commit 2daacdcc26d0dd7b6978d267cb2ed6f9bbacfe04 Author: ModelHub XC Date: Fri May 22 09:04:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/BehChat-v2.1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..9474dc7 --- /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-v2.1.f16.gguf filter=lfs diff=lfs merge=lfs -text +BehChat-v2.1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +BehChat-v2.1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +BehChat-v2.1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +BehChat-v2.1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +BehChat-v2.1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +BehChat-v2.1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +BehChat-v2.1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +BehChat-v2.1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +BehChat-v2.1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +BehChat-v2.1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +BehChat-v2.1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/BehChat-v2.1.IQ4_XS.gguf b/BehChat-v2.1.IQ4_XS.gguf new file mode 100644 index 0000000..2adeb01 --- /dev/null +++ b/BehChat-v2.1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e73617c4bfcca4d98ee4cc8b34a6bda9b5eed480584fc12e344b4c6cc88e99ee +size 4593296384 diff --git a/BehChat-v2.1.Q2_K.gguf b/BehChat-v2.1.Q2_K.gguf new file mode 100644 index 0000000..dad0aa6 --- /dev/null +++ b/BehChat-v2.1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b51336afbfdccc580588e9cd3a467861262eef1884f859247487107da286bf4 +size 3281732608 diff --git a/BehChat-v2.1.Q3_K_L.gguf b/BehChat-v2.1.Q3_K_L.gguf new file mode 100644 index 0000000..0c924e2 --- /dev/null +++ b/BehChat-v2.1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6870f340268f87d82254ca3247cee8a7988ecba5101ffc2e82526d3d1f9eef6 +size 4431393792 diff --git a/BehChat-v2.1.Q3_K_M.gguf b/BehChat-v2.1.Q3_K_M.gguf new file mode 100644 index 0000000..efde70f --- /dev/null +++ b/BehChat-v2.1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce432bae4af056baec0bb50a19a9550b9068f44c68f1d31d8dde057bea6f0b94 +size 4124161024 diff --git a/BehChat-v2.1.Q3_K_S.gguf b/BehChat-v2.1.Q3_K_S.gguf new file mode 100644 index 0000000..498d023 --- /dev/null +++ b/BehChat-v2.1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f6ded8bb989fff454db5327b3e6cdbeee2ce33417cb23ed6a683759b6aaef99 +size 3769611264 diff --git a/BehChat-v2.1.Q4_K_M.gguf b/BehChat-v2.1.Q4_K_M.gguf new file mode 100644 index 0000000..75b90e3 --- /dev/null +++ b/BehChat-v2.1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6dc0a9b9b55434faf857eba22ecaa0e1606d62bc803c6d32c8d94dcc789de2b +size 5027783680 diff --git a/BehChat-v2.1.Q4_K_S.gguf b/BehChat-v2.1.Q4_K_S.gguf new file mode 100644 index 0000000..9f9e4e1 --- /dev/null +++ b/BehChat-v2.1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6416eb7c4bced26e702532648fbabf0b151a0955772b9d05daf88535d1b1b41 +size 4802012160 diff --git a/BehChat-v2.1.Q5_K_M.gguf b/BehChat-v2.1.Q5_K_M.gguf new file mode 100644 index 0000000..3f8f161 --- /dev/null +++ b/BehChat-v2.1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b389c2f6ba94c532b5bc857e10343eebc9575e25bb1a1e8242088a57c03b45a8 +size 5851112448 diff --git a/BehChat-v2.1.Q5_K_S.gguf b/BehChat-v2.1.Q5_K_S.gguf new file mode 100644 index 0000000..c181f9a --- /dev/null +++ b/BehChat-v2.1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7128dca18a99c86e56624a6ce8ddfc190c2a37ccd7eb6b5e4265b54ec7e714a3 +size 5720761344 diff --git a/BehChat-v2.1.Q6_K.gguf b/BehChat-v2.1.Q6_K.gguf new file mode 100644 index 0000000..ae499e2 --- /dev/null +++ b/BehChat-v2.1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1bd97d9bb8d54cd17f5b82bdd00b70afe8f0f0c5a737cde75ec8f2824d89a3b +size 6725899264 diff --git a/BehChat-v2.1.Q8_0.gguf b/BehChat-v2.1.Q8_0.gguf new file mode 100644 index 0000000..5f0a234 --- /dev/null +++ b/BehChat-v2.1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b4c18d96e74ddc70f00c772bb5585d329493158fc59d4117c28b691d478335b +size 8709518336 diff --git a/BehChat-v2.1.f16.gguf b/BehChat-v2.1.f16.gguf new file mode 100644 index 0000000..30a6266 --- /dev/null +++ b/BehChat-v2.1.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13606cf3cfa8a80b8c79962a1faa3bb2f58f2986edba90bddb75673941024804 +size 16388043776 diff --git a/README.md b/README.md new file mode 100644 index 0000000..308d8bf --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +base_model: zypchn/BehChat-v2.1 +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-v2.1 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#BehChat-v2.1-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-v2.1-GGUF/resolve/main/BehChat-v2.1.Q2_K.gguf) | Q2_K | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/BehChat-v2.1-GGUF/resolve/main/BehChat-v2.1.Q3_K_S.gguf) | Q3_K_S | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/BehChat-v2.1-GGUF/resolve/main/BehChat-v2.1.Q3_K_M.gguf) | Q3_K_M | 4.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/BehChat-v2.1-GGUF/resolve/main/BehChat-v2.1.Q3_K_L.gguf) | Q3_K_L | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/BehChat-v2.1-GGUF/resolve/main/BehChat-v2.1.IQ4_XS.gguf) | IQ4_XS | 4.7 | | +| [GGUF](https://huggingface.co/mradermacher/BehChat-v2.1-GGUF/resolve/main/BehChat-v2.1.Q4_K_S.gguf) | Q4_K_S | 4.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/BehChat-v2.1-GGUF/resolve/main/BehChat-v2.1.Q4_K_M.gguf) | Q4_K_M | 5.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/BehChat-v2.1-GGUF/resolve/main/BehChat-v2.1.Q5_K_S.gguf) | Q5_K_S | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/BehChat-v2.1-GGUF/resolve/main/BehChat-v2.1.Q5_K_M.gguf) | Q5_K_M | 6.0 | | +| [GGUF](https://huggingface.co/mradermacher/BehChat-v2.1-GGUF/resolve/main/BehChat-v2.1.Q6_K.gguf) | Q6_K | 6.8 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/BehChat-v2.1-GGUF/resolve/main/BehChat-v2.1.Q8_0.gguf) | Q8_0 | 8.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/BehChat-v2.1-GGUF/resolve/main/BehChat-v2.1.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. + +