commit ab58cac252a46ebcad5f9a88fa73043b50cbff0d Author: ModelHub XC Date: Sun May 31 08:44:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Hakim-v2-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..5e35221 --- /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 +Hakim-v2.f16.gguf filter=lfs diff=lfs merge=lfs -text +Hakim-v2.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Hakim-v2.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Hakim-v2.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Hakim-v2.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Hakim-v2.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Hakim-v2.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Hakim-v2.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Hakim-v2.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Hakim-v2.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Hakim-v2.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Hakim-v2.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Hakim-v2.IQ4_XS.gguf b/Hakim-v2.IQ4_XS.gguf new file mode 100644 index 0000000..09616b5 --- /dev/null +++ b/Hakim-v2.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98a71f80b821f160756bf6f59c182f0d6e64ae63eef3f14f0d8b6f0351733727 +size 3915995232 diff --git a/Hakim-v2.Q2_K.gguf b/Hakim-v2.Q2_K.gguf new file mode 100644 index 0000000..e221548 --- /dev/null +++ b/Hakim-v2.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61a0eb3cfa583471bb7f8a970ee9ed54bfd9a903fd2ec1e47c115aff950f5c02 +size 2757318752 diff --git a/Hakim-v2.Q3_K_L.gguf b/Hakim-v2.Q3_K_L.gguf new file mode 100644 index 0000000..63f0af5 --- /dev/null +++ b/Hakim-v2.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e5a2fc324c82ce15cf35c80123b8aa04bfec627cfda50f5e7d83b0a735398eb +size 3601995872 diff --git a/Hakim-v2.Q3_K_M.gguf b/Hakim-v2.Q3_K_M.gguf new file mode 100644 index 0000000..9f4158d --- /dev/null +++ b/Hakim-v2.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e7f8dbb292a6314e0adfc8485c27015a6d52d9fcc4ef44ff0b95a5c1ae3d719 +size 3440908384 diff --git a/Hakim-v2.Q3_K_S.gguf b/Hakim-v2.Q3_K_S.gguf new file mode 100644 index 0000000..5957da6 --- /dev/null +++ b/Hakim-v2.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26046a749765604fa246c3272fb36e708b69fc31fd95d12e181de02d8adbd0e4 +size 3251910752 diff --git a/Hakim-v2.Q4_K_M.gguf b/Hakim-v2.Q4_K_M.gguf new file mode 100644 index 0000000..1454fca --- /dev/null +++ b/Hakim-v2.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:949efd3c6b12fa9ac150b723d7292365136e97a53ab437f13a6eadf253f69c3f +size 4237064288 diff --git a/Hakim-v2.Q4_K_S.gguf b/Hakim-v2.Q4_K_S.gguf new file mode 100644 index 0000000..625c956 --- /dev/null +++ b/Hakim-v2.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b53d462a470cc65e4add3dc1ce898f07d19c3056896b900974259e124bc0323 +size 4102707296 diff --git a/Hakim-v2.Q5_K_M.gguf b/Hakim-v2.Q5_K_M.gguf new file mode 100644 index 0000000..d76bad3 --- /dev/null +++ b/Hakim-v2.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df76819a011a3de45edac481b94948f808d705a6821e272c85d558448cbcff47 +size 4947998816 diff --git a/Hakim-v2.Q5_K_S.gguf b/Hakim-v2.Q5_K_S.gguf new file mode 100644 index 0000000..661e4ad --- /dev/null +++ b/Hakim-v2.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d05e0d8d43549c4e2fd87db0ff9a003fb0dec6d59b0b1e7f9fa6e7fce7bfcee +size 4869871712 diff --git a/Hakim-v2.Q6_K.gguf b/Hakim-v2.Q6_K.gguf new file mode 100644 index 0000000..d06a535 --- /dev/null +++ b/Hakim-v2.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68a46abf4cfdccab5be6a0911ea61a0de8b0d722bd3e1a93a29fd7f8b5c11f5d +size 5703366752 diff --git a/Hakim-v2.Q8_0.gguf b/Hakim-v2.Q8_0.gguf new file mode 100644 index 0000000..33ce4e7 --- /dev/null +++ b/Hakim-v2.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a04359ade5224d181886a2629bfef5a8d70b2c9cd8827afbbe1ca99d7f57e624 +size 7353292896 diff --git a/Hakim-v2.f16.gguf b/Hakim-v2.f16.gguf new file mode 100644 index 0000000..459c64c --- /dev/null +++ b/Hakim-v2.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6eb057b23ed2996fa6704a904ee0c11c92bb0bbb5ddd52faa32a79afe1b0f7f +size 13740103776 diff --git a/README.md b/README.md new file mode 100644 index 0000000..0a950ab --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +base_model: Rabe3/Hakim-v2 +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- gemma3n +--- +## About + + + + + + + + + +static quants of https://huggingface.co/Rabe3/Hakim-v2 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Hakim-v2-GGUF).*** + +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/Hakim-v2-GGUF/resolve/main/Hakim-v2.Q2_K.gguf) | Q2_K | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Hakim-v2-GGUF/resolve/main/Hakim-v2.Q3_K_S.gguf) | Q3_K_S | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/Hakim-v2-GGUF/resolve/main/Hakim-v2.Q3_K_M.gguf) | Q3_K_M | 3.5 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Hakim-v2-GGUF/resolve/main/Hakim-v2.Q3_K_L.gguf) | Q3_K_L | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/Hakim-v2-GGUF/resolve/main/Hakim-v2.IQ4_XS.gguf) | IQ4_XS | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/Hakim-v2-GGUF/resolve/main/Hakim-v2.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Hakim-v2-GGUF/resolve/main/Hakim-v2.Q4_K_M.gguf) | Q4_K_M | 4.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Hakim-v2-GGUF/resolve/main/Hakim-v2.Q5_K_S.gguf) | Q5_K_S | 5.0 | | +| [GGUF](https://huggingface.co/mradermacher/Hakim-v2-GGUF/resolve/main/Hakim-v2.Q5_K_M.gguf) | Q5_K_M | 5.0 | | +| [GGUF](https://huggingface.co/mradermacher/Hakim-v2-GGUF/resolve/main/Hakim-v2.Q6_K.gguf) | Q6_K | 5.8 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Hakim-v2-GGUF/resolve/main/Hakim-v2.Q8_0.gguf) | Q8_0 | 7.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Hakim-v2-GGUF/resolve/main/Hakim-v2.f16.gguf) | f16 | 13.8 | 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. + +