commit 3b3eda4a1cececa4c9cea1bb58672d86f70b9b88 Author: ModelHub XC Date: Tue Aug 11 15:27:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Meta-Llama-3.1-8B-Instruct-sliced-18-layers-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..adc5b0b --- /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 +Meta-Llama-3.1-8B-Instruct-sliced-18-layers.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3.1-8B-Instruct-sliced-18-layers.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3.1-8B-Instruct-sliced-18-layers.f16.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3.1-8B-Instruct-sliced-18-layers.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3.1-8B-Instruct-sliced-18-layers.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3.1-8B-Instruct-sliced-18-layers.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3.1-8B-Instruct-sliced-18-layers.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3.1-8B-Instruct-sliced-18-layers.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3.1-8B-Instruct-sliced-18-layers.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3.1-8B-Instruct-sliced-18-layers.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3.1-8B-Instruct-sliced-18-layers.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3.1-8B-Instruct-sliced-18-layers.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3.1-8B-Instruct-sliced-18-layers.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3.1-8B-Instruct-sliced-18-layers.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3.1-8B-Instruct-sliced-18-layers.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Meta-Llama-3.1-8B-Instruct-sliced-18-layers.IQ3_M.gguf b/Meta-Llama-3.1-8B-Instruct-sliced-18-layers.IQ3_M.gguf new file mode 100644 index 0000000..032de7f --- /dev/null +++ b/Meta-Llama-3.1-8B-Instruct-sliced-18-layers.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1162e1a4d0e1ff6055b22a1def51d805c850a58cf02789ecd5423819fa583f73 +size 2417735904 diff --git a/Meta-Llama-3.1-8B-Instruct-sliced-18-layers.IQ3_S.gguf b/Meta-Llama-3.1-8B-Instruct-sliced-18-layers.IQ3_S.gguf new file mode 100644 index 0000000..02871eb --- /dev/null +++ b/Meta-Llama-3.1-8B-Instruct-sliced-18-layers.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4ae348bd86dac9495f8f4c43d8cb9444cc00a2bd71107c07932b69f47381555 +size 2362030304 diff --git a/Meta-Llama-3.1-8B-Instruct-sliced-18-layers.IQ3_XS.gguf b/Meta-Llama-3.1-8B-Instruct-sliced-18-layers.IQ3_XS.gguf new file mode 100644 index 0000000..cb8681b --- /dev/null +++ b/Meta-Llama-3.1-8B-Instruct-sliced-18-layers.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37c6138a62934985e201bcf3fd85240adfedf219b436fa86f5ec6f03f7825e7f +size 2272770272 diff --git a/Meta-Llama-3.1-8B-Instruct-sliced-18-layers.IQ4_XS.gguf b/Meta-Llama-3.1-8B-Instruct-sliced-18-layers.IQ4_XS.gguf new file mode 100644 index 0000000..f64fbbf --- /dev/null +++ b/Meta-Llama-3.1-8B-Instruct-sliced-18-layers.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf37bbaee2a8f0d7702179db9f93c9a0f31fbc0020533a79ecbf0691bfc0cdab +size 2834225376 diff --git a/Meta-Llama-3.1-8B-Instruct-sliced-18-layers.Q2_K.gguf b/Meta-Llama-3.1-8B-Instruct-sliced-18-layers.Q2_K.gguf new file mode 100644 index 0000000..5b89713 --- /dev/null +++ b/Meta-Llama-3.1-8B-Instruct-sliced-18-layers.