commit 51986d939debf9fca521fe82fa754bc445d1fd24 Author: ModelHub XC Date: Fri May 1 22:09:34 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/L3.1-Aspire-Heart-Matrix-8B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..7cba0b1 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,48 @@ +*.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 +L3.1-Aspire-Heart-Matrix-8B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Aspire-Heart-Matrix-8B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Aspire-Heart-Matrix-8B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Aspire-Heart-Matrix-8B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Aspire-Heart-Matrix-8B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Aspire-Heart-Matrix-8B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Aspire-Heart-Matrix-8B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Aspire-Heart-Matrix-8B.f16.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Aspire-Heart-Matrix-8B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Aspire-Heart-Matrix-8B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Aspire-Heart-Matrix-8B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Aspire-Heart-Matrix-8B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-Aspire-Heart-Matrix-8B.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/L3.1-Aspire-Heart-Matrix-8B.IQ4_XS.gguf b/L3.1-Aspire-Heart-Matrix-8B.IQ4_XS.gguf new file mode 100644 index 0000000..367ba33 --- /dev/null +++ b/L3.1-Aspire-Heart-Matrix-8B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bab515e5bca0d3a9ce71c7fe7e209da5e5acd1c78bd26545ce6408ed003373c8 +size 4484363904 diff --git a/L3.1-Aspire-Heart-Matrix-8B.Q2_K.gguf b/L3.1-Aspire-Heart-Matrix-8B.Q2_K.gguf new file mode 100644 index 0000000..1aca036 --- /dev/null +++ b/L3.1-Aspire-Heart-Matrix-8B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8dcae1e507b680c82c7011a8b7c6a055e298529b53f28644f11b3be3db2fe764 +size 3179132544 diff --git a/L3.1-Aspire-Heart-Matrix-8B.Q3_K_L.gguf b/L3.1-Aspire-Heart-Matrix-8B.Q3_K_L.gguf new file mode 100644 index 0000000..2e01fd8 --- /dev/null +++ b/L3.1-Aspire-Heart-Matrix-8B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b804ed8c80bb11dfde24dce85937c2de55dc5d68eabacc4295d2c2b09fdbc33 +size 4321957504 diff --git a/L3.1-Aspire-Heart-Matrix-8B.Q3_K_M.gguf b/L3.1-Aspire-Heart-Matrix-8B.Q3_K_M.gguf new file mode 100644 index 0000000..abcb02f --- /dev/null +++ b/L3.1-Aspire-Heart-Matrix-8B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e0435fa9340c4d2347f8be26c7280c8fe7cfd95a49df9d0ff26fd5780d89b7b +size 4018919040 diff --git a/L3.1-Aspire-Heart-Matrix-8B.Q3_K_S.gguf b/L3.1-Aspire-Heart-Matrix-8B.Q3_K_S.gguf new file mode 100644 index 0000000..7607097 --- /dev/null +++ b/L3.1-Aspire-Heart-Matrix-8B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce3fdad5545065c555f6b8da1b2ae8ecb92b4ac39d8f64c9e88a81f932bd9f95 +size 3664500352 diff --git a/L3.1-Aspire-Heart-Matrix-8B.Q4_0_4_4.gguf b/L3.1-Aspire-Heart-Matrix-8B.Q4_0_4_4.gguf new file mode 100644 index 0000000..871c050 --- /dev/null +++ b/L3.1-Aspire-Heart-Matrix-8B.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3652a27266d0729b23200e5bbeeb25bd145d8afeed525ec1d050ab6762ebbce +size 4661212800 diff --git a/L3.1-Aspire-Heart-Matrix-8B.Q4_K_M.gguf b/L3.1-Aspire-Heart-Matrix-8B.Q4_K_M.gguf new file mode 100644 index 0000000..c477214 --- /dev/null +++ b/L3.1-Aspire-Heart-Matrix-8B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d90abaae59f39e8f04548151265dce3b9c913303e6755860f5d28dd5cfc2d86 +size 4920735360 diff --git a/L3.1-Aspire-Heart-Matrix-8B.Q4_K_S.gguf b/L3.1-Aspire-Heart-Matrix-8B.Q4_K_S.gguf new file mode 100644 index 0000000..f255ce2 --- /dev/null +++ b/L3.1-Aspire-Heart-Matrix-8B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:996b726a5afa6cd3faab90c722c6ebcf203a171dcfbe66ba2a2a46c23e1a6cb6 +size 4692670080 diff --git a/L3.1-Aspire-Heart-Matrix-8B.Q5_K_M.gguf b/L3.1-Aspire-Heart-Matrix-8B.Q5_K_M.gguf new file mode 100644 index 0000000..6b587c3 --- /dev/null +++ b/L3.1-Aspire-Heart-Matrix-8B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:043eacc8c597173ed4bf172bf960137f851eea087a474376f77b204f268c7d5c +size 5732988544 diff --git a/L3.1-Aspire-Heart-Matrix-8B.Q5_K_S.gguf b/L3.1-Aspire-Heart-Matrix-8B.Q5_K_S.gguf new file mode 100644 index 0000000..9e30c55 --- /dev/null +++ b/L3.1-Aspire-Heart-Matrix-8B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c5fdec51ee511f603f37a10a52addad6b722636224642518e071b7a3dad188f +size 5599295104 diff --git a/L3.1-Aspire-Heart-Matrix-8B.Q6_K.gguf b/L3.1-Aspire-Heart-Matrix-8B.Q6_K.gguf new file mode 100644 index 0000000..2affc32 --- /dev/null +++ b/L3.1-Aspire-Heart-Matrix-8B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b76d1cd6b477a7c801494814b3463bdb30d76a0e86933a3b81069b415cce7b7d +size 6596007552 diff --git a/L3.1-Aspire-Heart-Matrix-8B.Q8_0.gguf b/L3.1-Aspire-Heart-Matrix-8B.Q8_0.gguf new file mode 100644 index 0000000..7ecd738 --- /dev/null +++ b/L3.1-Aspire-Heart-Matrix-8B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28a71c91a724e6a482c20ae4943c1861cf7f5ff75abcab525222a4ed08e1de4e +size 8540771968 diff --git a/L3.1-Aspire-Heart-Matrix-8B.f16.gguf b/L3.1-Aspire-Heart-Matrix-8B.f16.gguf new file mode 100644 index 0000000..e9b5f29 --- /dev/null +++ b/L3.1-Aspire-Heart-Matrix-8B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78e82c83ef64cdb2b677eebc262522f83e06343a9b1351d4b7e1344caa437c91 +size 16068892288 diff --git a/README.md b/README.md new file mode 100644 index 0000000..549c4f8 --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: ZeroXClem/L3-Aspire-Heart-Matrix-8B +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- merge +- mergekit +- lazymergekit +- vllm +- bfloat16 +- llama +--- +## About + + + + + + +static quants of https://huggingface.co/ZeroXClem/L3-Aspire-Heart-Matrix-8B + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/L3.1-Aspire-Heart-Matrix-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/L3.1-Aspire-Heart-Matrix-8B-GGUF/resolve/main/L3.1-Aspire-Heart-Matrix-8B.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Aspire-Heart-Matrix-8B-GGUF/resolve/main/L3.1-Aspire-Heart-Matrix-8B.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Aspire-Heart-Matrix-8B-GGUF/resolve/main/L3.1-Aspire-Heart-Matrix-8B.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Aspire-Heart-Matrix-8B-GGUF/resolve/main/L3.1-Aspire-Heart-Matrix-8B.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Aspire-Heart-Matrix-8B-GGUF/resolve/main/L3.1-Aspire-Heart-Matrix-8B.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Aspire-Heart-Matrix-8B-GGUF/resolve/main/L3.1-Aspire-Heart-Matrix-8B.Q4_0_4_4.gguf) | Q4_0_4_4 | 4.8 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Aspire-Heart-Matrix-8B-GGUF/resolve/main/L3.1-Aspire-Heart-Matrix-8B.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Aspire-Heart-Matrix-8B-GGUF/resolve/main/L3.1-Aspire-Heart-Matrix-8B.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Aspire-Heart-Matrix-8B-GGUF/resolve/main/L3.1-Aspire-Heart-Matrix-8B.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Aspire-Heart-Matrix-8B-GGUF/resolve/main/L3.1-Aspire-Heart-Matrix-8B.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Aspire-Heart-Matrix-8B-GGUF/resolve/main/L3.1-Aspire-Heart-Matrix-8B.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Aspire-Heart-Matrix-8B-GGUF/resolve/main/L3.1-Aspire-Heart-Matrix-8B.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/L3.1-Aspire-Heart-Matrix-8B-GGUF/resolve/main/L3.1-Aspire-Heart-Matrix-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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. + +