commit d54f9c57c1ac2739b36e6f9259a8744e072e8c2f Author: ModelHub XC Date: Tue Jun 2 20:45:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/GRaPE-Flash-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..7081522 --- /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 +GRaPE-Flash.f16.gguf filter=lfs diff=lfs merge=lfs -text +GRaPE-Flash.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GRaPE-Flash.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +GRaPE-Flash.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +GRaPE-Flash.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +GRaPE-Flash.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GRaPE-Flash.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GRaPE-Flash.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +GRaPE-Flash.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GRaPE-Flash.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GRaPE-Flash.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GRaPE-Flash.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/GRaPE-Flash.IQ4_XS.gguf b/GRaPE-Flash.IQ4_XS.gguf new file mode 100644 index 0000000..8908fb4 --- /dev/null +++ b/GRaPE-Flash.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d12f4355def2db8e8560ec81c4a504d9622c0033099dcbbbf5bbfb6bdfe4135 +size 3757046592 diff --git a/GRaPE-Flash.Q2_K.gguf b/GRaPE-Flash.Q2_K.gguf new file mode 100644 index 0000000..fc3f385 --- /dev/null +++ b/GRaPE-Flash.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab9c199c6d790c6a738d8d0af8ed59cb2090d4d49502da8dab4f5028ce788af6 +size 2562763584 diff --git a/GRaPE-Flash.Q3_K_L.gguf b/GRaPE-Flash.Q3_K_L.gguf new file mode 100644 index 0000000..b5fb775 --- /dev/null +++ b/GRaPE-Flash.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24360b457de575bbf289ef3e52062ac58abe278d26791a466a9aac0bee68205a +size 3611317056 diff --git a/GRaPE-Flash.Q3_K_M.gguf b/GRaPE-Flash.Q3_K_M.gguf new file mode 100644 index 0000000..ab810d3 --- /dev/null +++ b/GRaPE-Flash.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b979258476ce8d328229bc29e761c4eb4a457ce197108c29f9f65bc2ffff376 +size 3343930176 diff --git a/GRaPE-Flash.Q3_K_S.gguf b/GRaPE-Flash.Q3_K_S.gguf new file mode 100644 index 0000000..a59efe3 --- /dev/null +++ b/GRaPE-Flash.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21351fe6fd71bf37957407617a7cbdd5388c190f9c813c315d3cae980f7b1537 +size 3023065920 diff --git a/GRaPE-Flash.Q4_K_M.gguf b/GRaPE-Flash.Q4_K_M.gguf new file mode 100644 index 0000000..7938964 --- /dev/null +++ b/GRaPE-Flash.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:afc8e6f3d12ca17b22088fd9cd0422610506cd9cccf207afbce2cbe9a3eb2b94 +size 4213513024 diff --git a/GRaPE-Flash.Q4_K_S.gguf b/GRaPE-Flash.Q4_K_S.gguf new file mode 100644 index 0000000..0070e9a --- /dev/null +++ b/GRaPE-Flash.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e0e6bcd0383da9d31f2a7819fd23c562acf8c6bd6e403fba1d93d5c2450b20f +size 3963689792 diff --git a/GRaPE-Flash.Q5_K_M.gguf b/GRaPE-Flash.Q5_K_M.gguf new file mode 100644 index 0000000..41ec21b --- /dev/null +++ b/GRaPE-Flash.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9725c5e2134829a9a7c76799794a230e762642a86a18e739326aa85b56845669 +size 4926839616 diff --git a/GRaPE-Flash.Q5_K_S.gguf b/GRaPE-Flash.Q5_K_S.gguf new file mode 100644 index 0000000..7f77dc6 --- /dev/null +++ b/GRaPE-Flash.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a106ab047703200960973009cd79765bdc1d093e0e40e534375f178b8833e07 +size 4779776832 diff --git a/GRaPE-Flash.Q6_K.gguf b/GRaPE-Flash.Q6_K.gguf new file mode 100644 index 0000000..057872c --- /dev/null +++ b/GRaPE-Flash.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82b8f8ca0c8bc13be9e671c1469ec540641a3c37524ec30857756b2defc71de0 +size 5684749120 diff --git a/GRaPE-Flash.Q8_0.gguf b/GRaPE-Flash.Q8_0.gguf new file mode 100644 index 0000000..d8409ce --- /dev/null +++ b/GRaPE-Flash.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01c35e34b66894ba63e8e03bad4119e708d9e44875cd8cc5a6001c0f2d62bede +size 7359943488 diff --git a/GRaPE-Flash.f16.gguf b/GRaPE-Flash.f16.gguf new file mode 100644 index 0000000..f4ba463 --- /dev/null +++ b/GRaPE-Flash.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7122398b69557c500154e07c8a9dd51c78cd446e810e90b491abd32d1998f3ff +size 13844566848 diff --git a/README.md b/README.md new file mode 100644 index 0000000..3d3dbca --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: SL-AI/GRaPE-Flash +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/SL-AI/GRaPE-Flash + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#GRaPE-Flash-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/GRaPE-Flash-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/GRaPE-Flash-GGUF/resolve/main/GRaPE-Flash.Q2_K.gguf) | Q2_K | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/GRaPE-Flash-GGUF/resolve/main/GRaPE-Flash.Q3_K_S.gguf) | Q3_K_S | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/GRaPE-Flash-GGUF/resolve/main/GRaPE-Flash.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/GRaPE-Flash-GGUF/resolve/main/GRaPE-Flash.Q3_K_L.gguf) | Q3_K_L | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/GRaPE-Flash-GGUF/resolve/main/GRaPE-Flash.IQ4_XS.gguf) | IQ4_XS | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/GRaPE-Flash-GGUF/resolve/main/GRaPE-Flash.Q4_K_S.gguf) | Q4_K_S | 4.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/GRaPE-Flash-GGUF/resolve/main/GRaPE-Flash.Q4_K_M.gguf) | Q4_K_M | 4.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/GRaPE-Flash-GGUF/resolve/main/GRaPE-Flash.Q5_K_S.gguf) | Q5_K_S | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/GRaPE-Flash-GGUF/resolve/main/GRaPE-Flash.Q5_K_M.gguf) | Q5_K_M | 5.0 | | +| [GGUF](https://huggingface.co/mradermacher/GRaPE-Flash-GGUF/resolve/main/GRaPE-Flash.Q6_K.gguf) | Q6_K | 5.8 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/GRaPE-Flash-GGUF/resolve/main/GRaPE-Flash.Q8_0.gguf) | Q8_0 | 7.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/GRaPE-Flash-GGUF/resolve/main/GRaPE-Flash.f16.gguf) | f16 | 13.9 | 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. + +