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47fdc86fba7a1d3d81480cda177c1cad3468c8842675ced4e671b8a6b4cbb8e4 +size 2055641312 diff --git a/Meta-Llama-3.1-8B-Instruct-sliced-18-layers.Q3_K_L.gguf b/Meta-Llama-3.1-8B-Instruct-sliced-18-layers.Q3_K_L.gguf new file mode 100644 index 0000000..f0d4c62 --- /dev/null +++ b/Meta-Llama-3.1-8B-Instruct-sliced-18-layers.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8b55f5b5c43fe5231745974a43897e1e2c2021fe271c1cdbd3bffef3c60c259 +size 2721822944 diff --git a/Meta-Llama-3.1-8B-Instruct-sliced-18-layers.Q3_K_M.gguf b/Meta-Llama-3.1-8B-Instruct-sliced-18-layers.Q3_K_M.gguf new file mode 100644 index 0000000..67f20f4 --- /dev/null +++ b/Meta-Llama-3.1-8B-Instruct-sliced-18-layers.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a350c106f6cec61743fdaf5644d46250c3a9f94246de39b6e43d126c8aa49aeb +size 2550905056 diff --git a/Meta-Llama-3.1-8B-Instruct-sliced-18-layers.Q3_K_S.gguf b/Meta-Llama-3.1-8B-Instruct-sliced-18-layers.Q3_K_S.gguf new file mode 100644 index 0000000..cb38499 --- /dev/null +++ b/Meta-Llama-3.1-8B-Instruct-sliced-18-layers.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b6688bc472bf5b08b992e5f8868b9c0fde0d404367b57ebca669be3bab80436 +size 2352003296 diff --git a/Meta-Llama-3.1-8B-Instruct-sliced-18-layers.Q4_K_M.gguf b/Meta-Llama-3.1-8B-Instruct-sliced-18-layers.Q4_K_M.gguf new file mode 100644 index 0000000..1864b79 --- /dev/null +++ b/Meta-Llama-3.1-8B-Instruct-sliced-18-layers.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5b13925d601768c5522654d10f75630d8b578f9fa19439579f846ba04bd51ad +size 3089160416 diff --git a/Meta-Llama-3.1-8B-Instruct-sliced-18-layers.Q4_K_S.gguf b/Meta-Llama-3.1-8B-Instruct-sliced-18-layers.Q4_K_S.gguf new file mode 100644 index 0000000..dab0d67 --- /dev/null +++ b/Meta-Llama-3.1-8B-Instruct-sliced-18-layers.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:002c8ff4aafa8d5a4cea645f3f7eb6f9a6ded46f7bdf2601c26a09acb08c0659 +size 2959956192 diff --git a/Meta-Llama-3.1-8B-Instruct-sliced-18-layers.Q5_K_M.gguf b/Meta-Llama-3.1-8B-Instruct-sliced-18-layers.Q5_K_M.gguf new file mode 100644 index 0000000..11a0a93 --- /dev/null +++ b/Meta-Llama-3.1-8B-Instruct-sliced-18-layers.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f82c3b5982f3d9f14e7d06efcef0aae9c568e4dd83021c867a0c1f7e9807a449 +size 3574782176 diff --git a/Meta-Llama-3.1-8B-Instruct-sliced-18-layers.Q5_K_S.gguf b/Meta-Llama-3.1-8B-Instruct-sliced-18-layers.Q5_K_S.gguf new file mode 100644 index 0000000..bd7161e --- /dev/null +++ b/Meta-Llama-3.1-8B-Instruct-sliced-18-layers.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:891728db3586cb8b8534a54baef2e58c45d39190c70c8b6d094ffd3f02a32d6c +size 3499579616 diff --git a/Meta-Llama-3.1-8B-Instruct-sliced-18-layers.Q6_K.gguf b/Meta-Llama-3.1-8B-Instruct-sliced-18-layers.Q6_K.gguf new file mode 100644 index 0000000..164ab93 --- /dev/null +++ b/Meta-Llama-3.1-8B-Instruct-sliced-18-layers.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4cffa2595109be44041687c8cd22d82cbfe738925e2616e686a75be462a5678f +size 4090755296 diff --git a/Meta-Llama-3.1-8B-Instruct-sliced-18-layers.Q8_0.gguf b/Meta-Llama-3.1-8B-Instruct-sliced-18-layers.Q8_0.gguf new file mode 100644 index 0000000..88cd05d --- /dev/null +++ b/Meta-Llama-3.1-8B-Instruct-sliced-18-layers.