commit f50e2a170e71a9db06df8e198b326f2988d25825 Author: ModelHub XC Date: Mon Aug 3 14:17:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/LlamaIceCakeV0RP-3.1-8b-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..ec400f6 --- /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 +LlamaIceCakeV0RP-3.1-8b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +LlamaIceCakeV0RP-3.1-8b.f16.gguf filter=lfs diff=lfs merge=lfs -text +LlamaIceCakeV0RP-3.1-8b.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +LlamaIceCakeV0RP-3.1-8b.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LlamaIceCakeV0RP-3.1-8b.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +LlamaIceCakeV0RP-3.1-8b.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +LlamaIceCakeV0RP-3.1-8b.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +LlamaIceCakeV0RP-3.1-8b.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LlamaIceCakeV0RP-3.1-8b.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LlamaIceCakeV0RP-3.1-8b.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +LlamaIceCakeV0RP-3.1-8b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LlamaIceCakeV0RP-3.1-8b.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LlamaIceCakeV0RP-3.1-8b.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LlamaIceCakeV0RP-3.1-8b.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +LlamaIceCakeV0RP-3.1-8b.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/LlamaIceCakeV0RP-3.1-8b.IQ3_M.gguf b/LlamaIceCakeV0RP-3.1-8b.IQ3_M.gguf new file mode 100644 index 0000000..5244ede --- /dev/null +++ b/LlamaIceCakeV0RP-3.1-8b.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d08282d1c53946580e0cfdc0351f43f03c4d2d4e194f9e121e896a0749d6a64 +size 3784824096 diff --git a/LlamaIceCakeV0RP-3.1-8b.IQ3_S.gguf b/LlamaIceCakeV0RP-3.1-8b.IQ3_S.gguf new file mode 100644 index 0000000..32c2b7c --- /dev/null +++ b/LlamaIceCakeV0RP-3.1-8b.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c4ef66dc5dfba063dc1f82e4b753c94e2bc82345724bc61f32999f6c4ad4c59 +size 3682325792 diff --git a/LlamaIceCakeV0RP-3.1-8b.IQ3_XS.gguf b/LlamaIceCakeV0RP-3.1-8b.IQ3_XS.gguf new file mode 100644 index 0000000..32bd986 --- /dev/null +++ b/LlamaIceCakeV0RP-3.1-8b.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:994bce852e694835daa244de37f6cf1f029545b1084682c6693a529858ba75e5 +size 3518747936 diff --git a/LlamaIceCakeV0RP-3.1-8b.IQ4_XS.gguf b/LlamaIceCakeV0RP-3.1-8b.IQ4_XS.gguf new file mode 100644 index 0000000..faf66fb --- /dev/null +++ b/LlamaIceCakeV0RP-3.1-8b.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c26ceb382c6d4ff5f239df6e04f69bc0334cc78ce506e057c44af7b2c0c51503 +size 4484363552 diff --git a/LlamaIceCakeV0RP-3.1-8b.Q2_K.gguf b/LlamaIceCakeV0RP-3.1-8b.Q2_K.gguf new file mode 100644 index 0000000..8c9688c --- /dev/null +++ b/LlamaIceCakeV0RP-3.1-8b.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:279dac861be070c661a8e66d95755068948e747e146ad38133d3742c7ac5a0b8 +size 3179132192 diff --git a/LlamaIceCakeV0RP-3.1-8b.Q3_K_L.gguf b/LlamaIceCakeV0RP-3.1-8b.Q3_K_L.gguf new file mode 100644 index 0000000..ae749f3 --- /dev/null +++ b/LlamaIceCakeV0RP-3.1-8b.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e04665074768ff3026a487c140b88c7e7ad815a03d930171d2e524e6b0bd626 +size 4321957152 diff --git a/LlamaIceCakeV0RP-3.1-8b.Q3_K_M.gguf b/LlamaIceCakeV0RP-3.1-8b.Q3_K_M.gguf new file mode 100644 index 0000000..59511f7 --- /dev/null +++ b/LlamaIceCakeV0RP-3.1-8b.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b6cff5dfc73b3f78f913163dad09faaf18c949ed4671303155d99dfe8ea3211 +size 4018918688 diff --git a/LlamaIceCakeV0RP-3.1-8b.Q3_K_S.gguf b/LlamaIceCakeV0RP-3.1-8b.Q3_K_S.gguf new file mode 100644 index 0000000..f3f2b95 --- /dev/null +++ b/LlamaIceCakeV0RP-3.1-8b.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dfd95b5ba7c2e7de26ba8e939ffddc481c29ef6ff91e0ef336ec981790a5bbc8 +size 3664500000 diff --git a/LlamaIceCakeV0RP-3.1-8b.Q4_K_M.gguf b/LlamaIceCakeV0RP-3.1-8b.Q4_K_M.gguf new file mode 100644 index 0000000..6dc6ce7 --- /dev/null +++ b/LlamaIceCakeV0RP-3.1-8b.