commit 631dfa16e25fb5dddd05c0b6c0bc0dd0effcf197 Author: ModelHub XC Date: Mon Sep 28 13:31:19 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3-8B-Stroganoff-4.0-Version-B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..1fb5ee9 --- /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 +Llama-3-8B-Stroganoff-4.0-Version-B.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Stroganoff-4.0-Version-B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Stroganoff-4.0-Version-B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Stroganoff-4.0-Version-B.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Stroganoff-4.0-Version-B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Stroganoff-4.0-Version-B.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Stroganoff-4.0-Version-B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Stroganoff-4.0-Version-B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Stroganoff-4.0-Version-B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Stroganoff-4.0-Version-B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Stroganoff-4.0-Version-B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Stroganoff-4.0-Version-B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Stroganoff-4.0-Version-B.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Stroganoff-4.0-Version-B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Stroganoff-4.0-Version-B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3-8B-Stroganoff-4.0-Version-B.IQ3_M.gguf b/Llama-3-8B-Stroganoff-4.0-Version-B.IQ3_M.gguf new file mode 100644 index 0000000..1e328c6 --- /dev/null +++ b/Llama-3-8B-Stroganoff-4.0-Version-B.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7909677c781ac55e589d840f2941bdbb137a54ee221a51ce02eb1c38866f13ec +size 3784835968 diff --git a/Llama-3-8B-Stroganoff-4.0-Version-B.IQ3_S.gguf b/Llama-3-8B-Stroganoff-4.0-Version-B.IQ3_S.gguf new file mode 100644 index 0000000..a72599b --- /dev/null +++ b/Llama-3-8B-Stroganoff-4.0-Version-B.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:349926155b9625d548907eb61ea4d11a80a564ab0f94e2495a840f28de9ad933 +size 3682337664 diff --git a/Llama-3-8B-Stroganoff-4.0-Version-B.IQ3_XS.gguf b/Llama-3-8B-Stroganoff-4.0-Version-B.IQ3_XS.gguf new file mode 100644 index 0000000..8ba203b --- /dev/null +++ b/Llama-3-8B-Stroganoff-4.0-Version-B.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:849adce3e5f1608b83a07d4e8a0d112c72602bf6292ecfe207c45605400085d9 +size 3518759808 diff --git a/Llama-3-8B-Stroganoff-4.0-Version-B.IQ4_XS.gguf b/Llama-3-8B-Stroganoff-4.0-Version-B.IQ4_XS.gguf new file mode 100644 index 0000000..bc60be7 --- /dev/null +++ b/Llama-3-8B-Stroganoff-4.0-Version-B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4dcf7ef356bbfee71243b7aea642aeef20118926de430ea87b2996aec8a0bb32 +size 4484376256 diff --git a/Llama-3-8B-Stroganoff-4.0-Version-B.Q2_K.gguf b/Llama-3-8B-Stroganoff-4.0-Version-B.Q2_K.gguf new file mode 100644 index 0000000..8d1681e --- /dev/null +++ b/Llama-3-8B-Stroganoff-4.0-Version-B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a47d0fe8f7f482a102ccb1d2590b163869ad3e510ab59375f1a834bf438e3ce1 +size 3179143232 diff --git a/Llama-3-8B-Stroganoff-4.0-Version-B.Q3_K_L.gguf b/Llama-3-8B-Stroganoff-4.0-Version-B.Q3_K_L.gguf new file mode 100644 index 0000000..219a7ff --- /dev/null +++ b/Llama-3-8B-Stroganoff-4.0-Version-B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7dc83ee9cc7435fd09c3ff8a974288393e2123826720c98677d0cd498b78393 +size 4321969024 diff --git a/Llama-3-8B-Stroganoff-4.0-Version-B.Q3_K_M.gguf b/Llama-3-8B-Stroganoff-4.0-Version-B.Q3_K_M.gguf new file mode 100644 index 0000000..48a28a9 --- /dev/null +++ b/Llama-3-8B-Stroganoff-4.0-Version-B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dcc92927e10fb8e620254116ade3252394c18e6c23d6716ee716b53107ecd124 +size 4018930560 diff --git a/Llama-3-8B-Stroganoff-4.0-Version-B.Q3_K_S.gguf b/Llama-3-8B-Stroganoff-4.0-Version-B.Q3_K_S.gguf new file mode 100644 index 0000000..c9dacba --- /dev/null +++ b/Llama-3-8B-Stroganoff-4.0-Version-B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05d5d65365ebd294bff3e0eeb2b81607609a0f3641bf7dd206a23521077c827d +size 3664511872 diff --git a/Llama-3-8B-Stroganoff-4.0-Version-B.Q4_K_M.gguf b/Llama-3-8B-Stroganoff-4.0-Version-B.Q4_K_M.gguf new file mode 100644 index 0000000..2c17749 --- /dev/null +++ b/Llama-3-8B-Stroganoff-4.0-Version-B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b6e344e00c90389888bba5a4c89730a920b1a0abf945ac8e7647634ff6e51d9 +size 4920747968 diff --git a/Llama-3-8B-Stroganoff-4.0-Version-B.Q4_K_S.gguf