commit f69d8829a317df7ccba5b40d45be170643fec073 Author: ModelHub XC Date: Sat May 9 02:05:06 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/AceInstruct-7B-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..1c6a3cb --- /dev/null +++ b/.gitattributes @@ -0,0 +1,59 @@ +*.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 +AceInstruct-7B.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +AceInstruct-7B.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +AceInstruct-7B.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +AceInstruct-7B.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +AceInstruct-7B.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +AceInstruct-7B.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +AceInstruct-7B.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +AceInstruct-7B.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +AceInstruct-7B.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +AceInstruct-7B.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +AceInstruct-7B.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +AceInstruct-7B.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +AceInstruct-7B.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +AceInstruct-7B.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +AceInstruct-7B.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +AceInstruct-7B.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +AceInstruct-7B.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +AceInstruct-7B.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +AceInstruct-7B.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +AceInstruct-7B.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +AceInstruct-7B.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +AceInstruct-7B.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +AceInstruct-7B.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +AceInstruct-7B.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/AceInstruct-7B.i1-IQ1_M.gguf b/AceInstruct-7B.i1-IQ1_M.gguf new file mode 100644 index 0000000..701c6be --- /dev/null +++ b/AceInstruct-7B.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7600d2b66a19a509c5c7777c84efbb90e18df6b1010412e5bd82475765b298e +size 2042194464 diff --git a/AceInstruct-7B.i1-IQ1_S.gguf b/AceInstruct-7B.i1-IQ1_S.gguf new file mode 100644 index 0000000..c5cfa95 --- /dev/null +++ b/AceInstruct-7B.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11a0c8e62c14ff9c1a4ee6c4528a2504bc02b0591a9c38167866057af702494e +size 1903665696 diff --git a/AceInstruct-7B.i1-IQ2_M.gguf b/AceInstruct-7B.i1-IQ2_M.gguf new file mode 100644 index 0000000..080eb6d --- /dev/null +++ b/AceInstruct-7B.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:983d5eb973b4c6089e568b91170af08e48a8e753306ae4493deb7826ea400e4c +size 2780340768 diff --git a/AceInstruct-7B.i1-IQ2_S.gguf b/AceInstruct-7B.i1-IQ2_S.gguf new file mode 100644 index 0000000..c56fde2 --- /dev/null +++ b/AceInstruct-7B.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:617d50bdec9ba7ed11aff79291d2f9f1380a6284692452428c2d745798151087 +size 2595635744 diff --git a/AceInstruct-7B.i1-IQ2_XS.gguf b/AceInstruct-7B.i1-IQ2_XS.gguf new file mode 100644 index 0000000..867756d --- /dev/null +++ b/AceInstruct-7B.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5402831062b80080c9a6d774039d6e8a1ff7ca443d2d7f83b819375af96f7aa8 +size 2469020192 diff --git a/AceInstruct-7B.i1-IQ2_XXS.gguf b/AceInstruct-7B.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..6e99b22 --- /dev/null +++ b/AceInstruct-7B.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4eb139636e78dea1c10efde4c06e5cd92bc074c0d45bcfca0830d1786b52dc34 +size 2273075744 diff --git a/AceInstruct-7B.i1-IQ3_M.gguf b/AceInstruct-7B.i1-IQ3_M.gguf new file mode 100644 index 0000000..e4de1cf --- /dev/null +++ b/AceInstruct-7B.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65b668a7d456b33baab1923d5cc0807c3cdf9fba35c32dd49c4657755a288760 +size 3574010400 diff --git a/AceInstruct-7B.i1-IQ3_S.gguf b/AceInstruct-7B.i1-IQ3_S.gguf new file mode 100644 index 0000000..6477009 --- /dev/null +++ b/AceInstruct-7B.