commit 332f08055c5ac2aed582bfbaab4f933ec53d6866 Author: ModelHub XC Date: Fri Apr 10 19:56:07 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/AetherLlama-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..dab6fb3 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,59 @@ +*.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 +imatrix.dat filter=lfs diff=lfs merge=lfs -text +AetherLlama.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +AetherLlama.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +AetherLlama.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +AetherLlama.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +AetherLlama.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +AetherLlama.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +AetherLlama.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +AetherLlama.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +AetherLlama.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +AetherLlama.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +AetherLlama.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +AetherLlama.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +AetherLlama.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +AetherLlama.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +AetherLlama.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +AetherLlama.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +AetherLlama.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +AetherLlama.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +AetherLlama.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +AetherLlama.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +AetherLlama.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +AetherLlama.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +AetherLlama.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/AetherLlama.i1-IQ1_M.gguf b/AetherLlama.i1-IQ1_M.gguf new file mode 100644 index 0000000..af6ab4b --- /dev/null +++ b/AetherLlama.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3fcf21fd7d7b48805278383bd20890b39593098f2a9e35ec1a4f8df973aa9bea +size 2161982144 diff --git a/AetherLlama.i1-IQ1_S.gguf b/AetherLlama.i1-IQ1_S.gguf new file mode 100644 index 0000000..5e001ce --- /dev/null +++ b/AetherLlama.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b85ebe80fb63acaf857961a17b373e3e766c574d39efbcc775de39a91a71e486 +size 2019637952 diff --git a/AetherLlama.i1-IQ2_M.gguf b/AetherLlama.i1-IQ2_M.gguf new file mode 100644 index 0000000..887c84b --- /dev/null +++ b/AetherLlama.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f05da8c451f417ca097a13aa13ae4e9ebce019925060bb804bf26dc5040da8c5 +size 2948291264 diff --git a/AetherLlama.i1-IQ2_S.gguf b/AetherLlama.i1-IQ2_S.gguf new file mode 100644 index 0000000..bc5c71e --- /dev/null +++ b/AetherLlama.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf4291764bac9451c02fd735256b2442018437bb06a83d9dda328c6e9ff01e2c +size 2758499008 diff --git a/AetherLlama.i1-IQ2_XS.gguf b/AetherLlama.i1-IQ2_XS.gguf new file mode 100644 index 0000000..916a998 --- /dev/null +++ b/AetherLlama.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:385cbbf3e2a2860952ba555984311a51fcb6ca992cdac08b44830275f29eef80 +size 2605791936 diff --git a/AetherLlama.i1-IQ2_XXS.gguf b/AetherLlama.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..ae7eb42 --- /dev/null +++ b/AetherLlama.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b58440142206d984f93b6ea13ddd19489d23fea973293c7e1e6fa70fe4ce4085 +size 2399222464 diff --git a/AetherLlama.i1-IQ3_M.gguf b/AetherLlama.i1-IQ3_M.gguf new file mode 100644 index 0000000..fb7e668 --- /dev/null +++ b/AetherLlama.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc769280d6e78b240e2e079f5c83b97adae60f72882347776b9a2336f893e865 +size 3784833728 diff --git a/AetherLlama.i1-IQ3_S.gguf b/AetherLlama.i1-IQ3_S.gguf new file mode 100644 index 0000000..bdb0ee9 --- /dev/null +++ b/AetherLlama.