commit 094f19402b0162447c2dd44b4900c0f26406d189 Author: ModelHub XC Date: Tue Jun 16 21:08:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/granite-3b-code-instruct-128k-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..4c9b631 --- /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 +granite-3b-code-instruct-128k.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +granite-3b-code-instruct-128k.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +granite-3b-code-instruct-128k.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +granite-3b-code-instruct-128k.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +granite-3b-code-instruct-128k.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +granite-3b-code-instruct-128k.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +granite-3b-code-instruct-128k.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +granite-3b-code-instruct-128k.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +granite-3b-code-instruct-128k.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +granite-3b-code-instruct-128k.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +granite-3b-code-instruct-128k.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +granite-3b-code-instruct-128k.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..2e64b37 --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +base_model: ibm-granite/granite-3b-code-instruct-128k +datasets: +- bigcode/commitpackft +- TIGER-Lab/MathInstruct +- meta-math/MetaMathQA +- glaiveai/glaive-code-assistant-v3 +- glaive-function-calling-v2 +- bugdaryan/sql-create-context-instruction +- garage-bAInd/Open-Platypus +- nvidia/HelpSteer +- bigcode/self-oss-instruct-sc2-exec-filter-50k +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- code +- granite +--- +## About + + + + + + +static quants of https://huggingface.co/ibm-granite/granite-3b-code-instruct-128k + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/granite-3b-code-instruct-128k-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/granite-3b-code-instruct-128k-GGUF/resolve/main/granite-3b-code-instruct-128k.Q2_K.gguf) | Q2_K | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/granite-3b-code-instruct-128k-GGUF/resolve/main/granite-3b-code-instruct-128k.Q3_K_S.gguf) | Q3_K_S | 1.7 | | +| [GGUF](https://huggingface.co/mradermacher/granite-3b-code-instruct-128k-GGUF/resolve/main/granite-3b-code-instruct-128k.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/granite-3b-code-instruct-128k-GGUF/resolve/main/granite-3b-code-instruct-128k.Q3_K_L.gguf) | Q3_K_L | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/granite-3b-code-instruct-128k-GGUF/resolve/main/granite-3b-code-instruct-128k.IQ4_XS.gguf) | IQ4_XS | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/granite-3b-code-instruct-128k-GGUF/resolve/main/granite-3b-code-instruct-128k.Q4_K_S.gguf) | Q4_K_S | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/granite-3b-code-instruct-128k-GGUF/resolve/main/granite-3b-code-instruct-128k.Q4_K_M.gguf) | Q4_K_M | 2.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/granite-3b-code-instruct-128k-GGUF/resolve/main/granite-3b-code-instruct-128k.Q5_K_S.gguf) | Q5_K_S | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/granite-3b-code-instruct-128k-GGUF/resolve/main/granite-3b-code-instruct-128k.Q5_K_M.gguf) | Q5_K_M | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/granite-3b-code-instruct-128k-GGUF/resolve/main/granite-3b-code-instruct-128k.Q6_K.gguf) | Q6_K | 3.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/granite-3b-code-instruct-128k-GGUF/resolve/main/granite-3b-code-instruct-128k.Q8_0.gguf) | Q8_0 | 3.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/granite-3b-code-instruct-128k-GGUF/resolve/main/granite-3b-code-instruct-128k.f16.gguf) | f16 | 7.1 | 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. 