commit 94d4b64a4ab49f41883e91934e31b42ccf1fa1ff Author: ModelHub XC Date: Tue Jun 16 23:36:21 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/granite-8b-code-base-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..64a35bc --- /dev/null +++ b/.gitattributes @@ -0,0 +1,57 @@ +*.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 +imatrix.dat filter=lfs diff=lfs merge=lfs -text +granite-8b-code-base.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +granite-8b-code-base.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +granite-8b-code-base.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +granite-8b-code-base.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +granite-8b-code-base.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +granite-8b-code-base.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +granite-8b-code-base.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +granite-8b-code-base.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +granite-8b-code-base.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +granite-8b-code-base.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +granite-8b-code-base.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +granite-8b-code-base.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +granite-8b-code-base.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +granite-8b-code-base.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +granite-8b-code-base.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +granite-8b-code-base.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +granite-8b-code-base.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +granite-8b-code-base.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +granite-8b-code-base.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +granite-8b-code-base.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +granite-8b-code-base.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..14ad02a --- /dev/null +++ b/README.md @@ -0,0 +1,81 @@ +--- +base_model: ibm-granite/granite-8b-code-base-4k +datasets: +- codeparrot/github-code-clean +- bigcode/starcoderdata +- open-web-math/open-web-math +- math-ai/StackMathQA +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- code +- granite +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/ibm-granite/granite-8b-code-base-4k + + +static quants are available at https://huggingface.co/mradermacher/granite-8b-code-base-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/granite-8b-code-base-i1-GGUF/resolve/main/granite-8b-code-base.i1-IQ1_S.gguf) | i1-IQ1_S | 1.9 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/granite-8b-code-base-i1-GGUF/resolve/main/granite-8b-code-base.i1-IQ1_M.gguf) | i1-IQ1_M | 2.1 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/granite-8b-code-base-i1-GGUF/resolve/main/granite-8b-code-base.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/granite-8b-code-base-i1-GGUF/resolve/main/granite-8b-code-base.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/granite-8b-code-base-i1-GGUF/resolve/main/granite-8b-code-base.i1-IQ2_S.gguf) | i1-IQ2_S | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/granite-8b-code-base-i1-GGUF/resolve/main/granite-8b-code-base.i1-IQ2_M.gguf) | i1-IQ2_M | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/granite-8b-code-base-i1-GGUF/resolve/main/granite-8b-code-base.i1-Q2_K.gguf) | i1-Q2_K | 3.2 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/granite-8b-code-base-i1-GGUF/resolve/main/granite-8b-code-base.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.3 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/granite-8b-code-base-i1-GGUF/resolve/main/granite-8b-code-base.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.5 | | +| [GGUF](https://huggingface.co/mradermacher/granite-8b-code-base-i1-GGUF/resolve/main/granite-8b-code-base.