commit ef2599b0598ad6a32047e9fd1b3f4d070ca7bc1a Author: ModelHub XC Date: Mon May 25 07:02:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Q3-8B-Kintsugi-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..ee4cba7 --- /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 +Q3-8B-Kintsugi.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Q3-8B-Kintsugi.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Q3-8B-Kintsugi.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Q3-8B-Kintsugi.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Q3-8B-Kintsugi.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Q3-8B-Kintsugi.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Q3-8B-Kintsugi.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Q3-8B-Kintsugi.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Q3-8B-Kintsugi.f16.gguf filter=lfs diff=lfs merge=lfs -text +Q3-8B-Kintsugi.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Q3-8B-Kintsugi.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Q3-8B-Kintsugi.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Q3-8B-Kintsugi.IQ4_XS.gguf b/Q3-8B-Kintsugi.IQ4_XS.gguf new file mode 100644 index 0000000..5b9d08c --- /dev/null +++ b/Q3-8B-Kintsugi.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f81679975f62f417ebc1229d711e23f442cb5fa29c835781cd6a84261338d32 +size 4593296928 diff --git a/Q3-8B-Kintsugi.Q2_K.gguf b/Q3-8B-Kintsugi.Q2_K.gguf new file mode 100644 index 0000000..7e64fea --- /dev/null +++ b/Q3-8B-Kintsugi.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d84e5dc4f7e9b0597bd0b70dabf48ad85caa2d865597a636c9456113f44b73bf +size 3281733152 diff --git a/Q3-8B-Kintsugi.Q3_K_L.gguf b/Q3-8B-Kintsugi.Q3_K_L.gguf new file mode 100644 index 0000000..6bf3f76 --- /dev/null +++ b/Q3-8B-Kintsugi.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2cbfdfc0000574ec3193de84c88bb6b7c0c8fa5e0a1414c2cd87ad56d5547c20 +size 4431394336 diff --git a/Q3-8B-Kintsugi.Q3_K_M.gguf b/Q3-8B-Kintsugi.Q3_K_M.gguf new file mode 100644 index 0000000..0cc3bf0 --- /dev/null +++ b/Q3-8B-Kintsugi.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb890fcc4226ef0ba8017e26c5182f0113de8cee74600cd66794e1dfe8d1959f +size 4124161568 diff --git a/Q3-8B-Kintsugi.Q3_K_S.gguf b/Q3-8B-Kintsugi.Q3_K_S.gguf new file mode 100644 index 0000000..0881387 --- /dev/null +++ b/Q3-8B-Kintsugi.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8cf252fd06e3fd4a3c81db42c32a6f04d155b6524e05bc4d38a71c001a68ffa7 +size 3769611808 diff --git a/Q3-8B-Kintsugi.Q4_K_M.gguf b/Q3-8B-Kintsugi.Q4_K_M.gguf new file mode 100644 index 0000000..2794876 --- /dev/null +++ b/Q3-8B-Kintsugi.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:321bf336aabde963637b280c4df3b176557114a8155104fd8a3aec109d060c2d +size 5027784224 diff --git a/Q3-8B-Kintsugi.Q4_K_S.gguf b/Q3-8B-Kintsugi.Q4_K_S.gguf new file mode 100644 index 0000000..0198d66 --- /dev/null +++ b/Q3-8B-Kintsugi.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c14e69912a7a8bd6a308d3a5244e8a4f9e1b5c85fe5725c92e37ca04afb4655a +size 4802012704 diff --git a/Q3-8B-Kintsugi.Q5_K_M.gguf b/Q3-8B-Kintsugi.Q5_K_M.gguf new file mode 100644 index 0000000..09255d7 --- /dev/null +++ b/Q3-8B-Kintsugi.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34a1fb5ac189e1e64bdb317c4bb1f9a44fd7fe9eb95d533b12674a75bee15aca +size 5851112992 diff --git a/Q3-8B-Kintsugi.Q5_K_S.gguf b/Q3-8B-Kintsugi.Q5_K_S.gguf new file mode 100644 index 0000000..7da4d57 --- /dev/null +++ b/Q3-8B-Kintsugi.