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-instruct-128k.IQ4_XS.gguf b/granite-3b-code-instruct-128k.IQ4_XS.gguf new file mode 100644 index 0000000..2c7a185 --- /dev/null +++ b/granite-3b-code-instruct-128k.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e14f2ee4d14a79a556f699d95178653020e3e583ebd8413569bafedea0893f8 +size 1908859232 diff --git a/granite-3b-code-instruct-128k.Q2_K.gguf b/granite-3b-code-instruct-128k.Q2_K.gguf new file mode 100644 index 0000000..5610b1d --- /dev/null +++ b/granite-3b-code-instruct-128k.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1213fc4360875e3494185d252911fe9c29b4b757ae9562efe5fc0c4598d427e1 +size 1338696032 diff --git a/granite-3b-code-instruct-128k.Q3_K_L.gguf b/granite-3b-code-instruct-128k.Q3_K_L.gguf new file mode 100644 index 0000000..0ae3f70 --- /dev/null +++ b/granite-3b-code-instruct-128k.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd035346a716c430898f793405b6994e7a487adf5be44ba984ba083ac8f728fb +size 1876091232 diff --git a/granite-3b-code-instruct-128k.Q3_K_M.gguf b/granite-3b-code-instruct-128k.Q3_K_M.gguf new file mode 100644 index 0000000..8630bee --- /dev/null +++ b/granite-3b-code-instruct-128k.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4bcc2a0aee2f41dc20a5ad663d73a0f4eac7f9982ac9b1dac032b1a7ccd1cbcb +size 1726996832 diff --git a/granite-3b-code-instruct-128k.Q3_K_S.gguf b/granite-3b-code-instruct-128k.Q3_K_S.gguf new file mode 100644 index 0000000..8e4fb74 --- /dev/null +++ b/granite-3b-code-instruct-128k.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e1757554e3e40d27c19958491bf46046de47173fbcc4deca7013f355d23969d +size 1551688032 diff --git a/granite-3b-code-instruct-128k.Q4_K_M.gguf b/granite-3b-code-instruct-128k.Q4_K_M.gguf new file mode 100644 index 0000000..10f5107 --- /dev/null +++ b/granite-3b-code-instruct-128k.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:632ba14c8c99f92983e18e1944d315729b66af9d7a78181de238f12a44f196b3 +size 2132500832 diff --git a/granite-3b-code-instruct-128k.Q4_K_S.gguf b/granite-3b-code-instruct-128k.Q4_K_S.gguf new file mode 100644 index 0000000..5bc502f --- /dev/null +++ b/granite-3b-code-instruct-128k.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d98afe195bd13be0119f6d42e05d7fdc5ec567f21e25150d76c7f4b956c019b8 +size 2013716832 diff --git a/granite-3b-code-instruct-128k.Q5_K_M.gguf b/granite-3b-code-instruct-128k.Q5_K_M.gguf new file mode 100644 index 0000000..555528f --- /dev/null +++ b/granite-3b-code-instruct-128k.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5ec8161c21ad1d7b41b23189928df4167f48f0f47308c59ddde40dbff88750b +size 2486395232 diff --git a/granite-3b-code-instruct-128k.Q5_K_S.gguf b/granite-3b-code-instruct-128k.Q5_K_S.gguf new file mode 100644 index 0000000..3dd02c8 --- /dev/null +++ b/granite-3b-code-instruct-128k.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22de7a0651ee588ef7c1122a8b10d7db13fd83883f3377995841b878c51a4162 +size 2416763232 diff --git a/granite-3b-code-instruct-128k.Q6_K.gguf b/granite-3b-code-instruct-128k.Q6_K.gguf new file mode 100644 index 0000000..5173ac1 --- /dev/null +++ b/granite-3b-code-instruct-128k.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24133daf4648459d9a7dadf87e9ad321f420e4c30afaca8fb3c01e5a333225c9 +size 2862408032 diff --git a/granite-3b-code-instruct-128k.Q8_0.gguf b/granite-3b-code-instruct-128k.Q8_0.gguf new file mode 100644 index 0000000..85aed84 --- /dev/null +++ b/granite-3b-code-instruct-128k.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8e350c456657beaf7b119d2ee946d374d0d76c88948d4d662642bf45a8b4d22 +size 3705528672 diff --git a/granite-3b-code-instruct-128k.f16.gguf b/granite-3b-code-instruct-128k.f16.gguf new file mode 100644 index 0000000..099c352 --- /dev/null +++ b/granite-3b-code-instruct-128k.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:35de4dea09afaba3707df01bbf9f6e1ec5e626edb2f6c73e6432631889b48770 +size 6969221472