commit 58e204a604569947ea3af21b62b8e1d1d69f7f5f Author: ModelHub XC Date: Mon Apr 13 19:46:05 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/L3.1-Boshima-b-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..5d6a8ca --- /dev/null +++ b/.gitattributes @@ -0,0 +1,50 @@ +*.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 +L3.1-Boshima-b.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Boshima-b.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Boshima-b.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Boshima-b.f16.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Boshima-b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Boshima-b.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Boshima-b.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Boshima-b.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Boshima-b.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Boshima-b.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Boshima-b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Boshima-b.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Boshima-b.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Boshima-b.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Boshima-b.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/L3.1-Boshima-b.IQ3_M.gguf b/L3.1-Boshima-b.IQ3_M.gguf new file mode 100644 index 0000000..b179199 --- /dev/null +++ b/L3.1-Boshima-b.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd1d64644c51c4307ba39902db9dd01b5fff805abe06dcb334cbb916ec96e048 +size 3784824672 diff --git a/L3.1-Boshima-b.IQ3_S.gguf b/L3.1-Boshima-b.IQ3_S.gguf new file mode 100644 index 0000000..8d924c5 --- /dev/null +++ b/L3.1-Boshima-b.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:298c3f670a61d192b7092fc61e785855443498b8448c03a878b45b3b423703b6 +size 3682326368 diff --git a/L3.1-Boshima-b.IQ3_XS.gguf b/L3.1-Boshima-b.IQ3_XS.gguf new file mode 100644 index 0000000..10c7443 --- /dev/null +++ b/L3.1-Boshima-b.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19f2669a4e1e6944b8c0c6dd7d0d4660b4e62847ceedb9dc355325b0064543b9 +size 3518748512 diff --git a/L3.1-Boshima-b.IQ4_XS.gguf b/L3.1-Boshima-b.IQ4_XS.gguf new file mode 100644 index 0000000..2687bca --- /dev/null +++ b/L3.1-Boshima-b.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb56f19c2c27cfb2b332ccafb05bcce8174df45f0dfa39dd2c8a0b08605dd27e +size 4484364128 diff --git a/L3.1-Boshima-b.Q2_K.gguf b/L3.1-Boshima-b.Q2_K.gguf new file mode 100644 index 0000000..634b768 --- /dev/null +++ b/L3.1-Boshima-b.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:539f728cc8372fa67ca6b7142a751c7b1c5186a57a763d53a6b6d54bbe35bc3e +size 3179132768 diff --git a/L3.1-Boshima-b.Q3_K_L.gguf b/L3.1-Boshima-b.Q3_K_L.gguf new file mode 100644 index 0000000..a7b7435 --- /dev/null +++ b/L3.1-Boshima-b.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c983de9cfee37aedb9f618ea41d4ea94c915c51c807255182c66e2fe48d127c +size 4321957728 diff --git a/L3.1-Boshima-b.Q3_K_M.gguf b/L3.1-Boshima-b.Q3_K_M.gguf new file mode 100644 index 0000000..3e3715e --- /dev/null +++ b/L3.1-Boshima-b.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1cd3415d3944e59f36b9a9a0b1fa14ecbdff7f7155c0a1affceffd3b205d036 +size 4018919264 diff --git a/L3.1-Boshima-b.Q3_K_S.gguf b/L3.1-Boshima-b.Q3_K_S.gguf new file mode 100644 index 0000000..37b60e1 --- /dev/null +++ b/L3.1-Boshima-b.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b3ed50a59b79a67fcea734f682931457c7faf6560f0c4a5a040cea2ced9f124 +size 3664500576 diff --git a/L3.1-Boshima-b.Q4_K_M.gguf b/L3.1-Boshima-b.Q4_K_M.gguf new file mode 100644 index 0000000..048fe44 --- /dev/null +++ b/L3.1-Boshima-b.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:def70a9c1021f908f2d599b48563bbd5eac89f7956a932f06c05d9805af20f93 +size 4920735584 diff --git a/L3.1-Boshima-b.Q4_K_S.gguf b/L3.1-Boshima-b.Q4_K_S.gguf new file mode 100644 index 0000000..815f27a --- /dev/null +++ b/L3.1-Boshima-b.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7af8b2fdc0184f191c690d542af1f97bb60a97de900b053352130142f7ee442 +size 4692670304 diff --git a/L3.1-Boshima-b.Q5_K_M.gguf b/L3.1-Boshima-b.Q5_K_M.gguf new file mode 100644 index 0000000..c0cb581 --- /dev/null +++ b/L3.1-Boshima-b.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e6c974fe756075833df2fd394f1586b69b79798e10bc2e14dc0384cb95d156a +size 5732988768 diff --git a/L3.1-Boshima-b.Q5_K_S.gguf b/L3.1-Boshima-b.Q5_K_S.gguf new file mode 100644 index 0000000..f8d23bc --- /dev/null +++ b/L3.1-Boshima-b.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e039db97f2d50638143017f767d9a666ea77311e3661b3bc8cde0e7dead8e6c2 +size 5599295328 diff --git a/L3.1-Boshima-b.Q6_K.gguf b/L3.1-Boshima-b.Q6_K.gguf new file mode 100644 index 0000000..cc7dac0 --- /dev/null +++ b/L3.1-Boshima-b.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:776238ebdcc358d13a77e866d604bd61221ac099361d71eb1b8d19ecf3e42752 +size 6596007776 diff --git a/L3.1-Boshima-b.Q8_0.gguf b/L3.1-Boshima-b.Q8_0.gguf new file mode 100644 index 0000000..d6b424f --- /dev/null +++ b/L3.1-Boshima-b.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77e12af83420c72da001f0eca6a1d574ad3b7137a4f38508f362e16d6c652f03 +size 8540772192 diff --git a/L3.1-Boshima-b.f16.gguf b/L3.1-Boshima-b.f16.gguf new file mode 100644 index 0000000..ee7a56a --- /dev/null +++ b/L3.1-Boshima-b.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef67b38d8ef460bccc32ce83cefd59844bfeba75bdc143ea89d32c90b7517d91 +size 16068892512 diff --git a/README.md b/README.md new file mode 100644 index 0000000..dd97291 --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: mergekit-community/L3.1-Boshima-b +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/mergekit-community/L3.1-Boshima-b + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/L3.1-Boshima-b-i1-GGUF +## 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/L3.1-Boshima-b-GGUF/resolve/main/L3.1-Boshima-b.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Boshima-b-GGUF/resolve/main/L3.1-Boshima-b.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Boshima-b-GGUF/resolve/main/L3.1-Boshima-b.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Boshima-b-GGUF/resolve/main/L3.1-Boshima-b.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Boshima-b-GGUF/resolve/main/L3.1-Boshima-b.IQ3_M.gguf) | IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Boshima-b-GGUF/resolve/main/L3.1-Boshima-b.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Boshima-b-GGUF/resolve/main/L3.1-Boshima-b.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Boshima-b-GGUF/resolve/main/L3.1-Boshima-b.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Boshima-b-GGUF/resolve/main/L3.1-Boshima-b.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Boshima-b-GGUF/resolve/main/L3.1-Boshima-b.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Boshima-b-GGUF/resolve/main/L3.1-Boshima-b.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Boshima-b-GGUF/resolve/main/L3.1-Boshima-b.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Boshima-b-GGUF/resolve/main/L3.1-Boshima-b.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Boshima-b-GGUF/resolve/main/L3.1-Boshima-b.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Boshima-b-GGUF/resolve/main/L3.1-Boshima-b.f16.gguf) | f16 | 16.2 | 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. + +