commit b46eb7348428a42ff66be9ae54e67bee55447a18 Author: ModelHub XC Date: Tue Jun 16 20:46:19 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: mradermacher/granite-3b-code-base-128k-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..ccf3b8c --- /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-3b-code-base-128k.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +granite-3b-code-base-128k.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +granite-3b-code-base-128k.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +granite-3b-code-base-128k.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +granite-3b-code-base-128k.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +granite-3b-code-base-128k.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +granite-3b-code-base-128k.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +granite-3b-code-base-128k.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +granite-3b-code-base-128k.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +granite-3b-code-base-128k.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +granite-3b-code-base-128k.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +granite-3b-code-base-128k.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +granite-3b-code-base-128k.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +granite-3b-code-base-128k.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +granite-3b-code-base-128k.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +granite-3b-code-base-128k.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +granite-3b-code-base-128k.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +granite-3b-code-base-128k.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +granite-3b-code-base-128k.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +granite-3b-code-base-128k.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +granite-3b-code-base-128k.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..a594220 --- /dev/null +++ b/README.md @@ -0,0 +1,81 @@ +--- +base_model: ibm-granite/granite-3b-code-base-128k +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-3b-code-base-128k + + +static quants are available at https://huggingface.co/mradermacher/granite-3b-code-base-128k-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-3b-code-base-128k-i1-GGUF/resolve/main/granite-3b-code-base-128k.i1-IQ1_S.gguf) | i1-IQ1_S | 0.9 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/granite-3b-code-base-128k-i1-GGUF/resolve/main/granite-3b-code-base-128k.i1-IQ1_M.gguf) | i1-IQ1_M | 1.0 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/granite-3b-code-base-128k-i1-GGUF/resolve/main/granite-3b-code-base-128k.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/granite-3b-code-base-128k-i1-GGUF/resolve/main/granite-3b-code-base-128k.i1-IQ2_XS.gguf) | i1-IQ2_XS | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/granite-3b-code-base-128k-i1-GGUF/resolve/main/granite-3b-code-base-128k.i1-IQ2_S.gguf) | i1-IQ2_S | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/granite-3b-code-base-128k-i1-GGUF/resolve/main/granite-3b-code-base-128k.i1-IQ2_M.gguf) | i1-IQ2_M | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/granite-3b-code-base-128k-i1-GGUF/resolve/main/granite-3b-code-base-128k.i1-Q2_K.gguf) | i1-Q2_K | 1.4 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/granite-3b-code-base-128k-i1-GGUF/resolve/main/granite-3b-code-base-128k.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 1.5 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/granite-3b-code-base-128k-i1-GGUF/resolve/main/granite-3b-code-base-128k.i1-IQ3_XS.gguf) | i1-IQ3_XS | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/granite-3b-code-base-128k-i1-GGUF/resolve/main/granite-3b-code-base-128k.i1-IQ3_S.gguf) | i1-IQ3_S | 1.7 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/granite-3b-code-base-128k-i1-GGUF/resolve/main/granite-3b-code-base-128k.i1-Q3_K_S.gguf) | i1-Q3_K_S | 1.7 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/granite-3b-code-base-128k-i1-GGUF/resolve/main/granite-3b-code-base-128k.i1-IQ3_M.gguf) | i1-IQ3_M | 1.7 | | +| [GGUF](https://huggingface.co/mradermacher/granite-3b-code-base-128k-i1-GGUF/resolve/main/granite-3b-code-base-128k.i1-Q3_K_M.gguf) | i1-Q3_K_M | 1.8 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/granite-3b-code-base-128k-i1-GGUF/resolve/main/granite-3b-code-base-128k.i1-Q3_K_L.gguf) | i1-Q3_K_L | 2.0 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/granite-3b-code-base-128k-i1-GGUF/resolve/main/granite-3b-code-base-128k.i1-IQ4_XS.gguf) | i1-IQ4_XS | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/granite-3b-code-base-128k-i1-GGUF/resolve/main/granite-3b-code-base-128k.i1-Q4_0.gguf) | i1-Q4_0 | 2.1 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/granite-3b-code-base-128k-i1-GGUF/resolve/main/granite-3b-code-base-128k.i1-Q4_K_S.gguf) | i1-Q4_K_S | 2.1 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/granite-3b-code-base-128k-i1-GGUF/resolve/main/granite-3b-code-base-128k.i1-Q4_K_M.gguf) | i1-Q4_K_M | 2.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/granite-3b-code-base-128k-i1-GGUF/resolve/main/granite-3b-code-base-128k.i1-Q5_K_S.gguf) | i1-Q5_K_S | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/granite-3b-code-base-128k-i1-GGUF/resolve/main/granite-3b-code-base-128k.i1-Q5_K_M.gguf) | i1-Q5_K_M | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/granite-3b-code-base-128k-i1-GGUF/resolve/main/granite-3b-code-base-128k.i1-Q6_K.gguf) | i1-Q6_K | 3.0 | 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-3b-code-base-128k.i1-IQ1_M.gguf b/granite-3b-code-base-128k.i1-IQ1_M.gguf new file mode 100644 index 0000000..16716f8 --- /dev/null +++ b/granite-3b-code-base-128k.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4982df46a4d16f32ca1ac0db76c0bb4dbb09f9a2286e30b9d2fa6a7865f6036 +size 869784000 diff --git a/granite-3b-code-base-128k.i1-IQ1_S.gguf b/granite-3b-code-base-128k.i1-IQ1_S.gguf new file mode 100644 index 0000000..cd34531 --- /dev/null +++ b/granite-3b-code-base-128k.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8daaa012337cb98dda51935c1fb0261028f783936bfa58de6496feca66c8e75b +size 803428800 diff --git a/granite-3b-code-base-128k.i1-IQ2_M.gguf b/granite-3b-code-base-128k.i1-IQ2_M.gguf new file mode 100644 index 0000000..f4c080d --- /dev/null +++ b/granite-3b-code-base-128k.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3659a73dbd430dfac8934bf41570dacce34a078eb6bdc059c74064c8ee1f120 +size 1225316800 diff --git a/granite-3b-code-base-128k.i1-IQ2_S.gguf b/granite-3b-code-base-128k.i1-IQ2_S.gguf new file mode 100644 index 0000000..52b28dd --- /dev/null +++ b/granite-3b-code-base-128k.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc812daef21cc99b8a2332a19af768974bd32b23b896d9bd4a5fb93705769bb8 +size 1136843200 diff --git a/granite-3b-code-base-128k.i1-IQ2_XS.gguf b/granite-3b-code-base-128k.i1-IQ2_XS.gguf new file mode 100644 index 0000000..80a0abd --- /dev/null +++ b/granite-3b-code-base-128k.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a1970f49030a3438f2c4735c69f14b39f3a34ac9d1ecd03288accbd4513e306 +size 1075403200 diff --git a/granite-3b-code-base-128k.i1-IQ2_XXS.gguf b/granite-3b-code-base-128k.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..acda390 --- /dev/null +++ b/granite-3b-code-base-128k.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9a573cbf96c332b967328701538fabddf608f1b9def452e2058a5adaf175147 +size 980376000 diff --git a/granite-3b-code-base-128k.i1-IQ3_M.gguf b/granite-3b-code-base-128k.i1-IQ3_M.gguf new file mode 100644 index 0000000..6ec09d6 --- /dev/null +++ b/granite-3b-code-base-128k.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00fe9ee2f1c67f6e56e1156c05cba4b325b7042e2db20f2659812533c8fe835b +size 1621318080 diff --git a/granite-3b-code-base-128k.i1-IQ3_S.gguf b/granite-3b-code-base-128k.i1-IQ3_S.gguf new file mode 100644 index 0000000..1c09b42 --- /dev/null +++ b/granite-3b-code-base-128k.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96c153e04e47aaff720f7a6e6ff0b938f683c23a4994a0ba294baf227c5b8a36 +size 1551686080 diff --git a/granite-3b-code-base-128k.i1-IQ3_XS.gguf b/granite-3b-code-base-128k.i1-IQ3_XS.gguf new file mode 100644 index 0000000..99dbe77 --- /dev/null +++ b/granite-3b-code-base-128k.