat-mini-v0.1-GGUF/resolve/main/BehChat-mini-v0.1.Q5_K_M.gguf) | Q5_K_M | 6.0 | | +| [GGUF](https://huggingface.co/mradermacher/BehChat-mini-v0.1-GGUF/resolve/main/BehChat-mini-v0.1.Q6_K.gguf) | Q6_K | 6.8 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/BehChat-mini-v0.1-GGUF/resolve/main/BehChat-mini-v0.1.Q8_0.gguf) | Q8_0 | 8.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/BehChat-mini-v0.1-GGUF/resolve/main/BehChat-mini-v0.1.f16.gguf) | f16 | 16.5 | 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. + +