commit ca946987fa21a4f8f0786b50d70fedc1d94c52b7 Author: ModelHub XC Date: Sun Jun 14 05:50:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/debiased-granite-3.2-8b-instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..52bd88c --- /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 +debiased-granite-3.2-8b-instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +debiased-granite-3.2-8b-instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text +debiased-granite-3.2-8b-instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +debiased-granite-3.2-8b-instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +debiased-granite-3.2-8b-instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +debiased-granite-3.2-8b-instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +debiased-granite-3.2-8b-instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +debiased-granite-3.2-8b-instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +debiased-granite-3.2-8b-instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +debiased-granite-3.2-8b-instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +debiased-granite-3.2-8b-instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +debiased-granite-3.2-8b-instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..a6e9a62 --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: hirundo-io/debiased-granite-3.2-8b-instruct +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/hirundo-io/debiased-granite-3.2-8b-instruct + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/debiased-granite-3.2-8b-instruct-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/debiased-granite-3.2-8b-instruct-GGUF/resolve/main/debiased-granite-3.2-8b-instruct.Q2_K.gguf) | Q2_K | 3.2 | | +| [GGUF](https://huggingface.co/mradermacher/debiased-granite-3.2-8b-instruct-GGUF/resolve/main/debiased-granite-3.2-8b-instruct.Q3_K_S.gguf) | Q3_K_S | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/debiased-granite-3.2-8b-instruct-GGUF/resolve/main/debiased-granite-3.2-8b-instruct.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/debiased-granite-3.2-8b-instruct-GGUF/resolve/main/debiased-granite-3.2-8b-instruct.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/debiased-granite-3.2-8b-instruct-GGUF/resolve/main/debiased-granite-3.2-8b-instruct.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/debiased-granite-3.2-8b-instruct-GGUF/resolve/main/debiased-granite-3.2-8b-instruct.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/debiased-granite-3.2-8b-instruct-GGUF/resolve/main/debiased-granite-3.2-8b-instruct.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/debiased-granite-3.2-8b-instruct-GGUF/resolve/main/debiased-granite-3.2-8b-instruct.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/debiased-granite-3.2-8b-instruct-GGUF/resolve/main/debiased-granite-3.2-8b-instruct.Q5_K_M.gguf) | Q5_K_M | 5.9 | | +| [GGUF](https://huggingface.co/mradermacher/debiased-granite-3.2-8b-instruct-GGUF/resolve/main/debiased-granite-3.2-8b-instruct.Q6_K.gguf) | Q6_K | 6.8 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/debiased-granite-3.2-8b-instruct-GGUF/resolve/main/debiased-granite-3.2-8b-instruct.Q8_0.gguf) | Q8_0 | 8.