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0aaa5f1f0cdc4719bdb5c90f51217e1e5b24a2a73b42a790b9f927cd2b67e68e +size 3499190816 diff --git a/AceInstruct-7B.i1-IQ3_XS.gguf b/AceInstruct-7B.i1-IQ3_XS.gguf new file mode 100644 index 0000000..cede111 --- /dev/null +++ b/AceInstruct-7B.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79d99bdb88e92aefc2cdce234882d7184df04bcd5f6a63ae00e9572ea5910f4c +size 3346254368 diff --git a/AceInstruct-7B.i1-IQ3_XXS.gguf b/AceInstruct-7B.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..ac96e2d --- /dev/null +++ b/AceInstruct-7B.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:565c365df847b378ccee1553440fec06eeed79d256c440fd0772d5e88b936cb2 +size 3114512928 diff --git a/AceInstruct-7B.i1-IQ4_NL.gguf b/AceInstruct-7B.i1-IQ4_NL.gguf new file mode 100644 index 0000000..fc0e51e --- /dev/null +++ b/AceInstruct-7B.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f332cdd8887beae4e86fb052639797707774ecd947c791ee33d69c4f293ab69d +size 4437811744 diff --git a/AceInstruct-7B.i1-IQ4_XS.gguf b/AceInstruct-7B.i1-IQ4_XS.gguf new file mode 100644 index 0000000..5d1a6b5 --- /dev/null +++ b/AceInstruct-7B.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a78615fc9b14f8025f17e27634e9f0471053da4c6ac4fe7b9b5936f77899f41a +size 4218470944 diff --git a/AceInstruct-7B.i1-Q2_K.gguf b/AceInstruct-7B.i1-Q2_K.gguf new file mode 100644 index 0000000..9f53697 --- /dev/null +++ b/AceInstruct-7B.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1dde90421493e078a31590f7334d527daf401ab59799b0ebd2332c393ea15b43 +size 3015938592 diff --git a/AceInstruct-7B.i1-Q2_K_S.gguf b/AceInstruct-7B.i1-Q2_K_S.gguf new file mode 100644 index 0000000..3a81547 --- /dev/null +++ b/AceInstruct-7B.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4da5958a2a5eeb41e28b9bbfa04b233c167885bb040cb8abe01b3449ec9df71 +size 2834072096 diff --git a/AceInstruct-7B.i1-Q3_K_L.gguf b/AceInstruct-7B.i1-Q3_K_L.gguf new file mode 100644 index 0000000..40355dc --- /dev/null +++ b/AceInstruct-7B.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51b4ff2cb51d100371e6e7cc226231d5e7bb2fac2c21c7f8e755000679653619 +size 4088457760 diff --git a/AceInstruct-7B.i1-Q3_K_M.gguf b/AceInstruct-7B.i1-Q3_K_M.gguf new file mode 100644 index 0000000..d9d5af0 --- /dev/null +++ b/AceInstruct-7B.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a1e144537e7ec8df25e6f86a816727dc308f939679dfa24c6bf85edaaf128db +size 3808389664 diff --git a/AceInstruct-7B.i1-Q3_K_S.gguf b/AceInstruct-7B.i1-Q3_K_S.gguf new file mode 100644 index 0000000..ff2e1c1 --- /dev/null +++ b/AceInstruct-7B.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6563fb4d3a3810760506fe36a3aa781ae8adbba13a3f7de8b6be226edc95629a +size 3492366880 diff --git a/AceInstruct-7B.i1-Q4_0.gguf b/AceInstruct-7B.i1-Q4_0.gguf new file mode 100644 index 0000000..ca223d8 --- /dev/null +++ b/AceInstruct-7B.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42cdfbd62831974f1541014cce6e2cabd63f33100a31deeafd0aa12e23724805 +size 4444119584 diff --git a/AceInstruct-7B.i1-Q4_1.gguf b/AceInstruct-7B.i1-Q4_1.gguf new file mode 100644 index 0000000..21d7f32 --- /dev/null +++ b/AceInstruct-7B.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ea51bdf8981a7f413c916cc622adf123e11ef2b137cb7e4092f430d1b27ba1b +size 4873282080 diff --git a/AceInstruct-7B.i1-Q4_K_M.gguf b/AceInstruct-7B.i1-Q4_K_M.gguf new file mode 100644 index 0000000..b30e762 --- /dev/null +++ b/AceInstruct-7B.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dbc57cfa18e5722ccb29624ff7d02680aff570e160db8839facc5b37b0741895 +size 4683072032 diff --git a/AceInstruct-7B.i1-Q4_K_S.gguf b/AceInstruct-7B.i1-Q4_K_S.gguf new file mode 100644 index 0000000..c0f1bb5 --- /dev/null +++ b/AceInstruct-7B.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a7fd501ba6ffd6a7cd359ef3c0bcff79bb0ee29a98a86fc25632a1b8b4a5238 +size 4457767456 diff --git a/AceInstruct-7B.i1-Q5_K_M.gguf b/AceInstruct-7B.i1-Q5_K_M.gguf new file mode 100644 index 0000000..246bdec --- /dev/null +++ b/AceInstruct-7B.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72a8997943d0ea0018e6b94e7c889f3dada9ad4bbc9d20d332ed1d9563f95665 +size 5444829728 diff --git a/AceInstruct-7B.i1-Q5_K_S.gguf b/AceInstruct-7B.i1-Q5_K_S.gguf new file mode 100644 index 0000000..20210f5 --- /dev/null +++ b/AceInstruct-7B.