commit 899e9111e63a884e1026e0b189b0228a0c3cbda3 Author: ModelHub XC Date: Wed Jun 17 01:28:15 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: mradermacher/granite-guardian-3.2-3b-a800m-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..3d91d46 --- /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-guardian-3.2-3b-a800m.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +granite-guardian-3.2-3b-a800m.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +granite-guardian-3.2-3b-a800m.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +granite-guardian-3.2-3b-a800m.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +granite-guardian-3.2-3b-a800m.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +granite-guardian-3.2-3b-a800m.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +granite-guardian-3.2-3b-a800m.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +granite-guardian-3.2-3b-a800m.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +granite-guardian-3.2-3b-a800m.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +granite-guardian-3.2-3b-a800m.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +granite-guardian-3.2-3b-a800m.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +granite-guardian-3.2-3b-a800m.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..b565789 --- /dev/null +++ b/README.md @@ -0,0 +1,65 @@ +--- +base_model: ibm-granite/granite-guardian-3.2-3b-a800m +language: +- en +library_name: transformers +license: apache-2.0 +no_imatrix: Missing importance matrix for tensor blk.0.ffn_gate_exps.weight in a very + low-bit quantization +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/ibm-granite/granite-guardian-3.2-3b-a800m + + +## 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-guardian-3.2-3b-a800m-GGUF/resolve/main/granite-guardian-3.2-3b-a800m.Q2_K.gguf) | Q2_K | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/granite-guardian-3.2-3b-a800m-GGUF/resolve/main/granite-guardian-3.2-3b-a800m.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/granite-guardian-3.2-3b-a800m-GGUF/resolve/main/granite-guardian-3.2-3b-a800m.Q3_K_M.gguf) | Q3_K_M | 1.7 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/granite-guardian-3.2-3b-a800m-GGUF/resolve/main/granite-guardian-3.2-3b-a800m.Q3_K_L.gguf) | Q3_K_L | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/granite-guardian-3.2-3b-a800m-GGUF/resolve/main/granite-guardian-3.2-3b-a800m.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/granite-guardian-3.2-3b-a800m-GGUF/resolve/main/granite-guardian-3.2-3b-a800m.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/granite-guardian-3.2-3b-a800m-GGUF/resolve/main/granite-guardian-3.2-3b-a800m.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/granite-guardian-3.2-3b-a800m-GGUF/resolve/main/granite-guardian-3.2-3b-a800m.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/granite-guardian-3.2-3b-a800m-GGUF/resolve/main/granite-guardian-3.2-3b-a800m.Q5_K_M.gguf) | Q5_K_M | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/granite-guardian-3.2-3b-a800m-GGUF/resolve/main/granite-guardian-3.2-3b-a800m.Q6_K.gguf) | Q6_K | 2.8 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/granite-guardian-3.2-3b-a800m-GGUF/resolve/main/granite-guardian-3.2-3b-a800m.Q8_0.gguf) | Q8_0 | 3.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/granite-guardian-3.2-3b-a800m-GGUF/resolve/main/granite-guardian-3.2-3b-a800m.f16.gguf) | f16 | 6.7 | 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/granite-guardian-3.2-3b-a800m.IQ4_XS.gguf b/granite-guardian-3.2-3b-a800m.IQ4_XS.gguf new file mode 100644 index 0000000..4e66ac1 --- /dev/null +++ b/granite-guardian-3.2-3b-a800m.