commit 25ec22533ea75560530c919bddfca8f7111c6915 Author: ModelHub XC Date: Mon Jul 6 18:23:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/AetherLlama-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f873907 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,47 @@ +*.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 +AetherLlama.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +AetherLlama.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +AetherLlama.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +AetherLlama.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +AetherLlama.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +AetherLlama.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +AetherLlama.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +AetherLlama.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +AetherLlama.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +AetherLlama.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +AetherLlama.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +AetherLlama.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/AetherLlama.IQ4_XS.gguf b/AetherLlama.IQ4_XS.gguf new file mode 100644 index 0000000..4a92451 --- /dev/null +++ b/AetherLlama.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9868d81677653d6f8c3bd11156fcee86edc16eb5e2582a5e7e4c857f2f6c31cb +size 4484372928 diff --git a/AetherLlama.Q2_K.gguf b/AetherLlama.Q2_K.gguf new file mode 100644 index 0000000..de69833 --- /dev/null +++ b/AetherLlama.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb0f81f929b22f9bf1fb11bf5c756c22a7d3c5f32680ac311a4751bce6fdaeec +size 3179141568 diff --git a/AetherLlama.Q3_K_L.gguf b/AetherLlama.Q3_K_L.gguf new file mode 100644 index 0000000..31777fb --- /dev/null +++ b/AetherLlama.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c59f9ffdb85f4cb6b6fc5339f8b77bbf961f00b993582f8c23abe783e73eadb3 +size 4321966528 diff --git a/AetherLlama.Q3_K_M.gguf b/AetherLlama.Q3_K_M.gguf new file mode 100644 index 0000000..01ea870 --- /dev/null +++ b/AetherLlama.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3bb38930a29a7db3610626f3ba166836f3fa09c66196a847d4c8e14eb9c0339 +size 4018928064 diff --git a/AetherLlama.Q3_K_S.gguf b/AetherLlama.Q3_K_S.gguf new file mode 100644 index 0000000..329c0aa --- /dev/null +++ b/AetherLlama.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0798931799e9b0d8d6b11239a7de47524ea689ea5cd87f8b9b2a3f8bacbec19 +size 3664509376 diff --git a/AetherLlama.Q4_K_M.gguf b/AetherLlama.Q4_K_M.gguf new file mode 100644 index 0000000..82a5f9a --- /dev/null +++ b/AetherLlama.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21f7e986ddc83a82b94a74e3001c294960b15103abdacc1260e347732fcd7830 +size 4920744384 diff --git a/AetherLlama.Q4_K_S.gguf b/AetherLlama.Q4_K_S.gguf new file mode 100644 index 0000000..4235b99 --- /dev/null +++ b/AetherLlama.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:354f48006a2fed843340d9d13ab71ea466ab7170f6010794a40a1fdac10b24d5 +size 4692679104 diff --git a/AetherLlama.Q5_K_M.gguf b/AetherLlama.Q5_K_M.gguf new file mode 100644 index 0000000..b66d531 --- /dev/null +++ b/AetherLlama.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8b67be341fe380d06157811f67073bf759afcd5aad1394f2055b8ccfe20044d +size 5732997568 diff --git a/AetherLlama.Q5_K_S.gguf b/AetherLlama.Q5_K_S.gguf new file mode 100644 index 0000000..72cb3b1 --- /dev/null +++ b/AetherLlama.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7846eff04e440ac7ce8cfc6e5cd281cbb95a2eefd9b8a65ee16a0db7bb11188 +size 5599304128 diff --git a/AetherLlama.Q6_K.gguf b/AetherLlama.Q6_K.gguf new file mode 100644 index 0000000..c8c1f0e --- /dev/null +++ b/AetherLlama.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28f7d9facb45f5928c769505c79b16cead83eccc78f1ad936ea16d9c583bfebe +size 6596016576 diff --git a/AetherLlama.Q8_0.gguf b/AetherLlama.Q8_0.gguf new file mode 100644 index 0000000..b9ba43e --- /dev/null +++ b/AetherLlama.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1670883d823e995d222eb0ea8e07d3c282d245847cfc7e010cb8fd9b0ef467c +size 8540780992 diff --git a/AetherLlama.f16.gguf b/AetherLlama.f16.gguf new file mode 100644 index 0000000..9993a58 --- /dev/null +++ b/AetherLlama.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6754e280bc81d06fcb40ee0d2db9a96f8abaeea36094a649be22ce0537a2949b +size 16068901312 diff --git a/README.md b/README.md new file mode 100644 index 0000000..0287540 --- /dev/null +++ b/README.md @@ -0,0 +1,74 @@ +--- +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 + + + + + + +static quants of https://huggingface.co/Daemontatox/AetherLlama + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/AetherLlama-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/AetherLlama-GGUF/resolve/main/AetherLlama.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/AetherLlama-GGUF/resolve/main/AetherLlama.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/AetherLlama-GGUF/resolve/main/AetherLlama.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/AetherLlama-GGUF/resolve/main/AetherLlama.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/AetherLlama-GGUF/resolve/main/AetherLlama.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/AetherLlama-GGUF/resolve/main/AetherLlama.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/AetherLlama-GGUF/resolve/main/AetherLlama.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/AetherLlama-GGUF/resolve/main/AetherLlama.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/AetherLlama-GGUF/resolve/main/AetherLlama.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/AetherLlama-GGUF/resolve/main/AetherLlama.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/AetherLlama-GGUF/resolve/main/AetherLlama.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/AetherLlama-GGUF/resolve/main/AetherLlama.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. + +