commit f319e828267256dd49b0a846c2d90c8e367b6b79 Author: ModelHub XC Date: Mon Jul 13 14:33:11 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/NeuralMiLLaMa-8B-slerp-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..2979cdf --- /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 +NeuralMiLLaMa-8B-slerp.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +NeuralMiLLaMa-8B-slerp.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +NeuralMiLLaMa-8B-slerp.f16.gguf filter=lfs diff=lfs merge=lfs -text +NeuralMiLLaMa-8B-slerp.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +NeuralMiLLaMa-8B-slerp.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +NeuralMiLLaMa-8B-slerp.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +NeuralMiLLaMa-8B-slerp.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +NeuralMiLLaMa-8B-slerp.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +NeuralMiLLaMa-8B-slerp.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +NeuralMiLLaMa-8B-slerp.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +NeuralMiLLaMa-8B-slerp.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +NeuralMiLLaMa-8B-slerp.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +NeuralMiLLaMa-8B-slerp.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +NeuralMiLLaMa-8B-slerp.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +NeuralMiLLaMa-8B-slerp.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/NeuralMiLLaMa-8B-slerp.IQ3_M.gguf b/NeuralMiLLaMa-8B-slerp.IQ3_M.gguf new file mode 100644 index 0000000..64abc87 --- /dev/null +++ b/NeuralMiLLaMa-8B-slerp.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3fdcf1ff8857ce5ee345a340042abec5b58bab78068870b188f87067f6511561 +size 3784823104 diff --git a/NeuralMiLLaMa-8B-slerp.IQ3_S.gguf b/NeuralMiLLaMa-8B-slerp.IQ3_S.gguf new file mode 100644 index 0000000..1bbc5ef --- /dev/null +++ b/NeuralMiLLaMa-8B-slerp.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4a2677f36fcda01543a2daeba98e5a07066f1cd9f2234b3e2e4a01c6753d0e1 +size 3682324800 diff --git a/NeuralMiLLaMa-8B-slerp.IQ3_XS.gguf b/NeuralMiLLaMa-8B-slerp.IQ3_XS.gguf new file mode 100644 index 0000000..007b4f2 --- /dev/null +++ b/NeuralMiLLaMa-8B-slerp.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c812c2a22f5c83e2144f0ea3d1a2892848f30c3bb2eff804ce9d9c23bd218233 +size 3518746944 diff --git a/NeuralMiLLaMa-8B-slerp.IQ4_XS.gguf b/NeuralMiLLaMa-8B-slerp.IQ4_XS.gguf new file mode 100644 index 0000000..067c386 --- /dev/null +++ b/NeuralMiLLaMa-8B-slerp.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:473b191113de8c560c560ecc3b11a002e650926b8e3ab8810a8955fbc874c74d +size 4484362560 diff --git a/NeuralMiLLaMa-8B-slerp.Q2_K.gguf b/NeuralMiLLaMa-8B-slerp.Q2_K.gguf new file mode 100644 index 0000000..de4479d --- /dev/null +++ b/NeuralMiLLaMa-8B-slerp.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04bf54f9065197f57ae13bd2caaf02ae39530b36c67e81d299f6708261ef2803 +size 3179131200 diff --git a/NeuralMiLLaMa-8B-slerp.Q3_K_L.gguf b/NeuralMiLLaMa-8B-slerp.Q3_K_L.gguf new file mode 100644 index 0000000..92ff232 --- /dev/null +++ b/NeuralMiLLaMa-8B-slerp.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:490041d2e4702e316f3d782947594c6d2f9df561aca93d19aedb4a93c7b1fa71 +size 4321956160 diff --git a/NeuralMiLLaMa-8B-slerp.Q3_K_M.gguf b/NeuralMiLLaMa-8B-slerp.Q3_K_M.gguf new file mode 100644 index 0000000..1a9251c --- /dev/null +++ b/NeuralMiLLaMa-8B-slerp.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aaee3acb08da3c56afb4ad6836d2ffa002aac36d54da566449998760f31d2913 +size 4018917696 diff --git a/NeuralMiLLaMa-8B-slerp.Q3_K_S.gguf b/NeuralMiLLaMa-8B-slerp.Q3_K_S.gguf new file mode 100644 index 0000000..f586d14 --- /dev/null +++ b/NeuralMiLLaMa-8B-slerp.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d34bcf607c6db161465f81be26d8739f619010165bd5e006a1a759ac5e163406 +size 3664499008 diff --git a/NeuralMiLLaMa-8B-slerp.Q4_K_M.gguf b/NeuralMiLLaMa-8B-slerp.Q4_K_M.gguf new file mode 100644 index 0000000..8f66063 --- /dev/null +++ b/NeuralMiLLaMa-8B-slerp.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb324e32a00be1bb2b34932c1e3e12b58c366a79682200263311ec2bf128705f +size 4920734016 diff --git a/NeuralMiLLaMa-8B-slerp.Q4_K_S.gguf b/NeuralMiLLaMa-8B-slerp.Q4_K_S.gguf new file mode 100644 index 0000000..5433fb9 --- /dev/null +++ b/NeuralMiLLaMa-8B-slerp.