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a5d05384fc4b8c793a68157af163dde01470d752e252ccf7df246abbf36fcab +size 5296011488 diff --git a/Meta-Llama-3.1-8B-Instruct-sliced-18-layers.f16.gguf b/Meta-Llama-3.1-8B-Instruct-sliced-18-layers.f16.gguf new file mode 100644 index 0000000..cf85774 --- /dev/null +++ b/Meta-Llama-3.1-8B-Instruct-sliced-18-layers.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18bd78c3654a32c9e3dffb0ce65cadbf006a8ac5cc2663b0cfc27e00bb606f22 +size 9961519328 diff --git a/README.md b/README.md new file mode 100644 index 0000000..239fa9c --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: maximalists/Meta-Llama-3.1-8B-Instruct-sliced-18-layers +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/maximalists/Meta-Llama-3.1-8B-Instruct-sliced-18-layers + + +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/Meta-Llama-3.1-8B-Instruct-sliced-18-layers-GGUF/resolve/main/Meta-Llama-3.1-8B-Instruct-sliced-18-layers.Q2_K.gguf) | Q2_K | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3.1-8B-Instruct-sliced-18-layers-GGUF/resolve/main/Meta-Llama-3.1-8B-Instruct-sliced-18-layers.IQ3_XS.gguf) | IQ3_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3.1-8B-Instruct-sliced-18-layers-GGUF/resolve/main/Meta-Llama-3.1-8B-Instruct-sliced-18-layers.Q3_K_S.gguf) | Q3_K_S | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3.1-8B-Instruct-sliced-18-layers-GGUF/resolve/main/Meta-Llama-3.1-8B-Instruct-sliced-18-layers.IQ3_S.gguf) | IQ3_S | 2.5 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3.1-8B-Instruct-sliced-18-layers-GGUF/resolve/main/Meta-Llama-3.1-8B-Instruct-sliced-18-layers.IQ3_M.gguf) | IQ3_M | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3.1-8B-Instruct-sliced-18-layers-GGUF/resolve/main/Meta-Llama-3.1-8B-Instruct-sliced-18-layers.Q3_K_M.gguf) | Q3_K_M | 2.7 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3.1-8B-Instruct-sliced-18-layers-GGUF/resolve/main/Meta-Llama-3.1-8B-Instruct-sliced-18-layers.Q3_K_L.gguf) | Q3_K_L | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3.1-8B-Instruct-sliced-18-layers-GGUF/resolve/main/Meta-Llama-3.1-8B-Instruct-sliced-18-layers.IQ4_XS.gguf) | IQ4_XS | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3.1-8B-Instruct-sliced-18-layers-GGUF/resolve/main/Meta-Llama-3.1-8B-Instruct-sliced-18-layers.Q4_K_S.gguf) | Q4_K_S | 3.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3.1-8B-Instruct-sliced-18-layers-GGUF/resolve/main/Meta-Llama-3.1-8B-Instruct-sliced-18-layers.Q4_K_M.gguf) | Q4_K_M | 3.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3.1-8B-Instruct-sliced-18-layers-GGUF/resolve/main/Meta-Llama-3.1-8B-Instruct-sliced-18-layers.Q5_K_S.gguf) | Q5_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3.1-8B-Instruct-sliced-18-layers-GGUF/resolve/main/Meta-Llama-3.1-8B-Instruct-sliced-18-layers.Q5_K_M.gguf) | Q5_K_M | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3.1-8B-Instruct-sliced-18-layers-GGUF/resolve/main/Meta-Llama-3.1-8B-Instruct-sliced-18-layers.Q6_K.gguf) | Q6_K | 4.2 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3.1-8B-Instruct-sliced-18-layers-GGUF/resolve/main/Meta-Llama-3.1-8B-Instruct-sliced-18-layers.Q8_0.gguf) | Q8_0 | 5.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3.1-8B-Instruct-sliced-18-layers-GGUF/resolve/main/Meta-Llama-3.1-8B-Instruct-sliced-18-layers.f16.gguf) | f16 | 10.1 | 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. + +