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.6 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/granite-8b-code-base-i1-GGUF/resolve/main/granite-8b-code-base.i1-IQ3_S.gguf) | i1-IQ3_S | 3.7 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/granite-8b-code-base-i1-GGUF/resolve/main/granite-8b-code-base.i1-IQ3_M.gguf) | i1-IQ3_M | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/granite-8b-code-base-i1-GGUF/resolve/main/granite-8b-code-base.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.0 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/granite-8b-code-base-i1-GGUF/resolve/main/granite-8b-code-base.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.4 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/granite-8b-code-base-i1-GGUF/resolve/main/granite-8b-code-base.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/granite-8b-code-base-i1-GGUF/resolve/main/granite-8b-code-base.i1-Q4_0.gguf) | i1-Q4_0 | 4.7 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/granite-8b-code-base-i1-GGUF/resolve/main/granite-8b-code-base.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.7 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/granite-8b-code-base-i1-GGUF/resolve/main/granite-8b-code-base.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/granite-8b-code-base-i1-GGUF/resolve/main/granite-8b-code-base.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/granite-8b-code-base-i1-GGUF/resolve/main/granite-8b-code-base.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/granite-8b-code-base-i1-GGUF/resolve/main/granite-8b-code-base.i1-Q6_K.gguf) | i1-Q6_K | 6.7 | practically like static Q6_K | + +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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. + + diff --git a/granite-8b-code-base.i1-IQ1_M.gguf b/granite-8b-code-base.i1-IQ1_M.gguf new file mode 100644 index 0000000..c74be15 --- /dev/null +++ b/granite-8b-code-base.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af8066a55f13ec28f6ada2b64fe5e00b8302b1fa8931ee21851ca916bfa9ab0e +size 1966308832 diff --git a/granite-8b-code-base.i1-IQ1_S.gguf b/granite-8b-code-base.i1-IQ1_S.gguf new file mode 100644 index 0000000..bd02ae1 --- /dev/null +++ b/granite-8b-code-base.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:222a820a10bdeb5c5c6e14978c6f90acb922e0dae4563467c09effd5c47b67b1 +size 1805483488 diff --git a/granite-8b-code-base.i1-IQ2_M.gguf b/granite-8b-code-base.i1-IQ2_M.gguf new file mode 100644 index 0000000..05cc7bd --- /dev/null +++ b/granite-8b-code-base.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ba9e59df3e6ef775633221b2da1846333356fb96d5e4eb291cec36f2eb08bd7 +size 2790882784 diff --git a/granite-8b-code-base.i1-IQ2_S.gguf b/granite-8b-code-base.i1-IQ2_S.gguf new file mode 100644 index 0000000..4570c6d --- /dev/null +++ b/granite-8b-code-base.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e977bd9c63296c81e44ea4e4b08c81894a59dd3687099d904d59282c56c72c1e +size 2576448992 diff --git a/granite-8b-code-base.i1-IQ2_XS.gguf b/granite-8b-code-base.i1-IQ2_XS.gguf new file mode 100644 index 0000000..21d5885 --- /dev/null +++ b/granite-8b-code-base.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4a8f796ed887bdac4de633e662dea4a5dc18796dd306f0c17b43d5407071905 +size 2467659232 diff --git a/granite-8b-code-base.i1-IQ2_XXS.gguf b/granite-8b-code-base.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..cee9658 --- /dev/null +++ b/granite-8b-code-base.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5fc3fbe58eeb0e3c7f3de9680c78c54f9a539d67e007577b84ffd65fe9541fd +size 2234351072 diff --git a/granite-8b-code-base.i1-IQ3_M.gguf b/granite-8b-code-base.i1-IQ3_M.gguf new file mode 100644 index 0000000..331553d --- /dev/null +++ b/granite-8b-code-base.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ecf25a84dadbf4d6d5b74f9d920b2605180c1e4ff92ac499ef2d3d9039b38e0 +size 3679550944 diff --git a/granite-8b-code-base.i1-IQ3_S.gguf b/granite-8b-code-base.i1-IQ3_S.gguf new file mode 100644 index 0000000..717f82c --- /dev/null +++ b/granite-8b-code-base.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af61a60d8185177568d23edc0fc368f8657e560efc645b20607c3bbb47d7f104 +size 3568139744 diff --git a/granite-8b-code-base.i1-IQ3_XS.gguf b/granite-8b-code-base.i1-IQ3_XS.gguf new file mode 100644 index 0000000..017960c --- /dev/null +++ b/granite-8b-code-base.