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92c4a49e5c14d59a91135cbf55e05562c9269bdd4b7d1e615c0ef21d346e533f +size 4692668736 diff --git a/NeuralMiLLaMa-8B-slerp.Q5_K_M.gguf b/NeuralMiLLaMa-8B-slerp.Q5_K_M.gguf new file mode 100644 index 0000000..f44e496 --- /dev/null +++ b/NeuralMiLLaMa-8B-slerp.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:425ea5f10130aa308b3f0b29f8b8dc546c9344e34a3b831dda1b77b635e2dfa0 +size 5732987200 diff --git a/NeuralMiLLaMa-8B-slerp.Q5_K_S.gguf b/NeuralMiLLaMa-8B-slerp.Q5_K_S.gguf new file mode 100644 index 0000000..b778086 --- /dev/null +++ b/NeuralMiLLaMa-8B-slerp.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:874cca24913f80ba39842f7972e7d9999ed6a5dc05943cff7a2249e778306a3f +size 5599293760 diff --git a/NeuralMiLLaMa-8B-slerp.Q6_K.gguf b/NeuralMiLLaMa-8B-slerp.Q6_K.gguf new file mode 100644 index 0000000..ae1da1f --- /dev/null +++ b/NeuralMiLLaMa-8B-slerp.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70d31a4cba0c692ef1dfc90e91a41da2b3f61f84b961dcf75e076ad78ecd4d64 +size 6596006208 diff --git a/NeuralMiLLaMa-8B-slerp.Q8_0.gguf b/NeuralMiLLaMa-8B-slerp.Q8_0.gguf new file mode 100644 index 0000000..81f8b0e --- /dev/null +++ b/NeuralMiLLaMa-8B-slerp.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d86b1a84ad6080c54a8d52206b3014f1589e9e57512666d291d42090e7f27b39 +size 8540770624 diff --git a/NeuralMiLLaMa-8B-slerp.f16.gguf b/NeuralMiLLaMa-8B-slerp.f16.gguf new file mode 100644 index 0000000..a19d4b9 --- /dev/null +++ b/NeuralMiLLaMa-8B-slerp.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c290fb361a06a358b58de76e290e9f5fc6d7cf6844b101db946963a7c397f98a +size 16068890944 diff --git a/README.md b/README.md new file mode 100644 index 0000000..a2c270b --- /dev/null +++ b/README.md @@ -0,0 +1,75 @@ +--- +base_model: Kukedlc/NeuralMiLLaMa-8B-slerp +language: +- en +library_name: transformers +license: other +quantized_by: mradermacher +tags: +- merge +- mergekit +- lazymergekit +- NousResearch/Meta-Llama-3-8B-Instruct +- elinas/Llama-3-8B-Ultra-Instruct +- mlabonne/ChimeraLlama-3-8B-v3 +- nvidia/Llama3-ChatQA-1.5-8B +- Kukedlc/SmartLlama-3-8B-MS-v0.1 +--- +## About + + + + + +static quants of https://huggingface.co/Kukedlc/NeuralMiLLaMa-8B-slerp + + +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/NeuralMiLLaMa-8B-slerp-GGUF/resolve/main/NeuralMiLLaMa-8B-slerp.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/NeuralMiLLaMa-8B-slerp-GGUF/resolve/main/NeuralMiLLaMa-8B-slerp.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/NeuralMiLLaMa-8B-slerp-GGUF/resolve/main/NeuralMiLLaMa-8B-slerp.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/NeuralMiLLaMa-8B-slerp-GGUF/resolve/main/NeuralMiLLaMa-8B-slerp.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/NeuralMiLLaMa-8B-slerp-GGUF/resolve/main/NeuralMiLLaMa-8B-slerp.IQ3_M.gguf) | IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/NeuralMiLLaMa-8B-slerp-GGUF/resolve/main/NeuralMiLLaMa-8B-slerp.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/NeuralMiLLaMa-8B-slerp-GGUF/resolve/main/NeuralMiLLaMa-8B-slerp.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/NeuralMiLLaMa-8B-slerp-GGUF/resolve/main/NeuralMiLLaMa-8B-slerp.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/NeuralMiLLaMa-8B-slerp-GGUF/resolve/main/NeuralMiLLaMa-8B-slerp.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/NeuralMiLLaMa-8B-slerp-GGUF/resolve/main/NeuralMiLLaMa-8B-slerp.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/NeuralMiLLaMa-8B-slerp-GGUF/resolve/main/NeuralMiLLaMa-8B-slerp.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/NeuralMiLLaMa-8B-slerp-GGUF/resolve/main/NeuralMiLLaMa-8B-slerp.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/NeuralMiLLaMa-8B-slerp-GGUF/resolve/main/NeuralMiLLaMa-8B-slerp.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/NeuralMiLLaMa-8B-slerp-GGUF/resolve/main/NeuralMiLLaMa-8B-slerp.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/NeuralMiLLaMa-8B-slerp-GGUF/resolve/main/NeuralMiLLaMa-8B-slerp.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. + +