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b259433b694cbe04334ace2bdbfe0d0f271492e89c30009a9118e1277ef5e7b +size 1473042880 diff --git a/granite-3b-code-base-128k.i1-IQ3_XXS.gguf b/granite-3b-code-base-128k.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..3328f52 --- /dev/null +++ b/granite-3b-code-base-128k.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac8d62caa51d891ad3a6d4758fc9fcb9548ad2f7442745c68d0b83970ffba7fd +size 1361304000 diff --git a/granite-3b-code-base-128k.i1-IQ4_XS.gguf b/granite-3b-code-base-128k.i1-IQ4_XS.gguf new file mode 100644 index 0000000..6e2dc62 --- /dev/null +++ b/granite-3b-code-base-128k.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6521de1df059424173812e1a5908bb4a900e6c53cbf3d36453830738a0e691a +size 1892473280 diff --git a/granite-3b-code-base-128k.i1-Q2_K.gguf b/granite-3b-code-base-128k.i1-Q2_K.gguf new file mode 100644 index 0000000..b243a09 --- /dev/null +++ b/granite-3b-code-base-128k.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c57ecc61ec789a008e0f4769a671a3ab9fc7eb349763b0e6bd1c8197b3c2a617 +size 1338694080 diff --git a/granite-3b-code-base-128k.i1-Q3_K_L.gguf b/granite-3b-code-base-128k.i1-Q3_K_L.gguf new file mode 100644 index 0000000..ba4a963 --- /dev/null +++ b/granite-3b-code-base-128k.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4d2420525913a7686995e5120f5a676e65848aae819be2291232a3d2936e94a +size 1876089280 diff --git a/granite-3b-code-base-128k.i1-Q3_K_M.gguf b/granite-3b-code-base-128k.i1-Q3_K_M.gguf new file mode 100644 index 0000000..129a065 --- /dev/null +++ b/granite-3b-code-base-128k.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1e0778c002fa2f439f346cc9492dbd2a59ecd1b83e0bcdded433bb52fb949e5 +size 1726994880 diff --git a/granite-3b-code-base-128k.i1-Q3_K_S.gguf b/granite-3b-code-base-128k.i1-Q3_K_S.gguf new file mode 100644 index 0000000..2c364e8 --- /dev/null +++ b/granite-3b-code-base-128k.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0e10cdaf7bd70cdcdd1f18509420f62268428f69b6abd709cd3f753160a170b +size 1551686080 diff --git a/granite-3b-code-base-128k.i1-Q4_0.gguf b/granite-3b-code-base-128k.i1-Q4_0.gguf new file mode 100644 index 0000000..472a420 --- /dev/null +++ b/granite-3b-code-base-128k.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56037dd301726fe80ee3a79d42de85bfad4482fa7952f1351005e0ca983253bf +size 2003884480 diff --git a/granite-3b-code-base-128k.i1-Q4_K_M.gguf b/granite-3b-code-base-128k.i1-Q4_K_M.gguf new file mode 100644 index 0000000..2c9b04b --- /dev/null +++ b/granite-3b-code-base-128k.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b03393b48f1767fd27da47911d089ac63e84ca3e5d6473a01223783e0606fec +size 2132498880 diff --git a/granite-3b-code-base-128k.i1-Q4_K_S.gguf b/granite-3b-code-base-128k.i1-Q4_K_S.gguf new file mode 100644 index 0000000..fd29f71 --- /dev/null +++ b/granite-3b-code-base-128k.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df123c00e33f6ec03a5fc33f9a0ea8edee73cf1f4746b65e2d3bb8163e2d3547 +size 2013714880 diff --git a/granite-3b-code-base-128k.i1-Q5_K_M.gguf b/granite-3b-code-base-128k.i1-Q5_K_M.gguf new file mode 100644 index 0000000..2655815 --- /dev/null +++ b/granite-3b-code-base-128k.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:971d456fb83acacbefa866a73d4d0af4d934c611e168d454f7befb19cbf73a4a +size 2486393280 diff --git a/granite-3b-code-base-128k.i1-Q5_K_S.gguf b/granite-3b-code-base-128k.i1-Q5_K_S.gguf new file mode 100644 index 0000000..4739729 --- /dev/null +++ b/granite-3b-code-base-128k.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f94f81f5593c5a6b66457052f15f2189fbe5b8c8025defac36c2ed8cba2f7150 +size 2416761280 diff --git a/granite-3b-code-base-128k.i1-Q6_K.gguf b/granite-3b-code-base-128k.i1-Q6_K.gguf new file mode 100644 index 0000000..a2fc1be --- /dev/null +++ b/granite-3b-code-base-128k.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d71dc1f75dd8a99a3b630beea7bcc851b66c9728bf9f11cefd2128cedd9f53c +size 2862406080 diff --git a/imatrix.dat b/imatrix.dat new file mode 100644 index 0000000..649e992 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1e4551add5b6773366ed0427e7451b51a2292e3945adf8474df74c8299375c3 +size 3284221