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a619b3bc78bbfc71e2e88353211f3fcf2c97363304c666ce1b63e94d3a7895a7 +size 5720761888 diff --git a/Q3-8B-Kintsugi.Q6_K.gguf b/Q3-8B-Kintsugi.Q6_K.gguf new file mode 100644 index 0000000..8c546ea --- /dev/null +++ b/Q3-8B-Kintsugi.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c722de8b9b92a1dbaf0d9967d89ddd9ee990541cb8d5e9f7bf478cfac0957443 +size 6725899808 diff --git a/Q3-8B-Kintsugi.Q8_0.gguf b/Q3-8B-Kintsugi.Q8_0.gguf new file mode 100644 index 0000000..d26d98e --- /dev/null +++ b/Q3-8B-Kintsugi.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ee3f5e3902b1f97fdec341dcc3963fbf0c13e0fc50b54d1bccc87dbb8f5c432 +size 8709518880 diff --git a/Q3-8B-Kintsugi.f16.gguf b/Q3-8B-Kintsugi.f16.gguf new file mode 100644 index 0000000..be1ae8c --- /dev/null +++ b/Q3-8B-Kintsugi.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fdb8c8501d70d068d0f845ad6cbf1771c3bd53db55c90905e19df0952cc7ad52 +size 16388044320 diff --git a/README.md b/README.md new file mode 100644 index 0000000..16d9cbb --- /dev/null +++ b/README.md @@ -0,0 +1,94 @@ +--- +base_model: allura-org/Q3-8B-Kintsugi +datasets: +- PygmalionAI/PIPPA +- Alfitaria/nemotron-ultra-reasoning-synthkink +- PocketDoc/Dans-Prosemaxx-Gutenberg +- FreedomIntelligence/Medical-R1-Distill-Data +- cognitivecomputations/SystemChat-2.0 +- allenai/tulu-3-sft-personas-instruction-following +- kalomaze/Opus_Instruct_25k +- simplescaling/s1K-claude-3-7-sonnet +- ai2-adapt-dev/flan_v2_converted +- grimulkan/theory-of-mind +- grimulkan/physical-reasoning +- nvidia/HelpSteer3 +- nbeerbower/gutenberg2-dpo +- nbeerbower/gutenberg-moderne-dpo +- nbeerbower/Purpura-DPO +- antiven0m/physical-reasoning-dpo +- allenai/tulu-3-IF-augmented-on-policy-70b +- NobodyExistsOnTheInternet/system-message-DPO +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- mergekit +- axolotl +- unsloth +- roleplay +- conversational +--- +## About + + + + + + +static quants of https://huggingface.co/allura-org/Q3-8B-Kintsugi + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Q3-8B-Kintsugi-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Q3-8B-Kintsugi-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/Q3-8B-Kintsugi-GGUF/resolve/main/Q3-8B-Kintsugi.Q2_K.gguf) | Q2_K | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/Q3-8B-Kintsugi-GGUF/resolve/main/Q3-8B-Kintsugi.Q3_K_S.gguf) | Q3_K_S | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Q3-8B-Kintsugi-GGUF/resolve/main/Q3-8B-Kintsugi.Q3_K_M.gguf) | Q3_K_M | 4.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Q3-8B-Kintsugi-GGUF/resolve/main/Q3-8B-Kintsugi.Q3_K_L.gguf) | Q3_K_L | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/Q3-8B-Kintsugi-GGUF/resolve/main/Q3-8B-Kintsugi.IQ4_XS.gguf) | IQ4_XS | 4.7 | | +| [GGUF](https://huggingface.co/mradermacher/Q3-8B-Kintsugi-GGUF/resolve/main/Q3-8B-Kintsugi.Q4_K_S.gguf) | Q4_K_S | 4.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Q3-8B-Kintsugi-GGUF/resolve/main/Q3-8B-Kintsugi.Q4_K_M.gguf) | Q4_K_M | 5.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Q3-8B-Kintsugi-GGUF/resolve/main/Q3-8B-Kintsugi.Q5_K_S.gguf) | Q5_K_S | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Q3-8B-Kintsugi-GGUF/resolve/main/Q3-8B-Kintsugi.Q5_K_M.gguf) | Q5_K_M | 6.0 | | +| [GGUF](https://huggingface.co/mradermacher/Q3-8B-Kintsugi-GGUF/resolve/main/Q3-8B-Kintsugi.Q6_K.gguf) | Q6_K | 6.8 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Q3-8B-Kintsugi-GGUF/resolve/main/Q3-8B-Kintsugi.Q8_0.gguf) | Q8_0 | 8.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Q3-8B-Kintsugi-GGUF/resolve/main/Q3-8B-Kintsugi.f16.gguf) | f16 | 16.5 | 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. + +