commit b99b4f20345aeae592d2e5df6da6b635c36d3010 Author: ModelHub XC Date: Mon Jun 1 14:31:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Primus-Optima-QwenKV-1.54B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..41fe110 --- /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 +Primus-Optima-QwenKV-1.54B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Primus-Optima-QwenKV-1.54B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Primus-Optima-QwenKV-1.54B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Primus-Optima-QwenKV-1.54B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Primus-Optima-QwenKV-1.54B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Primus-Optima-QwenKV-1.54B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Primus-Optima-QwenKV-1.54B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Primus-Optima-QwenKV-1.54B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Primus-Optima-QwenKV-1.54B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Primus-Optima-QwenKV-1.54B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Primus-Optima-QwenKV-1.54B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Primus-Optima-QwenKV-1.54B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Primus-Optima-QwenKV-1.54B.IQ4_XS.gguf b/Primus-Optima-QwenKV-1.54B.IQ4_XS.gguf new file mode 100644 index 0000000..df36f77 --- /dev/null +++ b/Primus-Optima-QwenKV-1.54B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9764aad17e85d6a88f45143865d2390065c65fa1895c34ccedb34edf66888e56 +size 902183360 diff --git a/Primus-Optima-QwenKV-1.54B.Q2_K.gguf b/Primus-Optima-QwenKV-1.54B.Q2_K.gguf new file mode 100644 index 0000000..5e41539 --- /dev/null +++ b/Primus-Optima-QwenKV-1.54B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0df49423a3a5f435207456b486564a10ded963ef21b789ee54b9ae95d7eae04a +size 676305344 diff --git a/Primus-Optima-QwenKV-1.54B.Q3_K_L.gguf b/Primus-Optima-QwenKV-1.54B.Q3_K_L.gguf new file mode 100644 index 0000000..a54c086 --- /dev/null +++ b/Primus-Optima-QwenKV-1.54B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dadb6df2936feefc6b2cf7bb31ac9955f931f68d6220fe50cf557a6f50854ad4 +size 880163264 diff --git a/Primus-Optima-QwenKV-1.54B.Q3_K_M.gguf b/Primus-Optima-QwenKV-1.54B.Q3_K_M.gguf new file mode 100644 index 0000000..88777fb --- /dev/null +++ b/Primus-Optima-QwenKV-1.54B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1146845ac1a08d0ae7cccc8d34fccb0fa3ac6c3854f35f4567faef62d5cefde3 +size 824179136 diff --git a/Primus-Optima-QwenKV-1.54B.Q3_K_S.gguf b/Primus-Optima-QwenKV-1.54B.Q3_K_S.gguf new file mode 100644 index 0000000..519c388 --- /dev/null +++ b/Primus-Optima-QwenKV-1.54B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e21626e1c965edc2453ecc1d2c5327acb6dd47ca0b7a74bdfbbaefdba12bb979 +size 760945088 diff --git a/Primus-Optima-QwenKV-1.54B.Q4_K_M.gguf b/Primus-Optima-QwenKV-1.54B.Q4_K_M.gguf new file mode 100644 index 0000000..481d9b4 --- /dev/null +++ b/Primus-Optima-QwenKV-1.54B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cfae784fbfd2ebbf10215d6e3aa52e852e18fd9c67d096915b7f848726e4d42e +size 986048960 diff --git a/Primus-Optima-QwenKV-1.54B.Q4_K_S.gguf b/Primus-Optima-QwenKV-1.54B.Q4_K_S.gguf new file mode 100644 index 0000000..bbadc56 --- /dev/null +++ b/Primus-Optima-QwenKV-1.54B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:795eb4f02c29431b195c187e4a12088e642e5d4970783f1a6e1705051cb5ec7b +size 940313024 diff --git a/Primus-Optima-QwenKV-1.54B.Q5_K_M.gguf b/Primus-Optima-QwenKV-1.54B.Q5_K_M.gguf new file mode 100644 index 0000000..c280749 --- /dev/null +++ b/Primus-Optima-QwenKV-1.54B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:637ee8f7744f11faab060270e1ccaa9dd893933bdf6d5d59645f85011ff582a3 +size 1125050816 diff --git a/Primus-Optima-QwenKV-1.54B.Q5_K_S.gguf b/Primus-Optima-QwenKV-1.54B.Q5_K_S.gguf new file mode 100644 index 0000000..00bf8d9 --- /dev/null +++ b/Primus-Optima-QwenKV-1.54B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e636dc4c2c6cc4359ad1394ca6a93a9f401700d4d228752b4e6b18ad9c902ae2 +size 1098729920 diff --git a/Primus-Optima-QwenKV-1.54B.Q6_K.gguf b/Primus-Optima-QwenKV-1.54B.Q6_K.gguf new file mode 100644 index 0000000..99c4605 --- /dev/null +++ b/Primus-Optima-QwenKV-1.54B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:939b21dd3de60924154f1eecb0f8b9e1c055b43155a81f304d6b45b55846c4e5 +size 1272740288 diff --git a/Primus-Optima-QwenKV-1.54B.Q8_0.gguf b/Primus-Optima-QwenKV-1.54B.Q8_0.gguf new file mode 100644 index 0000000..eec2c31 --- /dev/null +++ b/Primus-Optima-QwenKV-1.54B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ecb74ce11459c630c560e623fe3cdfa14b3d4527379fa4cbaf3d5e6e9a53e63 +size 1646573504 diff --git a/Primus-Optima-QwenKV-1.54B.f16.gguf b/Primus-Optima-QwenKV-1.54B.f16.gguf new file mode 100644 index 0000000..747e1f5 --- /dev/null +++ b/Primus-Optima-QwenKV-1.54B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c8dcbe191bf7a0d3585e3d2a4871ed7ccda90a878e98edcf1faef08f271ead1 +size 3093669824 diff --git a/README.md b/README.md new file mode 100644 index 0000000..4e422ca --- /dev/null +++ b/README.md @@ -0,0 +1,76 @@ +--- +base_model: prithivMLmods/Primus-Optima-QwenKV-1.54B +language: +- en +- zh +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- Code +- Math +- RL +- R1 +--- +## About + + + + + + +static quants of https://huggingface.co/prithivMLmods/Primus-Optima-QwenKV-1.54B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Primus-Optima-QwenKV-1.54B-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/Primus-Optima-QwenKV-1.54B-GGUF/resolve/main/Primus-Optima-QwenKV-1.54B.Q2_K.gguf) | Q2_K | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Primus-Optima-QwenKV-1.54B-GGUF/resolve/main/Primus-Optima-QwenKV-1.54B.Q3_K_S.gguf) | Q3_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Primus-Optima-QwenKV-1.54B-GGUF/resolve/main/Primus-Optima-QwenKV-1.54B.Q3_K_M.gguf) | Q3_K_M | 0.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Primus-Optima-QwenKV-1.54B-GGUF/resolve/main/Primus-Optima-QwenKV-1.54B.Q3_K_L.gguf) | Q3_K_L | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Primus-Optima-QwenKV-1.54B-GGUF/resolve/main/Primus-Optima-QwenKV-1.54B.IQ4_XS.gguf) | IQ4_XS | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Primus-Optima-QwenKV-1.54B-GGUF/resolve/main/Primus-Optima-QwenKV-1.54B.Q4_K_S.gguf) | Q4_K_S | 1.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Primus-Optima-QwenKV-1.54B-GGUF/resolve/main/Primus-Optima-QwenKV-1.54B.Q4_K_M.gguf) | Q4_K_M | 1.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Primus-Optima-QwenKV-1.54B-GGUF/resolve/main/Primus-Optima-QwenKV-1.54B.Q5_K_S.gguf) | Q5_K_S | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Primus-Optima-QwenKV-1.54B-GGUF/resolve/main/Primus-Optima-QwenKV-1.54B.Q5_K_M.gguf) | Q5_K_M | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Primus-Optima-QwenKV-1.54B-GGUF/resolve/main/Primus-Optima-QwenKV-1.54B.Q6_K.gguf) | Q6_K | 1.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Primus-Optima-QwenKV-1.54B-GGUF/resolve/main/Primus-Optima-QwenKV-1.54B.Q8_0.gguf) | Q8_0 | 1.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Primus-Optima-QwenKV-1.54B-GGUF/resolve/main/Primus-Optima-QwenKV-1.54B.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. + +