commit d35ad661e8b8248b559ea6f011e264c82f33a2bf Author: ModelHub XC Date: Wed Aug 26 19:34:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Sparkle-12B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..5235e10 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,48 @@ +*.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 +Sparkle-12B.mmproj-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Sparkle-12B.mmproj-f16.gguf filter=lfs diff=lfs merge=lfs -text +Sparkle-12B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Sparkle-12B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Sparkle-12B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Sparkle-12B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Sparkle-12B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Sparkle-12B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Sparkle-12B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Sparkle-12B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Sparkle-12B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Sparkle-12B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Sparkle-12B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..d28308b --- /dev/null +++ b/README.md @@ -0,0 +1,79 @@ +--- +base_model: soob3123/Sparkle-12B +datasets: +- soob3123/rp_dataset +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- narration +- storytelling +- creative-writing +- happy +- positive +- descriptive +--- +## About + + + + + + +static quants of https://huggingface.co/soob3123/Sparkle-12B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Sparkle-12B-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Sparkle-12B-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/Sparkle-12B-GGUF/resolve/main/Sparkle-12B.mmproj-Q8_0.gguf) | mmproj-Q8_0 | 0.7 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/Sparkle-12B-GGUF/resolve/main/Sparkle-12B.mmproj-f16.gguf) | mmproj-f16 | 1.0 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/Sparkle-12B-GGUF/resolve/main/Sparkle-12B.Q2_K.gguf) | Q2_K | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/Sparkle-12B-GGUF/resolve/main/Sparkle-12B.Q3_K_S.gguf) | Q3_K_S | 5.6 | | +| [GGUF](https://huggingface.co/mradermacher/Sparkle-12B-GGUF/resolve/main/Sparkle-12B.Q3_K_M.gguf) | Q3_K_M | 6.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Sparkle-12B-GGUF/resolve/main/Sparkle-12B.Q3_K_L.gguf) | Q3_K_L | 6.6 | | +| [GGUF](https://huggingface.co/mradermacher/Sparkle-12B-GGUF/resolve/main/Sparkle-12B.IQ4_XS.gguf) | IQ4_XS | 6.7 | | +| [GGUF](https://huggingface.co/mradermacher/Sparkle-12B-GGUF/resolve/main/Sparkle-12B.Q4_K_S.gguf) | Q4_K_S | 7.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Sparkle-12B-GGUF/resolve/main/Sparkle-12B.Q4_K_M.gguf) | Q4_K_M | 7.4 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Sparkle-12B-GGUF/resolve/main/Sparkle-12B.Q5_K_S.gguf) | Q5_K_S | 8.3 | | +| [GGUF](https://huggingface.co/mradermacher/Sparkle-12B-GGUF/resolve/main/Sparkle-12B.Q5_K_M.gguf) | Q5_K_M | 8.5 | | +| [GGUF](https://huggingface.co/mradermacher/Sparkle-12B-GGUF/resolve/main/Sparkle-12B.Q6_K.gguf) | Q6_K | 9.8 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Sparkle-12B-GGUF/resolve/main/Sparkle-12B.Q8_0.gguf) | Q8_0 | 12.6 | fast, best quality | + +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/Sparkle-12B.IQ4_XS.gguf b/Sparkle-12B.IQ4_XS.gguf new file mode 100644 index 0000000..7cddf0d --- /dev/null +++ b/Sparkle-12B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:026f273284b85f02bbb4df5a19292a7b9cc0ea5cb8dbde4ad4cd2805c98b9d6d +size 6606261120 diff --git a/Sparkle-12B.Q2_K.gguf b/Sparkle-12B.Q2_K.gguf new file mode 100644 index 0000000..2a4e69a --- /dev/null +++ b/Sparkle-12B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34c9c8bd6ea31e60fdc10a8a5e02a99f21dc927448de14874b9ac3768bb4b689 +size 4768222080 diff --git a/Sparkle-12B.Q3_K_L.gguf b/Sparkle-12B.Q3_K_L.gguf new file mode 100644 index 0000000..6d70d80 --- /dev/null +++ b/Sparkle-12B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d5ac2041189485644c1c0650c1e474e2bc62ef6cdbc934d30637c32e13bf465 +size 6480186240 diff --git a/Sparkle-12B.Q3_K_M.gguf b/Sparkle-12B.Q3_K_M.gguf new file mode 100644 index 0000000..661a46e --- /dev/null +++ b/Sparkle-12B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d4c15565d859b209e26c15887985eeca7039752b8e96f52d369f0e30337b76e +size 6008818560 diff --git a/Sparkle-12B.Q3_K_S.gguf b/Sparkle-12B.Q3_K_S.gguf new file mode 100644 index 0000000..36469b1 --- /dev/null +++ b/Sparkle-12B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f20e5173c4bbe3e52631a33781404ec834a5505ad8c8a5f0e0be4e7885bd5357 +size 5458316160 diff --git a/Sparkle-12B.Q4_K_M.gguf b/Sparkle-12B.Q4_K_M.gguf new file mode 100644 index 0000000..9dd6bac --- /dev/null +++ b/Sparkle-12B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a80a098a32f933cbad77dd7918d761d0f367b7da1e8dfaa23bf2a9f156036c55 +size 7300778880 diff --git a/Sparkle-12B.Q4_K_S.gguf b/Sparkle-12B.Q4_K_S.gguf new file mode 100644 index 0000000..41fd0f7 --- /dev/null +++ b/Sparkle-12B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5516c1ebcc44e745aa2be65d93ac969363229abbdec5e808b597fb0abcb1ed9f +size 6935333760 diff --git a/Sparkle-12B.Q5_K_M.gguf b/Sparkle-12B.Q5_K_M.gguf new file mode 100644 index 0000000..803dfeb --- /dev/null +++ b/Sparkle-12B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd7c10035df4a5e8bb7c59c7da598699bae5e3f873b1dcd7809236ea5164e3ba +size 8445037440 diff --git a/Sparkle-12B.Q5_K_S.gguf b/Sparkle-12B.Q5_K_S.gguf new file mode 100644 index 0000000..e86bf75 --- /dev/null +++ b/Sparkle-12B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7453478101b946b5986eda98bf3f3b15442efde842725891517fa87bfe0389b1 +size 8231963520 diff --git a/Sparkle-12B.Q6_K.gguf b/Sparkle-12B.Q6_K.gguf new file mode 100644 index 0000000..53f41bc --- /dev/null +++ b/Sparkle-12B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b6ff36f49670a3c267a4404c362ae3d5d6fec80805ae2c0351ad2c3fed394be +size 9660812160 diff --git a/Sparkle-12B.Q8_0.gguf b/Sparkle-12B.Q8_0.gguf new file mode 100644 index 0000000..0abeca7 --- /dev/null +++ b/Sparkle-12B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cafee0ceea92958de3dc91d3271c554fbf66b966db2fe020b53af6aa466557cf +size 12510213120 diff --git a/Sparkle-12B.mmproj-Q8_0.gguf b/Sparkle-12B.mmproj-Q8_0.gguf new file mode 100644 index 0000000..adab5b5 --- /dev/null +++ b/Sparkle-12B.mmproj-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd46cb64556fbd4118a944b5b27a8398c5e7b6111957dd0ca7eda472fd0e1f81 +size 590179104 diff --git a/Sparkle-12B.mmproj-f16.gguf b/Sparkle-12B.mmproj-f16.gguf new file mode 100644 index 0000000..7c64fe4 --- /dev/null +++ b/Sparkle-12B.mmproj-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:30c02d056410848227001830866e0a269fcc28aaf8ca971bded494003de9f5a5 +size 854200224