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b946f099d4db117b3d7b58552c828f38fcc3389b460deb47d5997c3da46f51a +size 5315174944 diff --git a/AceInstruct-7B.i1-Q6_K.gguf b/AceInstruct-7B.i1-Q6_K.gguf new file mode 100644 index 0000000..72c98f0 --- /dev/null +++ b/AceInstruct-7B.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2fc9dc3dfe46a16a6f8544ea5527a949f1087ea617255adeb81c5ded60cc9eb1 +size 6254197280 diff --git a/README.md b/README.md new file mode 100644 index 0000000..6e3c345 --- /dev/null +++ b/README.md @@ -0,0 +1,84 @@ +--- +base_model: nvidia/AceInstruct-7B +language: +- en +library_name: transformers +license: cc-by-nc-4.0 +quantized_by: mradermacher +tags: +- nvidia +- AceInstruct +- code +- math +- general_domain +- instruct_model +- pytorch +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/nvidia/AceInstruct-7B + + +static quants are available at https://huggingface.co/mradermacher/AceInstruct-7B-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/AceInstruct-7B-i1-GGUF/resolve/main/AceInstruct-7B.i1-IQ1_S.gguf) | i1-IQ1_S | 2.0 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/AceInstruct-7B-i1-GGUF/resolve/main/AceInstruct-7B.i1-IQ1_M.gguf) | i1-IQ1_M | 2.1 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/AceInstruct-7B-i1-GGUF/resolve/main/AceInstruct-7B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/AceInstruct-7B-i1-GGUF/resolve/main/AceInstruct-7B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/AceInstruct-7B-i1-GGUF/resolve/main/AceInstruct-7B.i1-IQ2_S.gguf) | i1-IQ2_S | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/AceInstruct-7B-i1-GGUF/resolve/main/AceInstruct-7B.i1-IQ2_M.gguf) | i1-IQ2_M | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/AceInstruct-7B-i1-GGUF/resolve/main/AceInstruct-7B.i1-Q2_K_S.gguf) | i1-Q2_K_S | 2.9 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/AceInstruct-7B-i1-GGUF/resolve/main/AceInstruct-7B.i1-Q2_K.gguf) | i1-Q2_K | 3.1 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/AceInstruct-7B-i1-GGUF/resolve/main/AceInstruct-7B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/AceInstruct-7B-i1-GGUF/resolve/main/AceInstruct-7B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/AceInstruct-7B-i1-GGUF/resolve/main/AceInstruct-7B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.6 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/AceInstruct-7B-i1-GGUF/resolve/main/AceInstruct-7B.i1-IQ3_S.gguf) | i1-IQ3_S | 3.6 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/AceInstruct-7B-i1-GGUF/resolve/main/AceInstruct-7B.i1-IQ3_M.gguf) | i1-IQ3_M | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/AceInstruct-7B-i1-GGUF/resolve/main/AceInstruct-7B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 3.9 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/AceInstruct-7B-i1-GGUF/resolve/main/AceInstruct-7B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.2 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/AceInstruct-7B-i1-GGUF/resolve/main/AceInstruct-7B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.3 | | +| [GGUF](https://huggingface.co/mradermacher/AceInstruct-7B-i1-GGUF/resolve/main/AceInstruct-7B.i1-IQ4_NL.gguf) | i1-IQ4_NL | 4.5 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/AceInstruct-7B-i1-GGUF/resolve/main/AceInstruct-7B.i1-Q4_0.gguf) | i1-Q4_0 | 4.5 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/AceInstruct-7B-i1-GGUF/resolve/main/AceInstruct-7B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.6 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/AceInstruct-7B-i1-GGUF/resolve/main/AceInstruct-7B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/AceInstruct-7B-i1-GGUF/resolve/main/AceInstruct-7B.i1-Q4_1.gguf) | i1-Q4_1 | 5.0 | | +| [GGUF](https://huggingface.co/mradermacher/AceInstruct-7B-i1-GGUF/resolve/main/AceInstruct-7B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/AceInstruct-7B-i1-GGUF/resolve/main/AceInstruct-7B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/AceInstruct-7B-i1-GGUF/resolve/main/AceInstruct-7B.i1-Q6_K.gguf) | i1-Q6_K | 6.4 | 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. + +