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:528def4cf8c424a6360156a88c59873bde35b0bf32cedf118cb16808a574412d +size 1802889344 diff --git a/granite-guardian-3.2-3b-a800m.Q2_K.gguf b/granite-guardian-3.2-3b-a800m.Q2_K.gguf new file mode 100644 index 0000000..9c118d7 --- /dev/null +++ b/granite-guardian-3.2-3b-a800m.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4fb6d7ef91bdbe404df68d7da50cf67446886e0702793cc561fcfec6eb013069 +size 1241376896 diff --git a/granite-guardian-3.2-3b-a800m.Q3_K_L.gguf b/granite-guardian-3.2-3b-a800m.Q3_K_L.gguf new file mode 100644 index 0000000..1be8300 --- /dev/null +++ b/granite-guardian-3.2-3b-a800m.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cda5cf8d08a35b1c97c0d6f583e855f5e33d9d58cdd9199959a6ed32df640abf +size 1741547648 diff --git a/granite-guardian-3.2-3b-a800m.Q3_K_M.gguf b/granite-guardian-3.2-3b-a800m.Q3_K_M.gguf new file mode 100644 index 0000000..decb6c6 --- /dev/null +++ b/granite-guardian-3.2-3b-a800m.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c68f7b4fc2e803500a1229692b0807a2cf3d1735d30fd2168a35a9daa0c587c +size 1611196544 diff --git a/granite-guardian-3.2-3b-a800m.Q3_K_S.gguf b/granite-guardian-3.2-3b-a800m.Q3_K_S.gguf new file mode 100644 index 0000000..88bea6e --- /dev/null +++ b/granite-guardian-3.2-3b-a800m.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5880a9fbdc1a078aa9501b5e159257da7ecd052107ddfeb2b642a533a99ad761 +size 1456072832 diff --git a/granite-guardian-3.2-3b-a800m.Q4_K_M.gguf b/granite-guardian-3.2-3b-a800m.Q4_K_M.gguf new file mode 100644 index 0000000..a3e2762 --- /dev/null +++ b/granite-guardian-3.2-3b-a800m.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7dbe0ca7f2380c7c17562bbb62ed0744109dc3ce79eb916c8f961bf2f793985 +size 2016897152 diff --git a/granite-guardian-3.2-3b-a800m.Q4_K_S.gguf b/granite-guardian-3.2-3b-a800m.Q4_K_S.gguf new file mode 100644 index 0000000..4e5e235 --- /dev/null +++ b/granite-guardian-3.2-3b-a800m.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33dad813bc1ba6fa5c4c51eb83799d7b658f04176b40c1b1608626fe0405e265 +size 1900013696 diff --git a/granite-guardian-3.2-3b-a800m.Q5_K_M.gguf b/granite-guardian-3.2-3b-a800m.Q5_K_M.gguf new file mode 100644 index 0000000..9bd1c09 --- /dev/null +++ b/granite-guardian-3.2-3b-a800m.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc37906fb11efb53731e0fea2cc4e482596fd56bf87869ff642d6566aa2e7a84 +size 2355062912 diff --git a/granite-guardian-3.2-3b-a800m.Q5_K_S.gguf b/granite-guardian-3.2-3b-a800m.Q5_K_S.gguf new file mode 100644 index 0000000..dbc6502 --- /dev/null +++ b/granite-guardian-3.2-3b-a800m.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec64b0346329db46cccb9d32939d150828d1e941603e01348d39a098f5f53677 +size 2286545024 diff --git a/granite-guardian-3.2-3b-a800m.Q6_K.gguf b/granite-guardian-3.2-3b-a800m.Q6_K.gguf new file mode 100644 index 0000000..5e3d43e --- /dev/null +++ b/granite-guardian-3.2-3b-a800m.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ae5fb260d54425a345d6a903b642dd0667c063b25599996c65a2cca99617b0a +size 2714364032 diff --git a/granite-guardian-3.2-3b-a800m.Q8_0.gguf b/granite-guardian-3.2-3b-a800m.Q8_0.gguf new file mode 100644 index 0000000..ac280d6 --- /dev/null +++ b/granite-guardian-3.2-3b-a800m.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1a83cf84691ed6cc71aba8f4d694ed8ec758582915408119bd119b79075e4cd +size 3512790208 diff --git a/granite-guardian-3.2-3b-a800m.f16.gguf b/granite-guardian-3.2-3b-a800m.f16.gguf new file mode 100644 index 0000000..37891aa --- /dev/null +++ b/granite-guardian-3.2-3b-a800m.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4292a936ba057cde8356c90b946a44b6e5c952a231d32b378c2e6f9741b1b68b +size 6603472288