commit c37c494da2956b44269e200a38a7a7dfbae77213 Author: ModelHub XC Date: Sun Jun 14 18:52:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/q1b-limo_dsr32b-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..5b1fdb1 --- /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 +q1b-limo_dsr32b.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +q1b-limo_dsr32b.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +q1b-limo_dsr32b.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +q1b-limo_dsr32b.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +q1b-limo_dsr32b.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +q1b-limo_dsr32b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +q1b-limo_dsr32b.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +q1b-limo_dsr32b.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +q1b-limo_dsr32b.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +q1b-limo_dsr32b.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +q1b-limo_dsr32b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +q1b-limo_dsr32b.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..2fc2e92 --- /dev/null +++ b/README.md @@ -0,0 +1,76 @@ +--- +base_model: nlee-208/q1b-limo_dsr32b +language: +- en +library_name: transformers +model_name: q1b-limo_dsr32b +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- generated_from_trainer +- trl +- sft +--- +## About + + + + + + + + + +static quants of https://huggingface.co/nlee-208/q1b-limo_dsr32b + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#q1b-limo_dsr32b-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/q1b-limo_dsr32b-GGUF/resolve/main/q1b-limo_dsr32b.Q2_K.gguf) | Q2_K | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/q1b-limo_dsr32b-GGUF/resolve/main/q1b-limo_dsr32b.Q3_K_S.gguf) | Q3_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/q1b-limo_dsr32b-GGUF/resolve/main/q1b-limo_dsr32b.Q3_K_M.gguf) | Q3_K_M | 0.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/q1b-limo_dsr32b-GGUF/resolve/main/q1b-limo_dsr32b.Q3_K_L.gguf) | Q3_K_L | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/q1b-limo_dsr32b-GGUF/resolve/main/q1b-limo_dsr32b.IQ4_XS.gguf) | IQ4_XS | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/q1b-limo_dsr32b-GGUF/resolve/main/q1b-limo_dsr32b.Q4_K_S.gguf) | Q4_K_S | 1.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/q1b-limo_dsr32b-GGUF/resolve/main/q1b-limo_dsr32b.Q4_K_M.gguf) | Q4_K_M | 1.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/q1b-limo_dsr32b-GGUF/resolve/main/q1b-limo_dsr32b.Q5_K_S.gguf) | Q5_K_S | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/q1b-limo_dsr32b-GGUF/resolve/main/q1b-limo_dsr32b.Q5_K_M.gguf) | Q5_K_M | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/q1b-limo_dsr32b-GGUF/resolve/main/q1b-limo_dsr32b.Q6_K.gguf) | Q6_K | 1.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/q1b-limo_dsr32b-GGUF/resolve/main/q1b-limo_dsr32b.Q8_0.gguf) | Q8_0 | 1.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/q1b-limo_dsr32b-GGUF/resolve/main/q1b-limo_dsr32b.f16.gguf) | f16 | 3.2 | 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. + + diff --git a/q1b-limo_dsr32b.IQ4_XS.gguf b/q1b-limo_dsr32b.IQ4_XS.gguf new file mode 100644 index 0000000..f9afd9a --- /dev/null +++ b/q1b-limo_dsr32b.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55589f178efcee171fd62d7dd4a1cb16e4239cbd9eab7538cedcd80f61d076ec +size 902183072 diff --git a/q1b-limo_dsr32b.Q2_K.gguf b/q1b-limo_dsr32b.Q2_K.gguf new file mode 100644 index 0000000..0453184 --- /dev/null +++ b/q1b-limo_dsr32b.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c25282648e3f67ed5cb1142ce6e331f54d2b0a2ae3a351e062e60a07c7d454da +size 676305056 diff --git a/q1b-limo_dsr32b.Q3_K_L.gguf b/q1b-limo_dsr32b.Q3_K_L.gguf new file mode 100644 index 0000000..394ef6e --- /dev/null +++ b/q1b-limo_dsr32b.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:134e3959d0f8a837d3e65dd5e3fcb25b52de632fbe02431d545bb3d260ffd244 +size 880162976 diff --git a/q1b-limo_dsr32b.Q3_K_M.gguf b/q1b-limo_dsr32b.Q3_K_M.gguf new file mode 100644 index 0000000..bdef7cf --- /dev/null +++ b/q1b-limo_dsr32b.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:164f1a7ae8f466b82831350c24b61108250b44ebf756017ec7f8ad6b7a6420a2 +size 824178848 diff --git a/q1b-limo_dsr32b.Q3_K_S.gguf b/q1b-limo_dsr32b.Q3_K_S.gguf new file mode 100644 index 0000000..e638246 --- /dev/null +++ b/q1b-limo_dsr32b.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7aede25eda7dc1fa976fe4da3e072b1814a6cdd40fcdf33e36c0f3bf840cbf5f +size 760944800 diff --git a/q1b-limo_dsr32b.Q4_K_M.gguf b/q1b-limo_dsr32b.Q4_K_M.gguf new file mode 100644 index 0000000..83c58b2 --- /dev/null +++ b/q1b-limo_dsr32b.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b2e399a053ee2a3c09e7bfaa180d4fc355c11c7fad7387fe67f9e3920c54c63 +size 986048672 diff --git a/q1b-limo_dsr32b.Q4_K_S.gguf b/q1b-limo_dsr32b.Q4_K_S.gguf new file mode 100644 index 0000000..1b6772b --- /dev/null +++ b/q1b-limo_dsr32b.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7eccd7bb39eefe9f4d5d4f9c692545b5c362dec72149c8e10a99ffda542341c8 +size 940312736 diff --git a/q1b-limo_dsr32b.Q5_K_M.gguf b/q1b-limo_dsr32b.Q5_K_M.gguf new file mode 100644 index 0000000..56a47a5 --- /dev/null +++ b/q1b-limo_dsr32b.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8fdb5f854bd3e76c30d71791f74b2ff59da6b34d47c42449c320eb4ab87d2015 +size 1125050528 diff --git a/q1b-limo_dsr32b.Q5_K_S.gguf b/q1b-limo_dsr32b.Q5_K_S.gguf new file mode 100644 index 0000000..9311337 --- /dev/null +++ b/q1b-limo_dsr32b.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d2fb078bb717938ce7dde8a82088434011d6dd814511104491f9cbc7ae77c05 +size 1098729632 diff --git a/q1b-limo_dsr32b.Q6_K.gguf b/q1b-limo_dsr32b.Q6_K.gguf new file mode 100644 index 0000000..cc8dfe0 --- /dev/null +++ b/q1b-limo_dsr32b.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6bb7091f5f2a3ba1211fbabbf225050560f306d9c323a2a7fbce45451c7ed3b +size 1272740000 diff --git a/q1b-limo_dsr32b.Q8_0.gguf b/q1b-limo_dsr32b.Q8_0.gguf new file mode 100644 index 0000000..dc955f8 --- /dev/null +++ b/q1b-limo_dsr32b.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:714929ea9e39a1eaf2a44021a3a01e1b639fcbba48cfee96f0131ff0c0fcf83b +size 1646573216 diff --git a/q1b-limo_dsr32b.f16.gguf b/q1b-limo_dsr32b.f16.gguf new file mode 100644 index 0000000..28099da --- /dev/null +++ b/q1b-limo_dsr32b.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34f9064da6910cc4a70da642a0faff48585e875ae0f582b56d8f1858e3fd2d25 +size 3093669536