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b9281fc7dd4ebb7ef37df8240339345da9f1e193d4318a500712afa06466171 +size 3682335424 diff --git a/AetherLlama.i1-IQ3_XS.gguf b/AetherLlama.i1-IQ3_XS.gguf new file mode 100644 index 0000000..9f6a32b --- /dev/null +++ b/AetherLlama.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81eb764c2cfdb75003b3f0010d70d4cbbe26e1f39f85be73b109653f511fd57a +size 3518757568 diff --git a/AetherLlama.i1-IQ3_XXS.gguf b/AetherLlama.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..2133618 --- /dev/null +++ b/AetherLlama.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eff5c4aaa57463242a042c7c7218e3e498a77c12dcb14056d0751dfb4b5f7619 +size 3274922688 diff --git a/AetherLlama.i1-IQ4_XS.gguf b/AetherLlama.i1-IQ4_XS.gguf new file mode 100644 index 0000000..e3c93d0 --- /dev/null +++ b/AetherLlama.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8dc6a9cf23ab7e91abf53b752074d88c01478e56c5d8b8912ca6755af43d25f +size 4447673024 diff --git a/AetherLlama.i1-Q2_K.gguf b/AetherLlama.i1-Q2_K.gguf new file mode 100644 index 0000000..4c3f314 --- /dev/null +++ b/AetherLlama.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17db59b7bcf7d253f4d7cedb7636e2a59cf9a3e34e34313a1bd7a728281dd89e +size 3179141824 diff --git a/AetherLlama.i1-Q2_K_S.gguf b/AetherLlama.i1-Q2_K_S.gguf new file mode 100644 index 0000000..548f688 --- /dev/null +++ b/AetherLlama.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ecbd8e6f38722fea5d0588775b98e2fc5a99b74beaff85d0edb4c9224d7660e2 +size 2988825280 diff --git a/AetherLlama.i1-Q3_K_L.gguf b/AetherLlama.i1-Q3_K_L.gguf new file mode 100644 index 0000000..d49951b --- /dev/null +++ b/AetherLlama.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b61c5da682b611a6a28b63ad6af57fd6b975f7678cb81a0263fd309479f3ef0a +size 4321966784 diff --git a/AetherLlama.i1-Q3_K_M.gguf b/AetherLlama.i1-Q3_K_M.gguf new file mode 100644 index 0000000..0eee525 --- /dev/null +++ b/AetherLlama.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f56254cfde1b70faf258b1159ee41593cc41a4ee45d8eae798fc06dd4fb84ec4 +size 4018928320 diff --git a/AetherLlama.i1-Q3_K_S.gguf b/AetherLlama.i1-Q3_K_S.gguf new file mode 100644 index 0000000..e3cef9d --- /dev/null +++ b/AetherLlama.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e17903c0dd5ad8baa77ed33558897806a336b69404a79e0808964aceb589078 +size 3664509632 diff --git a/AetherLlama.i1-Q4_0.gguf b/AetherLlama.i1-Q4_0.gguf new file mode 100644 index 0000000..d898bab --- /dev/null +++ b/AetherLlama.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d33695722343e48be2f987449ae6da5bea5e47253ec13eb0594ed8674ef6e6cb +size 4675902144 diff --git a/AetherLlama.i1-Q4_1.gguf b/AetherLlama.i1-Q4_1.gguf new file mode 100644 index 0000000..27f3ec1 --- /dev/null +++ b/AetherLlama.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8541e8725e5a9af84b4bf8e746001cdd0f49e97f3dacf275df9d203146d35d14 +size 5130263232 diff --git a/AetherLlama.i1-Q4_K_M.gguf b/AetherLlama.i1-Q4_K_M.gguf new file mode 100644 index 0000000..26a9e06 --- /dev/null +++ b/AetherLlama.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e2d6c070d64f8639dc111f24778b914860ebf566ea35a99108a736bbab5cb9d +size 4920744640 diff --git a/AetherLlama.i1-Q4_K_S.gguf b/AetherLlama.i1-Q4_K_S.gguf new file mode 100644 index 0000000..953cc91 --- /dev/null +++ b/AetherLlama.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8cbf7416970427d57aa93a835abc80abe2fc8658d0941129b5690affa162cec2 +size 4692679360 diff --git a/AetherLlama.i1-Q5_K_M.gguf b/AetherLlama.i1-Q5_K_M.gguf new file mode 100644 index 0000000..60ea0b7 --- /dev/null +++ b/AetherLlama.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d191dd6847594433d7559b268e72cd75cc1fc243abe5a83542ce23196a6a94d +size 5732997824 diff --git a/AetherLlama.i1-Q5_K_S.gguf b/AetherLlama.i1-Q5_K_S.gguf new file mode 100644 index 0000000..343a999 --- /dev/null +++ b/AetherLlama.