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8637ffcc7e56c48d8869ee70fd901c010f14a4e8b90ce2194382852a84b6fb49 +size 3384114656 diff --git a/granite-8b-code-base.i1-IQ3_XXS.gguf b/granite-8b-code-base.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..fcbc15b --- /dev/null +++ b/granite-8b-code-base.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ccc9f523ec1d2fc7f53d3dc02bdf6df65779facb93333a9b72ccf4112ac2a8d3 +size 3161554400 diff --git a/granite-8b-code-base.i1-IQ4_XS.gguf b/granite-8b-code-base.i1-IQ4_XS.gguf new file mode 100644 index 0000000..0a76959 --- /dev/null +++ b/granite-8b-code-base.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d92ede9b780f5883927daf0d9f6628f1481d0c9bc412ebdf9f4838828a72146c +size 4369120736 diff --git a/granite-8b-code-base.i1-Q2_K.gguf b/granite-8b-code-base.i1-Q2_K.gguf new file mode 100644 index 0000000..ab53304 --- /dev/null +++ b/granite-8b-code-base.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a2620d9ef5449bdabad1eebf1e426621eb61cf1f78355b69fc4f247d5d9fa40 +size 3062070752 diff --git a/granite-8b-code-base.i1-Q3_K_L.gguf b/granite-8b-code-base.i1-Q3_K_L.gguf new file mode 100644 index 0000000..0fc4347 --- /dev/null +++ b/granite-8b-code-base.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81fd2a2a4250abdb11db286631482fde16019d33c66535083c66def97d4a43c7 +size 4287725024 diff --git a/granite-8b-code-base.i1-Q3_K_M.gguf b/granite-8b-code-base.i1-Q3_K_M.gguf new file mode 100644 index 0000000..0b25913 --- /dev/null +++ b/granite-8b-code-base.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:993f508041e7abeb530a745e5d1a47c8aee76553f325016df59cd1578decbef3 +size 3944840672 diff --git a/granite-8b-code-base.i1-Q3_K_S.gguf b/granite-8b-code-base.i1-Q3_K_S.gguf new file mode 100644 index 0000000..a4cb255 --- /dev/null +++ b/granite-8b-code-base.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c5c59b7d33f24e1457aa64d81626b50e60fe7881258760d5b816cd9e0250a52 +size 3548085728 diff --git a/granite-8b-code-base.i1-Q4_0.gguf b/granite-8b-code-base.i1-Q4_0.gguf new file mode 100644 index 0000000..5b870ee --- /dev/null +++ b/granite-8b-code-base.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92acff8b685a1e08aa68d3cb68264e30b7147ed3e7b371cf2a69bc5138234524 +size 4605574624 diff --git a/granite-8b-code-base.i1-Q4_K_M.gguf b/granite-8b-code-base.i1-Q4_K_M.gguf new file mode 100644 index 0000000..a635d40 --- /dev/null +++ b/granite-8b-code-base.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4cd342742a2302e8218912213b6f4faef389093134810724e1f1a6a75668971d +size 4882857440 diff --git a/granite-8b-code-base.i1-Q4_K_S.gguf b/granite-8b-code-base.i1-Q4_K_S.gguf new file mode 100644 index 0000000..4d5c169 --- /dev/null +++ b/granite-8b-code-base.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4bdfb20927dbc4e1d38e620bc27b0c9e7f2e2f98dc855e163f4dbe975e555cc +size 4622351840 diff --git a/granite-8b-code-base.i1-Q5_K_M.gguf b/granite-8b-code-base.i1-Q5_K_M.gguf new file mode 100644 index 0000000..f2bcd45 --- /dev/null +++ b/granite-8b-code-base.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:30b16304bd01a658786e49ac1edb7e485b97d8f06ab5753bf511aa0a527122e5 +size 5722766816 diff --git a/granite-8b-code-base.i1-Q5_K_S.gguf b/granite-8b-code-base.i1-Q5_K_S.gguf new file mode 100644 index 0000000..e8854ad --- /dev/null +++ b/granite-8b-code-base.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bcd1be51db25d43ff861a65fb086b15dc8c42ad5ebe9572ff54942a524032e68 +size 5572361696 diff --git a/granite-8b-code-base.i1-Q6_K.gguf b/granite-8b-code-base.i1-Q6_K.gguf new file mode 100644 index 0000000..caf585c --- /dev/null +++ b/granite-8b-code-base.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c3350bcb30ceb8619c0ada80ad88d0dadc0651258b21edef4b6b676ffeaff04 +size 6615170528 diff --git a/imatrix.dat b/imatrix.dat new file mode 100644 index 0000000..5a6684f --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73823b7699f06d3e426aaea65057f2f751caf908e685e52ab44f4139ec22d54b +size 5611681