commit 4ec29e75858cf57e25d3e1c5993699f1a9115d87 Author: ModelHub XC Date: Sun Apr 12 22:43:58 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Ramses-II-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..31aac31 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,50 @@ +*.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 +Ramses-II.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Ramses-II.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Ramses-II.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Ramses-II.f16.gguf filter=lfs diff=lfs merge=lfs -text +Ramses-II.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Ramses-II.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Ramses-II.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Ramses-II.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Ramses-II.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Ramses-II.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Ramses-II.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Ramses-II.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Ramses-II.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Ramses-II.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Ramses-II.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..3bcfbcd --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: CoprolaliacPress/Ramses-II +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/CoprolaliacPress/Ramses-II + + +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/Ramses-II-GGUF/resolve/main/Ramses-II.Q2_K.gguf) | Q2_K | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/Ramses-II-GGUF/resolve/main/Ramses-II.IQ3_XS.gguf) | IQ3_XS | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/Ramses-II-GGUF/resolve/main/Ramses-II.Q3_K_S.gguf) | Q3_K_S | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Ramses-II-GGUF/resolve/main/Ramses-II.IQ3_S.gguf) | IQ3_S | 3.3 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Ramses-II-GGUF/resolve/main/Ramses-II.IQ3_M.gguf) | IQ3_M | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/Ramses-II-GGUF/resolve/main/Ramses-II.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Ramses-II-GGUF/resolve/main/Ramses-II.Q3_K_L.gguf) | Q3_K_L | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Ramses-II-GGUF/resolve/main/Ramses-II.IQ4_XS.gguf) | IQ4_XS | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/Ramses-II-GGUF/resolve/main/Ramses-II.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Ramses-II-GGUF/resolve/main/Ramses-II.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Ramses-II-GGUF/resolve/main/Ramses-II.Q5_K_S.gguf) | Q5_K_S | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/Ramses-II-GGUF/resolve/main/Ramses-II.Q5_K_M.gguf) | Q5_K_M | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/Ramses-II-GGUF/resolve/main/Ramses-II.Q6_K.gguf) | Q6_K | 6.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Ramses-II-GGUF/resolve/main/Ramses-II.Q8_0.gguf) | Q8_0 | 7.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Ramses-II-GGUF/resolve/main/Ramses-II.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. + + diff --git a/Ramses-II.IQ3_M.gguf b/Ramses-II.IQ3_M.gguf new file mode 100644 index 0000000..4df6ad8 --- /dev/null +++ b/Ramses-II.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99678d55e06072dd0babe1839d7cc4667a066d0184d0ff48f5c5026ae591cd43 +size 3284891904 diff --git a/Ramses-II.IQ3_S.gguf b/Ramses-II.IQ3_S.gguf new file mode 100644 index 0000000..28eb0df --- /dev/null +++ b/Ramses-II.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c7aa5e82222cc512bcd644dd487b67a1415cfe537e898a0aa52229d011760ec +size 3182393600 diff --git a/Ramses-II.IQ3_XS.gguf b/Ramses-II.IQ3_XS.gguf new file mode 100644 index 0000000..0fffca0 --- /dev/null +++ b/Ramses-II.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e2b305a6f4077b83e0a4423870303f8040f9076c1b86f98821fb4c28ad0abb9 +size 3018815744 diff --git a/Ramses-II.IQ4_XS.gguf b/Ramses-II.IQ4_XS.gguf new file mode 100644 index 0000000..808dcb3 --- /dev/null +++ b/Ramses-II.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8d670a21c85f25f60f3ddb8d2f57a263b3bb65c75debc207fa9525efd65c9a2 +size 3944388864 diff --git a/Ramses-II.Q2_K.gguf b/Ramses-II.Q2_K.gguf new file mode 100644 index 0000000..b288026 --- /dev/null +++ b/Ramses-II.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d7cade21160481d22a47bb78bc48dac4f8e7ee291c02247dba284009412e4ed +size 2719242496 diff --git a/Ramses-II.Q3_K_L.gguf b/Ramses-II.Q3_K_L.gguf new file mode 100644 index 0000000..7830536 --- /dev/null +++ b/Ramses-II.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d95c24eeaf51623c006224fba0d2a55a6ad3e281b8ca95b97c528743a5101fa +size 3822024960 diff --git a/Ramses-II.Q3_K_M.gguf b/Ramses-II.Q3_K_M.gguf new file mode 100644 index 0000000..3e63381 --- /dev/null +++ b/Ramses-II.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e8ada067ecd897dbec39f3c72f3a59933e23b76ff9c0feb2cd85656542e5e68 +size 3518986496 diff --git a/Ramses-II.Q3_K_S.gguf b/Ramses-II.Q3_K_S.gguf new file mode 100644 index 0000000..ce9eb44 --- /dev/null +++ b/Ramses-II.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:018fc5b63d1ff1d527ac474f6005c46dae7f9fed4fafdc2326d7096eb0dfb5e9 +size 3164567808 diff --git a/Ramses-II.Q4_K_M.gguf b/Ramses-II.Q4_K_M.gguf new file mode 100644 index 0000000..446ec91 --- /dev/null +++ b/Ramses-II.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d442573d9d102483e9510a9356508d2764a2737b363604542812175d6450c8e3 +size 4368439552 diff --git a/Ramses-II.Q4_K_S.gguf b/Ramses-II.Q4_K_S.gguf new file mode 100644 index 0000000..a22f52f --- /dev/null +++ b/Ramses-II.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cfd76712b8cf136d7c9d68982b42ee16425823d1c8a460e01812dcd76f5f982e +size 4140374272 diff --git a/Ramses-II.Q5_K_M.gguf b/Ramses-II.Q5_K_M.gguf new file mode 100644 index 0000000..ee47c90 --- /dev/null +++ b/Ramses-II.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aeb3427f72eea421bfa95f1e6bc4387cc6af9fd8cbf180824244a1e6c166f172 +size 5131409664 diff --git a/Ramses-II.Q5_K_S.gguf b/Ramses-II.Q5_K_S.gguf new file mode 100644 index 0000000..16da9b8 --- /dev/null +++ b/Ramses-II.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:935f397a029507c2968eee6476c5c5d07a92f0d2af6e1fe9bd02d350fecbb0e3 +size 4997716224 diff --git a/Ramses-II.Q6_K.gguf b/Ramses-II.Q6_K.gguf new file mode 100644 index 0000000..eff24a9 --- /dev/null +++ b/Ramses-II.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98e9e833f1fa64f833a7d3c2463bdf723b43dd56cdd5d74ac4ac05d8313d73db +size 5942065408 diff --git a/Ramses-II.Q8_0.gguf b/Ramses-II.Q8_0.gguf new file mode 100644 index 0000000..72ff7a5 --- /dev/null +++ b/Ramses-II.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cebc5c7d061d75ddc6177dd2d21072534162e819998f9322208642747901dbbd +size 7695857920 diff --git a/Ramses-II.f16.gguf b/Ramses-II.f16.gguf new file mode 100644 index 0000000..dae6da1 --- /dev/null +++ b/Ramses-II.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b90a6d760f89cc513853b3b1eef70f1b1d40e5f1d07ad4a6754b362b492e0cf0 +size 14484732160