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5199d79549a2898278f74f2dd22b4dd4c9eb977d9da51ff299bfbbefa654de6a +size 5599304384 diff --git a/AetherLlama.i1-Q6_K.gguf b/AetherLlama.i1-Q6_K.gguf new file mode 100644 index 0000000..bf0c82e --- /dev/null +++ b/AetherLlama.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:abc927238460327986316cc470fd52723e41383b86a2e57277d3735bd9d87613 +size 6596016832 diff --git a/README.md b/README.md new file mode 100644 index 0000000..833c5be --- /dev/null +++ b/README.md @@ -0,0 +1,85 @@ +--- +base_model: Daemontatox/AetherLlama +datasets: +- Daemontatox/LongCOT-Reason +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- Llama3 +- trl +- COT +- Reasoning +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/Daemontatox/AetherLlama + + +static quants are available at https://huggingface.co/mradermacher/AetherLlama-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/AetherLlama-i1-GGUF/resolve/main/AetherLlama.i1-IQ1_S.gguf) | i1-IQ1_S | 2.1 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/AetherLlama-i1-GGUF/resolve/main/AetherLlama.i1-IQ1_M.gguf) | i1-IQ1_M | 2.3 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/AetherLlama-i1-GGUF/resolve/main/AetherLlama.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/AetherLlama-i1-GGUF/resolve/main/AetherLlama.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/AetherLlama-i1-GGUF/resolve/main/AetherLlama.i1-IQ2_S.gguf) | i1-IQ2_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/AetherLlama-i1-GGUF/resolve/main/AetherLlama.i1-IQ2_M.gguf) | i1-IQ2_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/AetherLlama-i1-GGUF/resolve/main/AetherLlama.i1-Q2_K_S.gguf) | i1-Q2_K_S | 3.1 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/AetherLlama-i1-GGUF/resolve/main/AetherLlama.i1-Q2_K.gguf) | i1-Q2_K | 3.3 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/AetherLlama-i1-GGUF/resolve/main/AetherLlama.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/AetherLlama-i1-GGUF/resolve/main/AetherLlama.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/AetherLlama-i1-GGUF/resolve/main/AetherLlama.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.8 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/AetherLlama-i1-GGUF/resolve/main/AetherLlama.i1-IQ3_S.gguf) | i1-IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/AetherLlama-i1-GGUF/resolve/main/AetherLlama.i1-IQ3_M.gguf) | i1-IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/AetherLlama-i1-GGUF/resolve/main/AetherLlama.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.1 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/AetherLlama-i1-GGUF/resolve/main/AetherLlama.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.4 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/AetherLlama-i1-GGUF/resolve/main/AetherLlama.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/AetherLlama-i1-GGUF/resolve/main/AetherLlama.i1-Q4_0.gguf) | i1-Q4_0 | 4.8 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/AetherLlama-i1-GGUF/resolve/main/AetherLlama.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.8 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/AetherLlama-i1-GGUF/resolve/main/AetherLlama.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/AetherLlama-i1-GGUF/resolve/main/AetherLlama.i1-Q4_1.gguf) | i1-Q4_1 | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/AetherLlama-i1-GGUF/resolve/main/AetherLlama.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/AetherLlama-i1-GGUF/resolve/main/AetherLlama.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/AetherLlama-i1-GGUF/resolve/main/AetherLlama.i1-Q6_K.gguf) | i1-Q6_K | 6.7 | practically like static Q6_K | + +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. + + diff --git a/imatrix.dat b/imatrix.dat new file mode 100644 index 0000000..d7e1a30 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de1d3b5d2ba56070fa4e4c0274dd946401da9dfd820edbd75be91e54ef54f1b7 +size 4988157