commit c812d56b9b4151364b701b74c16c3bca1a1af341 Author: ModelHub XC Date: Sun Jun 21 00:08:19 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/AwareAILabs-v0-3-8B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..16aaffc --- /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 +AwareAILabs-v0-3-8B.f16.gguf filter=lfs diff=lfs merge=lfs -text +AwareAILabs-v0-3-8B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +AwareAILabs-v0-3-8B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +AwareAILabs-v0-3-8B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +AwareAILabs-v0-3-8B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +AwareAILabs-v0-3-8B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +AwareAILabs-v0-3-8B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +AwareAILabs-v0-3-8B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +AwareAILabs-v0-3-8B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +AwareAILabs-v0-3-8B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +AwareAILabs-v0-3-8B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +AwareAILabs-v0-3-8B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/AwareAILabs-v0-3-8B.IQ4_XS.gguf b/AwareAILabs-v0-3-8B.IQ4_XS.gguf new file mode 100644 index 0000000..01a0dd6 --- /dev/null +++ b/AwareAILabs-v0-3-8B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d9a22afd5023d6a22fe291d9abad11ff5ab6fee8cbba8157b6d5d3f178f8118 +size 4484374208 diff --git a/AwareAILabs-v0-3-8B.Q2_K.gguf b/AwareAILabs-v0-3-8B.Q2_K.gguf new file mode 100644 index 0000000..827041e --- /dev/null +++ b/AwareAILabs-v0-3-8B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ff89fd954bd45ffa27f98951c24b609c068969633208d30d265b78133ee0957 +size 3179141184 diff --git a/AwareAILabs-v0-3-8B.Q3_K_L.gguf b/AwareAILabs-v0-3-8B.Q3_K_L.gguf new file mode 100644 index 0000000..178f67e --- /dev/null +++ b/AwareAILabs-v0-3-8B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25bbe071b0785d320a5b19dec5cbc4066a96dd05e2b377e454afb889d389877a +size 4321966976 diff --git a/AwareAILabs-v0-3-8B.Q3_K_M.gguf b/AwareAILabs-v0-3-8B.Q3_K_M.gguf new file mode 100644 index 0000000..3d6ec9d --- /dev/null +++ b/AwareAILabs-v0-3-8B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e7fb642df1ec7c283e826ccca42e66bfe6f9e35c0168d324c9fa087ccf02cb3 +size 4018928512 diff --git a/AwareAILabs-v0-3-8B.Q3_K_S.gguf b/AwareAILabs-v0-3-8B.Q3_K_S.gguf new file mode 100644 index 0000000..07a8668 --- /dev/null +++ b/AwareAILabs-v0-3-8B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5c9d5810185d560d2861637588e85aaff86db7fd40a2219eb063640e906f296 +size 3664509824 diff --git a/AwareAILabs-v0-3-8B.Q4_K_M.gguf b/AwareAILabs-v0-3-8B.Q4_K_M.gguf new file mode 100644 index 0000000..8406516 --- /dev/null +++ b/AwareAILabs-v0-3-8B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8ea1db2995b3128f3eb9794cd0378d0d1984d8571c4dc637955ab184812f1e2 +size 4920745920 diff --git a/AwareAILabs-v0-3-8B.Q4_K_S.gguf b/AwareAILabs-v0-3-8B.Q4_K_S.gguf new file mode 100644 index 0000000..82ddbf1 --- /dev/null +++ b/AwareAILabs-v0-3-8B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43c182dcc3ef8c5ab023a59faf2b701ec857462fb77d711f21d0cc6672708216 +size 4692680640 diff --git a/AwareAILabs-v0-3-8B.Q5_K_M.gguf b/AwareAILabs-v0-3-8B.Q5_K_M.gguf new file mode 100644 index 0000000..c7bec4f --- /dev/null +++ b/AwareAILabs-v0-3-8B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2ea816384efba99d5255bff6eed29681159b4f7ae56dcb6730097bfb2fe2a55 +size 5733000128 diff --git a/AwareAILabs-v0-3-8B.Q5_K_S.gguf b/AwareAILabs-v0-3-8B.Q5_K_S.gguf new file mode 100644 index 0000000..459d1fb --- /dev/null +++ b/AwareAILabs-v0-3-8B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef194f9e6c033cd169335b78cf25797482912241f5dab30137c9a4593bc90588 +size 5599306688 diff --git a/AwareAILabs-v0-3-8B.Q6_K.gguf b/AwareAILabs-v0-3-8B.Q6_K.gguf new file mode 100644 index 0000000..e5ca56f --- /dev/null +++ b/AwareAILabs-v0-3-8B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40b962bcb84b55b0340e000f42188d7318030fcbfe54f5a6ec95203031c6d906 +size 6596020224 diff --git a/AwareAILabs-v0-3-8B.Q8_0.gguf b/AwareAILabs-v0-3-8B.Q8_0.gguf new file mode 100644 index 0000000..54488af --- /dev/null +++ b/AwareAILabs-v0-3-8B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d682427d2bffc155112607ce91c770a5e639ddb0812f6b0f9e749cb88b543a53 +size 8540788608 diff --git a/AwareAILabs-v0-3-8B.f16.gguf b/AwareAILabs-v0-3-8B.f16.gguf new file mode 100644 index 0000000..35954ed --- /dev/null +++ b/AwareAILabs-v0-3-8B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:306426a45266df9c9c1be7b35e030b771e8a2bb536eb73e440746cbdb2c9b887 +size 16068924288 diff --git a/README.md b/README.md new file mode 100644 index 0000000..4b1a59d --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: dz237/AwareAILabs-v0-3-8B +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/dz237/AwareAILabs-v0-3-8B + + +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/AwareAILabs-v0-3-8B-GGUF/resolve/main/AwareAILabs-v0-3-8B.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/AwareAILabs-v0-3-8B-GGUF/resolve/main/AwareAILabs-v0-3-8B.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/AwareAILabs-v0-3-8B-GGUF/resolve/main/AwareAILabs-v0-3-8B.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/AwareAILabs-v0-3-8B-GGUF/resolve/main/AwareAILabs-v0-3-8B.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/AwareAILabs-v0-3-8B-GGUF/resolve/main/AwareAILabs-v0-3-8B.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/AwareAILabs-v0-3-8B-GGUF/resolve/main/AwareAILabs-v0-3-8B.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/AwareAILabs-v0-3-8B-GGUF/resolve/main/AwareAILabs-v0-3-8B.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/AwareAILabs-v0-3-8B-GGUF/resolve/main/AwareAILabs-v0-3-8B.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/AwareAILabs-v0-3-8B-GGUF/resolve/main/AwareAILabs-v0-3-8B.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/AwareAILabs-v0-3-8B-GGUF/resolve/main/AwareAILabs-v0-3-8B.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/AwareAILabs-v0-3-8B-GGUF/resolve/main/AwareAILabs-v0-3-8B.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/AwareAILabs-v0-3-8B-GGUF/resolve/main/AwareAILabs-v0-3-8B.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. + +