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce48ff14969867b8d079195de4cd2cdb3233f9bf6aec388e5c2a64a4313b5d5e +size 4920735008 diff --git a/LlamaIceCakeV0RP-3.1-8b.Q4_K_S.gguf b/LlamaIceCakeV0RP-3.1-8b.Q4_K_S.gguf new file mode 100644 index 0000000..211a535 --- /dev/null +++ b/LlamaIceCakeV0RP-3.1-8b.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e75ac75bc43bdd41c6731e440aa8557c7676b5f7fe4398b4ac852f33448016c +size 4692669728 diff --git a/LlamaIceCakeV0RP-3.1-8b.Q5_K_M.gguf b/LlamaIceCakeV0RP-3.1-8b.Q5_K_M.gguf new file mode 100644 index 0000000..d8965d2 --- /dev/null +++ b/LlamaIceCakeV0RP-3.1-8b.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2415ed669312123cfe90818b58b78d6e00bff1722cf8e105fac508b81e6cbc99 +size 5732988192 diff --git a/LlamaIceCakeV0RP-3.1-8b.Q5_K_S.gguf b/LlamaIceCakeV0RP-3.1-8b.Q5_K_S.gguf new file mode 100644 index 0000000..b72ac81 --- /dev/null +++ b/LlamaIceCakeV0RP-3.1-8b.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27e230b72596f51f3e64c14db5746867513b9b450a43da5eeba52fe2c3e33204 +size 5599294752 diff --git a/LlamaIceCakeV0RP-3.1-8b.Q6_K.gguf b/LlamaIceCakeV0RP-3.1-8b.Q6_K.gguf new file mode 100644 index 0000000..ccd4967 --- /dev/null +++ b/LlamaIceCakeV0RP-3.1-8b.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c360bc17e8551a744fbb03907cefb5aa3b785636bc17b09e5d5eb4bdc5d1729c +size 6596007200 diff --git a/LlamaIceCakeV0RP-3.1-8b.Q8_0.gguf b/LlamaIceCakeV0RP-3.1-8b.Q8_0.gguf new file mode 100644 index 0000000..9eba808 --- /dev/null +++ b/LlamaIceCakeV0RP-3.1-8b.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e1522eacef413be10e2eaae944909f7180693ea40d4c38f1ccefe4531700f4d +size 8540771616 diff --git a/LlamaIceCakeV0RP-3.1-8b.f16.gguf b/LlamaIceCakeV0RP-3.1-8b.f16.gguf new file mode 100644 index 0000000..908d58f --- /dev/null +++ b/LlamaIceCakeV0RP-3.1-8b.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb7df0267ed62e4a46dcfb041c30d2b5543f92f37a93410c83bae392d8640831 +size 16068891936 diff --git a/README.md b/README.md new file mode 100644 index 0000000..c60cde7 --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: icefog72/LlamaIceCakeV0RP-3.1-8b +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/icefog72/LlamaIceCakeV0RP-3.1-8b + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/LlamaIceCakeV0RP-3.1-8b-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/LlamaIceCakeV0RP-3.1-8b-GGUF/resolve/main/LlamaIceCakeV0RP-3.1-8b.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/LlamaIceCakeV0RP-3.1-8b-GGUF/resolve/main/LlamaIceCakeV0RP-3.1-8b.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/LlamaIceCakeV0RP-3.1-8b-GGUF/resolve/main/LlamaIceCakeV0RP-3.1-8b.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/LlamaIceCakeV0RP-3.1-8b-GGUF/resolve/main/LlamaIceCakeV0RP-3.1-8b.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/LlamaIceCakeV0RP-3.1-8b-GGUF/resolve/main/LlamaIceCakeV0RP-3.1-8b.IQ3_M.gguf) | IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/LlamaIceCakeV0RP-3.1-8b-GGUF/resolve/main/LlamaIceCakeV0RP-3.1-8b.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/LlamaIceCakeV0RP-3.1-8b-GGUF/resolve/main/LlamaIceCakeV0RP-3.1-8b.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/LlamaIceCakeV0RP-3.1-8b-GGUF/resolve/main/LlamaIceCakeV0RP-3.1-8b.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/LlamaIceCakeV0RP-3.1-8b-GGUF/resolve/main/LlamaIceCakeV0RP-3.1-8b.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LlamaIceCakeV0RP-3.1-8b-GGUF/resolve/main/LlamaIceCakeV0RP-3.1-8b.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LlamaIceCakeV0RP-3.1-8b-GGUF/resolve/main/LlamaIceCakeV0RP-3.1-8b.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/LlamaIceCakeV0RP-3.1-8b-GGUF/resolve/main/LlamaIceCakeV0RP-3.1-8b.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/LlamaIceCakeV0RP-3.1-8b-GGUF/resolve/main/LlamaIceCakeV0RP-3.1-8b.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/LlamaIceCakeV0RP-3.1-8b-GGUF/resolve/main/LlamaIceCakeV0RP-3.1-8b.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/LlamaIceCakeV0RP-3.1-8b-GGUF/resolve/main/LlamaIceCakeV0RP-3.1-8b.f16.gguf) | f16 | 16.2 | 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. + +