commit 87da5619a03234f6f62637630080664f67275516 Author: ModelHub XC Date: Sat Jun 6 11:04:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/glm-muse-elite-v4-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..b5a5e2a --- /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 +glm-muse-elite-v4.f16.gguf filter=lfs diff=lfs merge=lfs -text +glm-muse-elite-v4.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +glm-muse-elite-v4.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +glm-muse-elite-v4.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +glm-muse-elite-v4.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +glm-muse-elite-v4.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +glm-muse-elite-v4.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +glm-muse-elite-v4.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +glm-muse-elite-v4.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +glm-muse-elite-v4.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +glm-muse-elite-v4.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +glm-muse-elite-v4.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..8cebbeb --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +base_model: MCult01/glm-muse-elite-v4 +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- glm4 +--- +## About + + + + + + + + + +static quants of https://huggingface.co/MCult01/glm-muse-elite-v4 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#glm-muse-elite-v4-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/glm-muse-elite-v4-GGUF/resolve/main/glm-muse-elite-v4.Q2_K.gguf) | Q2_K | 4.1 | | +| [GGUF](https://huggingface.co/mradermacher/glm-muse-elite-v4-GGUF/resolve/main/glm-muse-elite-v4.Q3_K_S.gguf) | Q3_K_S | 4.7 | | +| [GGUF](https://huggingface.co/mradermacher/glm-muse-elite-v4-GGUF/resolve/main/glm-muse-elite-v4.Q3_K_M.gguf) | Q3_K_M | 5.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/glm-muse-elite-v4-GGUF/resolve/main/glm-muse-elite-v4.Q3_K_L.gguf) | Q3_K_L | 5.3 | | +| [GGUF](https://huggingface.co/mradermacher/glm-muse-elite-v4-GGUF/resolve/main/glm-muse-elite-v4.IQ4_XS.gguf) | IQ4_XS | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/glm-muse-elite-v4-GGUF/resolve/main/glm-muse-elite-v4.Q4_K_S.gguf) | Q4_K_S | 5.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/glm-muse-elite-v4-GGUF/resolve/main/glm-muse-elite-v4.Q4_K_M.gguf) | Q4_K_M | 6.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/glm-muse-elite-v4-GGUF/resolve/main/glm-muse-elite-v4.Q5_K_S.gguf) | Q5_K_S | 6.8 | | +| [GGUF](https://huggingface.co/mradermacher/glm-muse-elite-v4-GGUF/resolve/main/glm-muse-elite-v4.Q5_K_M.gguf) | Q5_K_M | 7.2 | | +| [GGUF](https://huggingface.co/mradermacher/glm-muse-elite-v4-GGUF/resolve/main/glm-muse-elite-v4.Q6_K.gguf) | Q6_K | 8.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/glm-muse-elite-v4-GGUF/resolve/main/glm-muse-elite-v4.Q8_0.gguf) | Q8_0 | 10.1 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/glm-muse-elite-v4-GGUF/resolve/main/glm-muse-elite-v4.f16.gguf) | f16 | 18.9 | 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/glm-muse-elite-v4.IQ4_XS.gguf b/glm-muse-elite-v4.IQ4_XS.gguf new file mode 100644 index 0000000..12b54af --- /dev/null +++ b/glm-muse-elite-v4.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a6caf38a4f24c9e770242d2550c548fc07312e5e4b7de63f1b9ada7b7a271d3 +size 5314869216 diff --git a/glm-muse-elite-v4.Q2_K.gguf b/glm-muse-elite-v4.Q2_K.gguf new file mode 100644 index 0000000..7f48ebb --- /dev/null +++ b/glm-muse-elite-v4.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05f0729669cf104764e2a1818f059c194caa20d987a0e39d4925da70e9c9e408 +size 4006344672 diff --git a/glm-muse-elite-v4.Q3_K_L.gguf b/glm-muse-elite-v4.Q3_K_L.gguf new file mode 100644 index 0000000..704ffff --- /dev/null +++ b/glm-muse-elite-v4.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:198131783e68eba37215612de21cfeb559cd1373cda1cb98d2f19c2e87b5a00d +size 5196609504 diff --git a/glm-muse-elite-v4.Q3_K_M.gguf b/glm-muse-elite-v4.Q3_K_M.gguf new file mode 100644 index 0000000..f48a355 --- /dev/null +++ b/glm-muse-elite-v4.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:083cb0023321acd986e1543671074670e87409f80d5680fcdda2810ce8f6da31 +size 4974508000 diff --git a/glm-muse-elite-v4.Q3_K_S.gguf b/glm-muse-elite-v4.Q3_K_S.gguf new file mode 100644 index 0000000..fea6cfd --- /dev/null +++ b/glm-muse-elite-v4.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d5f874294c30ccf12aeebfc9b583c7afc85b05d8983df5cc1116fa9b96c0261 +size 4592039904 diff --git a/glm-muse-elite-v4.Q4_K_M.gguf b/glm-muse-elite-v4.Q4_K_M.gguf new file mode 100644 index 0000000..ead21c9 --- /dev/null +++ b/glm-muse-elite-v4.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4abb024e8d973144dee9a2ec0421ad04a68556e52db214933986a92188d6832b +size 6166575072 diff --git a/glm-muse-elite-v4.Q4_K_S.gguf b/glm-muse-elite-v4.Q4_K_S.gguf new file mode 100644 index 0000000..c70e84f --- /dev/null +++ b/glm-muse-elite-v4.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8f346a8d02f0978b1082283e6f1ff4dcf81499381ed9ea441cdc51fb73cca90 +size 5758482400 diff --git a/glm-muse-elite-v4.Q5_K_M.gguf b/glm-muse-elite-v4.Q5_K_M.gguf new file mode 100644 index 0000000..aae39ca --- /dev/null +++ b/glm-muse-elite-v4.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f56ab77d79d3f894e9e7617b008d0724cf932aa7cfe6484772f76b64369c0dd7 +size 7050917856 diff --git a/glm-muse-elite-v4.Q5_K_S.gguf b/glm-muse-elite-v4.Q5_K_S.gguf new file mode 100644 index 0000000..99a4895 --- /dev/null +++ b/glm-muse-elite-v4.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd845ab0dc1cd7f45c12c52c2d826b3d697b1fe8dfa4d01f2e7c174058de0f77 +size 6697514976 diff --git a/glm-muse-elite-v4.Q6_K.gguf b/glm-muse-elite-v4.Q6_K.gguf new file mode 100644 index 0000000..c982226 --- /dev/null +++ b/glm-muse-elite-v4.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b909b31fbea2fcb8a7abc5bd870d9d4dca5ff3eae6ff036aa7ba5e91389d4179 +size 8266643424 diff --git a/glm-muse-elite-v4.Q8_0.gguf b/glm-muse-elite-v4.Q8_0.gguf new file mode 100644 index 0000000..80de7a9 --- /dev/null +++ b/glm-muse-elite-v4.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71f8b2e37665d55f73a445a10b4de162895e2148302f978c64377dc97412e4bc +size 9999611872 diff --git a/glm-muse-elite-v4.f16.gguf b/glm-muse-elite-v4.f16.gguf new file mode 100644 index 0000000..4cea11b --- /dev/null +++ b/glm-muse-elite-v4.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ebf9bad7abece5b96fd7cf87813a239e81d4aa17bd6b418c045f16fd33d4138 +size 18811582432