commit a4f5040aec2dc53dbaab6e2f32d1730fda109917 Author: ModelHub XC Date: Mon Aug 10 21:05:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Muffin-2.9b-1C25-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..c4afa31 --- /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 +Muffin-2.9b-1C25.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Muffin-2.9b-1C25.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Muffin-2.9b-1C25.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Muffin-2.9b-1C25.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Muffin-2.9b-1C25.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Muffin-2.9b-1C25.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Muffin-2.9b-1C25.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Muffin-2.9b-1C25.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Muffin-2.9b-1C25.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Muffin-2.9b-1C25.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Muffin-2.9b-1C25.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Muffin-2.9b-1C25.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Muffin-2.9b-1C25.IQ4_XS.gguf b/Muffin-2.9b-1C25.IQ4_XS.gguf new file mode 100644 index 0000000..8dc977a --- /dev/null +++ b/Muffin-2.9b-1C25.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b1e8460ca332b54ab97eb53c35f008dcd79dd45032bd6b3bf9e56f9ed716473 +size 59390752 diff --git a/Muffin-2.9b-1C25.Q2_K.gguf b/Muffin-2.9b-1C25.Q2_K.gguf new file mode 100644 index 0000000..db96dec --- /dev/null +++ b/Muffin-2.9b-1C25.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ecf945d37315564ea2ca1cc668e4fd0427495df710dc4e6d4f99c38705c9f416 +size 52561696 diff --git a/Muffin-2.9b-1C25.Q3_K_L.gguf b/Muffin-2.9b-1C25.Q3_K_L.gguf new file mode 100644 index 0000000..69ed1b1 --- /dev/null +++ b/Muffin-2.9b-1C25.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:30fece3524c5f9860311fc6d231a0f955b5eb66340fac8db53a6370bebc74b7b +size 61049632 diff --git a/Muffin-2.9b-1C25.Q3_K_M.gguf b/Muffin-2.9b-1C25.Q3_K_M.gguf new file mode 100644 index 0000000..cbdd1f3 --- /dev/null +++ b/Muffin-2.9b-1C25.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d04bdda742383ac9318a13352a6763cc3e9424f689f46a3379bed27b97efbaf0 +size 58837792 diff --git a/Muffin-2.9b-1C25.Q3_K_S.gguf b/Muffin-2.9b-1C25.Q3_K_S.gguf new file mode 100644 index 0000000..94df969 --- /dev/null +++ b/Muffin-2.9b-1C25.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4bc60c2d6f552e55197f3ba74424d6040b57fd36bca43b1e82b78f2125a228ac +size 55077664 diff --git a/Muffin-2.9b-1C25.Q4_K_M.gguf b/Muffin-2.9b-1C25.Q4_K_M.gguf new file mode 100644 index 0000000..b0b74d1 --- /dev/null +++ b/Muffin-2.9b-1C25.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f81cc2a0ccff8ddc07eea0041fe6829019d1b06abde0dd36115a8b94a51e1c7 +size 63261472 diff --git a/Muffin-2.9b-1C25.Q4_K_S.gguf b/Muffin-2.9b-1C25.Q4_K_S.gguf new file mode 100644 index 0000000..15e52a9 --- /dev/null +++ b/Muffin-2.9b-1C25.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:281a5e4d6eae0c922d93cdbd90fe941df72f63df2bcd6f9507a4623f81391781 +size 60717856 diff --git a/Muffin-2.9b-1C25.Q5_K_M.gguf b/Muffin-2.9b-1C25.Q5_K_M.gguf new file mode 100644 index 0000000..cba46ae --- /dev/null +++ b/Muffin-2.9b-1C25.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e65e93d3636d05c22037644cacb310ef492672634a44c817286e864521d0eb4c +size 68063008 diff --git a/Muffin-2.9b-1C25.Q5_K_S.gguf b/Muffin-2.9b-1C25.Q5_K_S.gguf new file mode 100644 index 0000000..bfc6650 --- /dev/null +++ b/Muffin-2.9b-1C25.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b66ee991008b549d491d9f9e4c495fbbe8c0a7e69c2fafb0e10c9334021182c6 +size 66026272 diff --git a/Muffin-2.9b-1C25.Q6_K.gguf b/Muffin-2.9b-1C25.Q6_K.gguf new file mode 100644 index 0000000..ac04248 --- /dev/null +++ b/Muffin-2.9b-1C25.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5bcd0c66dc54bf06f301bb642197058f1ac573d5bf22e2f5d687917a7bcb984 +size 71666464 diff --git a/Muffin-2.9b-1C25.Q8_0.gguf b/Muffin-2.9b-1C25.Q8_0.gguf new file mode 100644 index 0000000..4f96e84 --- /dev/null +++ b/Muffin-2.9b-1C25.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46475da70bd4f33cd34d8f2f94b01b0e05e7767b15ab730eefa33781995d2eca +size 91300448 diff --git a/Muffin-2.9b-1C25.f16.gguf b/Muffin-2.9b-1C25.f16.gguf new file mode 100644 index 0000000..eeed9ec --- /dev/null +++ b/Muffin-2.9b-1C25.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29ef13dff34ef1b9ffd52b6f7f355bd5793d7a815566821a87ec4dee5468dfcb +size 167302912 diff --git a/README.md b/README.md new file mode 100644 index 0000000..34cc933 --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: FlameF0X/Muffin-2.9b-1C25 +datasets: +- FlameF0X/DialogMLM-50K +language: +- en +library_name: transformers +license: mit +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +--- +## About + + + + + + +static quants of https://huggingface.co/FlameF0X/Muffin-2.9b-1C25 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Muffin-2.9b-1C25-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/Muffin-2.9b-1C25-GGUF/resolve/main/Muffin-2.9b-1C25.Q2_K.gguf) | Q2_K | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/Muffin-2.9b-1C25-GGUF/resolve/main/Muffin-2.9b-1C25.Q3_K_S.gguf) | Q3_K_S | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/Muffin-2.9b-1C25-GGUF/resolve/main/Muffin-2.9b-1C25.Q3_K_M.gguf) | Q3_K_M | 0.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Muffin-2.9b-1C25-GGUF/resolve/main/Muffin-2.9b-1C25.IQ4_XS.gguf) | IQ4_XS | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/Muffin-2.9b-1C25-GGUF/resolve/main/Muffin-2.9b-1C25.Q4_K_S.gguf) | Q4_K_S | 0.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Muffin-2.9b-1C25-GGUF/resolve/main/Muffin-2.9b-1C25.Q3_K_L.gguf) | Q3_K_L | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/Muffin-2.9b-1C25-GGUF/resolve/main/Muffin-2.9b-1C25.Q4_K_M.gguf) | Q4_K_M | 0.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Muffin-2.9b-1C25-GGUF/resolve/main/Muffin-2.9b-1C25.Q5_K_S.gguf) | Q5_K_S | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/Muffin-2.9b-1C25-GGUF/resolve/main/Muffin-2.9b-1C25.Q5_K_M.gguf) | Q5_K_M | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/Muffin-2.9b-1C25-GGUF/resolve/main/Muffin-2.9b-1C25.Q6_K.gguf) | Q6_K | 0.2 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Muffin-2.9b-1C25-GGUF/resolve/main/Muffin-2.9b-1C25.Q8_0.gguf) | Q8_0 | 0.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Muffin-2.9b-1C25-GGUF/resolve/main/Muffin-2.9b-1C25.f16.gguf) | f16 | 0.3 | 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. + +