commit a33bbf0a69ca80f4c01a9abcf1b9b061216c98f7 Author: ModelHub XC Date: Mon Jul 6 13:58:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/NeuralRaphael7B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..40a11a3 --- /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 +NeuralRaphael7B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +NeuralRaphael7B.f16.gguf filter=lfs diff=lfs merge=lfs -text +NeuralRaphael7B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +NeuralRaphael7B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +NeuralRaphael7B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +NeuralRaphael7B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +NeuralRaphael7B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +NeuralRaphael7B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +NeuralRaphael7B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +NeuralRaphael7B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +NeuralRaphael7B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +NeuralRaphael7B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/NeuralRaphael7B.IQ4_XS.gguf b/NeuralRaphael7B.IQ4_XS.gguf new file mode 100644 index 0000000..678775c --- /dev/null +++ b/NeuralRaphael7B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95ca2831328bd59c9e2f03d9df1e51e312f78ecee42b75d8f6faca580281a497 +size 3944389888 diff --git a/NeuralRaphael7B.Q2_K.gguf b/NeuralRaphael7B.Q2_K.gguf new file mode 100644 index 0000000..979431e --- /dev/null +++ b/NeuralRaphael7B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ccce116192900a2d278545d671cad12b3bfbc13e0fecd06f40da47745aff168b +size 2719243520 diff --git a/NeuralRaphael7B.Q3_K_L.gguf b/NeuralRaphael7B.Q3_K_L.gguf new file mode 100644 index 0000000..466bb78 --- /dev/null +++ b/NeuralRaphael7B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29d93dc25e312797de1bb0b0b7c1694e936c97788d7fa9d7cd3668b2970d7cda +size 3822025984 diff --git a/NeuralRaphael7B.Q3_K_M.gguf b/NeuralRaphael7B.Q3_K_M.gguf new file mode 100644 index 0000000..cc484f4 --- /dev/null +++ b/NeuralRaphael7B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:884a19ef7cb8781558e80ad543e5c35d93c80d59e570d19f3e46ccf71619916a +size 3518987520 diff --git a/NeuralRaphael7B.Q3_K_S.gguf b/NeuralRaphael7B.Q3_K_S.gguf new file mode 100644 index 0000000..4a7ddfa --- /dev/null +++ b/NeuralRaphael7B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45d85c9f263e298bd881a2663ec37dc0a1ed367b4d10c9259a3f73d01a89830c +size 3164568832 diff --git a/NeuralRaphael7B.Q4_K_M.gguf b/NeuralRaphael7B.Q4_K_M.gguf new file mode 100644 index 0000000..b9f2192 --- /dev/null +++ b/NeuralRaphael7B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7891802ab081993d3c9cbe327b2f4ee6e37f1bc62c1902583e40a4c9ef515202 +size 4368440576 diff --git a/NeuralRaphael7B.Q4_K_S.gguf b/NeuralRaphael7B.Q4_K_S.gguf new file mode 100644 index 0000000..871d04a --- /dev/null +++ b/NeuralRaphael7B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09365204d1fda2f922a043771f10f450b2cb91c82dff4ac2edf84372d8abc55e +size 4140375296 diff --git a/NeuralRaphael7B.Q5_K_M.gguf b/NeuralRaphael7B.Q5_K_M.gguf new file mode 100644 index 0000000..24d91d5 --- /dev/null +++ b/NeuralRaphael7B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa1490aa314dc81e2dac1674b269d2758dc28b3e802b1de874569fa990dc7b32 +size 5131410688 diff --git a/NeuralRaphael7B.Q5_K_S.gguf b/NeuralRaphael7B.Q5_K_S.gguf new file mode 100644 index 0000000..bd681ab --- /dev/null +++ b/NeuralRaphael7B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b804cc236e3f03ee941cc09267fa98e6cf332d92f15f6752fdccbc552392eab +size 4997717248 diff --git a/NeuralRaphael7B.Q6_K.gguf b/NeuralRaphael7B.Q6_K.gguf new file mode 100644 index 0000000..372b722 --- /dev/null +++ b/NeuralRaphael7B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4a7aaaff1cf36672d56f380862a4c0dd73997163bdb1a329653e5bbd598bc4b +size 5942066432 diff --git a/NeuralRaphael7B.Q8_0.gguf b/NeuralRaphael7B.Q8_0.gguf new file mode 100644 index 0000000..0051b10 --- /dev/null +++ b/NeuralRaphael7B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae74d01a8f03fd9237565bbd330dec5debed82babafbb7e97e5b79339a8c5713 +size 7695858944 diff --git a/NeuralRaphael7B.f16.gguf b/NeuralRaphael7B.f16.gguf new file mode 100644 index 0000000..311e3d6 --- /dev/null +++ b/NeuralRaphael7B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cabb273f17690d7ab6520f0ebc3c3c85f09435e88cb35647f7ef7a42e9b0f1cf +size 14484733184 diff --git a/README.md b/README.md new file mode 100644 index 0000000..6dab6aa --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: itchindigo/NeuralRaphael7B +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/itchindigo/NeuralRaphael7B + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/NeuralRaphael7B-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/NeuralRaphael7B-GGUF/resolve/main/NeuralRaphael7B.Q2_K.gguf) | Q2_K | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/NeuralRaphael7B-GGUF/resolve/main/NeuralRaphael7B.Q3_K_S.gguf) | Q3_K_S | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/NeuralRaphael7B-GGUF/resolve/main/NeuralRaphael7B.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/NeuralRaphael7B-GGUF/resolve/main/NeuralRaphael7B.Q3_K_L.gguf) | Q3_K_L | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/NeuralRaphael7B-GGUF/resolve/main/NeuralRaphael7B.IQ4_XS.gguf) | IQ4_XS | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/NeuralRaphael7B-GGUF/resolve/main/NeuralRaphael7B.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/NeuralRaphael7B-GGUF/resolve/main/NeuralRaphael7B.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/NeuralRaphael7B-GGUF/resolve/main/NeuralRaphael7B.Q5_K_S.gguf) | Q5_K_S | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/NeuralRaphael7B-GGUF/resolve/main/NeuralRaphael7B.Q5_K_M.gguf) | Q5_K_M | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/NeuralRaphael7B-GGUF/resolve/main/NeuralRaphael7B.Q6_K.gguf) | Q6_K | 6.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/NeuralRaphael7B-GGUF/resolve/main/NeuralRaphael7B.Q8_0.gguf) | Q8_0 | 7.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/NeuralRaphael7B-GGUF/resolve/main/NeuralRaphael7B.f16.gguf) | f16 | 14.6 | 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. + +