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/debiased-granite-3.2-8b-instruct-GGUF/resolve/main/debiased-granite-3.2-8b-instruct.f16.gguf) | f16 | 16.4 | 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. + + diff --git a/debiased-granite-3.2-8b-instruct.IQ4_XS.gguf b/debiased-granite-3.2-8b-instruct.IQ4_XS.gguf new file mode 100644 index 0000000..7617555 --- /dev/null +++ b/debiased-granite-3.2-8b-instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6dfb339aa20a0a01e6527eef0b8fe764725bbbb024ca5f4cc2d7d45764cbd58b +size 4469034368 diff --git a/debiased-granite-3.2-8b-instruct.Q2_K.gguf b/debiased-granite-3.2-8b-instruct.Q2_K.gguf new file mode 100644 index 0000000..6d82056 --- /dev/null +++ b/debiased-granite-3.2-8b-instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69e1cf0d1eecca3384f457ee39ba06b8d05953b6c4dd9a39e44f536a5aba1dff +size 3103591808 diff --git a/debiased-granite-3.2-8b-instruct.Q3_K_L.gguf b/debiased-granite-3.2-8b-instruct.Q3_K_L.gguf new file mode 100644 index 0000000..0b78df1 --- /dev/null +++ b/debiased-granite-3.2-8b-instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b929af4cbfb66ef23672d51200e726871bc8d90dac7f2076ae2a74edc990de93 +size 4349431168 diff --git a/debiased-granite-3.2-8b-instruct.Q3_K_M.gguf b/debiased-granite-3.2-8b-instruct.Q3_K_M.gguf new file mode 100644 index 0000000..ba5dc7d --- /dev/null +++ b/debiased-granite-3.2-8b-instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0dbe50499dbaa6ba334d6bf836f958680442af4bb8afbe6316c7b015e74c87f +size 3996585344 diff --git a/debiased-granite-3.2-8b-instruct.Q3_K_S.gguf b/debiased-granite-3.2-8b-instruct.Q3_K_S.gguf new file mode 100644 index 0000000..a57eaf1 --- /dev/null +++ b/debiased-granite-3.2-8b-instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1562dc14808168e301ffe1f24e5fb84f8bdf8e9021339488ba5666d27d252b5 +size 3592490368 diff --git a/debiased-granite-3.2-8b-instruct.Q4_K_M.gguf b/debiased-granite-3.2-8b-instruct.Q4_K_M.gguf new file mode 100644 index 0000000..0c0eb3f --- /dev/null +++ b/debiased-granite-3.2-8b-instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:acd3f78c7f4445666cd8bb310adbeb157579fdc43d279271927249999cf799aa +size 4942859648 diff --git a/debiased-granite-3.2-8b-instruct.Q4_K_S.gguf b/debiased-granite-3.2-8b-instruct.Q4_K_S.gguf new file mode 100644 index 0000000..8d315d3 --- /dev/null +++ b/debiased-granite-3.2-8b-instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9822115bd43f35cd67174d5a8ce3a726964225d2528d44025c14d7293cedc978 +size 4685761920 diff --git a/debiased-granite-3.2-8b-instruct.Q5_K_M.gguf b/debiased-granite-3.2-8b-instruct.Q5_K_M.gguf new file mode 100644 index 0000000..21a8b99 --- /dev/null +++ b/debiased-granite-3.2-8b-instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98a6d7293e270ddaee254ad7a62f08f6a568a3e552f5e2652a8effe21c482af1 +size 5797449088 diff --git a/debiased-granite-3.2-8b-instruct.Q5_K_S.gguf b/debiased-granite-3.2-8b-instruct.Q5_K_S.gguf new file mode 100644 index 0000000..e6f7a8c --- /dev/null +++ b/debiased-granite-3.2-8b-instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9279c18036d7996b8a85a6bff954a4dcaa9fd4c7f1553c97cd854d9383c2ce6 +size 5647043968 diff --git a/debiased-granite-3.2-8b-instruct.Q6_K.gguf b/debiased-granite-3.2-8b-instruct.Q6_K.gguf new file mode 100644 index 0000000..7e4f1b2 --- /dev/null +++ b/debiased-granite-3.2-8b-instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff83aa116b2677ddf42d3d74cad29f93dca06a9d296d7ea3e9137a5f32d49a44 +size 6705450368 diff --git a/debiased-granite-3.2-8b-instruct.Q8_0.gguf b/debiased-granite-3.2-8b-instruct.Q8_0.gguf new file mode 100644 index 0000000..353b4a0 --- /dev/null +++ b/debiased-granite-3.2-8b-instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9ce894834f4e6421115839706d3f94ed53457abf481dcdea6d4e387d5ae4670 +size 8684247328 diff --git a/debiased-granite-3.2-8b-instruct.f16.gguf b/debiased-granite-3.2-8b-instruct.f16.gguf new file mode 100644 index 0000000..7ec2ad9 --- /dev/null +++ b/debiased-granite-3.2-8b-instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d62d31432f2c1a1ccf2a1295ec3491c4b4c09fa952116c4bb780c7ffb9d9f37 +size 16344106528