b/Llama-3-8B-Stroganoff-4.0-Version-B.Q4_K_S.gguf new file mode 100644 index 0000000..7ee6a75 --- /dev/null +++ b/Llama-3-8B-Stroganoff-4.0-Version-B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:657d2dffc42df587ec4838e7bf8e726aa740f13437f7a7cdf9ec29bfeeb71b2a +size 4692682688 diff --git a/Llama-3-8B-Stroganoff-4.0-Version-B.Q5_K_M.gguf b/Llama-3-8B-Stroganoff-4.0-Version-B.Q5_K_M.gguf new file mode 100644 index 0000000..ab79a82 --- /dev/null +++ b/Llama-3-8B-Stroganoff-4.0-Version-B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82ebc8385113b98972876b8d9ebe9b43710287c8cdb0ea487260f868c8638efd +size 5733002176 diff --git a/Llama-3-8B-Stroganoff-4.0-Version-B.Q5_K_S.gguf b/Llama-3-8B-Stroganoff-4.0-Version-B.Q5_K_S.gguf new file mode 100644 index 0000000..fd7ea76 --- /dev/null +++ b/Llama-3-8B-Stroganoff-4.0-Version-B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:201563f02520f9c206194774664197c1b76e8529356070cbd0144214d1cdfe5e +size 5599308736 diff --git a/Llama-3-8B-Stroganoff-4.0-Version-B.Q6_K.gguf b/Llama-3-8B-Stroganoff-4.0-Version-B.Q6_K.gguf new file mode 100644 index 0000000..b9c6272 --- /dev/null +++ b/Llama-3-8B-Stroganoff-4.0-Version-B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b166e35909b3b174adbcc74f4315975f8779499477e23ce804032e25d169b02b +size 6596022272 diff --git a/Llama-3-8B-Stroganoff-4.0-Version-B.Q8_0.gguf b/Llama-3-8B-Stroganoff-4.0-Version-B.Q8_0.gguf new file mode 100644 index 0000000..8f8e393 --- /dev/null +++ b/Llama-3-8B-Stroganoff-4.0-Version-B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61864e98586e726e220517bec5bfa35b5f4ca0c9288d8cb9eb76f2cded494b31 +size 8540790656 diff --git a/Llama-3-8B-Stroganoff-4.0-Version-B.f16.gguf b/Llama-3-8B-Stroganoff-4.0-Version-B.f16.gguf new file mode 100644 index 0000000..ed1853b --- /dev/null +++ b/Llama-3-8B-Stroganoff-4.0-Version-B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67d15a14023f283f62fcb6ee14bf90062c6c369eb6c1c3607849bd8641bc0cde +size 16068926336 diff --git a/README.md b/README.md new file mode 100644 index 0000000..b469ed3 --- /dev/null +++ b/README.md @@ -0,0 +1,74 @@ +--- +base_model: HiroseKoichi/Llama-3-8B-Stroganoff-4.0 +language: +- en +library_name: transformers +license: llama3 +quantized_by: mradermacher +tags: +- nsfw +- not-for-all-audiences +- llama-3 +- text-generation-inference +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/HiroseKoichi/Llama-3-8B-Stroganoff-4.0 + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-3-8B-Stroganoff-4.0-Version-B-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/Llama-3-8B-Stroganoff-4.0-Version-B-GGUF/resolve/main/Llama-3-8B-Stroganoff-4.0-Version-B.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Stroganoff-4.0-Version-B-GGUF/resolve/main/Llama-3-8B-Stroganoff-4.0-Version-B.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Stroganoff-4.0-Version-B-GGUF/resolve/main/Llama-3-8B-Stroganoff-4.0-Version-B.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Stroganoff-4.0-Version-B-GGUF/resolve/main/Llama-3-8B-Stroganoff-4.0-Version-B.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Stroganoff-4.0-Version-B-GGUF/resolve/main/Llama-3-8B-Stroganoff-4.0-Version-B.IQ3_M.gguf) | IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Stroganoff-4.0-Version-B-GGUF/resolve/main/Llama-3-8B-Stroganoff-4.0-Version-B.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Stroganoff-4.0-Version-B-GGUF/resolve/main/Llama-3-8B-Stroganoff-4.0-Version-B.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Stroganoff-4.0-Version-B-GGUF/resolve/main/Llama-3-8B-Stroganoff-4.0-Version-B.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Stroganoff-4.0-Version-B-GGUF/resolve/main/Llama-3-8B-Stroganoff-4.0-Version-B.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Stroganoff-4.0-Version-B-GGUF/resolve/main/Llama-3-8B-Stroganoff-4.0-Version-B.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Stroganoff-4.0-Version-B-GGUF/resolve/main/Llama-3-8B-Stroganoff-4.0-Version-B.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Stroganoff-4.0-Version-B-GGUF/resolve/main/Llama-3-8B-Stroganoff-4.0-Version-B.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Stroganoff-4.0-Version-B-GGUF/resolve/main/Llama-3-8B-Stroganoff-4.0-Version-B.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Stroganoff-4.0-Version-B-GGUF/resolve/main/Llama-3-8B-Stroganoff-4.0-Version-B.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Stroganoff-4.0-Version-B-GGUF/resolve/main/Llama-3-8B-Stroganoff-4.0-Version-B.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. + +