commit e59817464be11ef7b04f91e9135c79cc435d13ca Author: ModelHub XC Date: Sat Jul 18 00:35:12 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: qwp4w3hyb/Mistral-Nemo-Instruct-2407-iMat-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..4256eba --- /dev/null +++ b/.gitattributes @@ -0,0 +1,54 @@ +*.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 +mistral-nemo-instruct-2407-bf16.gguf filter=lfs diff=lfs merge=lfs -text +mistral-nemo-instruct-2407-imat-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +mistral-nemo-instruct-2407-imat-IQ2_L.gguf filter=lfs diff=lfs merge=lfs -text +mistral-nemo-instruct-2407-imat-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +mistral-nemo-instruct-2407-imat-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +mistral-nemo-instruct-2407-imat-IQ3_L.gguf filter=lfs diff=lfs merge=lfs -text +mistral-nemo-instruct-2407-imat-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +mistral-nemo-instruct-2407-imat-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +mistral-nemo-instruct-2407-imat-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +mistral-nemo-instruct-2407-imat-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +mistral-nemo-instruct-2407-imat-Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text +mistral-nemo-instruct-2407-imat-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +mistral-nemo-instruct-2407-imat-Q5_K_L.gguf filter=lfs diff=lfs merge=lfs -text +mistral-nemo-instruct-2407-imat-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +mistral-nemo-instruct-2407-imat-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +mistral-nemo-instruct-2407-imat-Q6_K_L.gguf filter=lfs diff=lfs merge=lfs -text +mistral-nemo-instruct-2407-imat-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +mistral-nemo-instruct-2407-imat-Q8_0_L.gguf filter=lfs diff=lfs merge=lfs -text +mistral-nemo-instruct-2407.imatrix filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..e44da32 --- /dev/null +++ b/README.md @@ -0,0 +1,30 @@ +--- +license: apache-2.0 +language: +- en +pipeline_tag: text-generation +tags: +- mistral +- instruct +- gguf +- imatrix +base_model: mistralai/Mistral-Nemo-Instruct-2407 +--- + +# Quant Infos + + +- needs [#8604](https://github.com/ggerganov/llama.cpp/pull/8604) & latest master with tekken tokenizer fixes applied +- quants done with an importance matrix for improved quantization loss +- Quantized ggufs & imatrix from hf bf16, through bf16. `safetensors bf16 -> gguf bf16 -> quant` for optimal quant loss. +- Wide coverage of different gguf quant types from Q\_8\_0 down to IQ1\_S + - experimental custom quant types + - `_L` with `--output-tensor-type f16 --token-embedding-type f16` (same as bartowski's) +- Imatrix generated with [this](https://gist.github.com/bartowski1182/eb213dccb3571f863da82e99418f81e8) multi-purpose dataset by [bartowski](https://huggingface.co/bartowski). + ``` + ./imatrix -m $model_name-bf16.gguf -f calibration_datav3.txt -o $model_name.imatrix + ``` + +# Original Model Card: + +TODO \ No newline at end of file diff --git a/mistral-nemo-instruct-2407-bf16.gguf b/mistral-nemo-instruct-2407-bf16.gguf new file mode 100644 index 0000000..8d88a48 --- /dev/null +++ b/mistral-nemo-instruct-2407-bf16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed0d5f408dd612f9bbc778262e512279b4dd187892c4cf735fd2ec41b5f6a9ba +size 24504276672 diff --git a/mistral-nemo-instruct-2407-imat-IQ1_S.gguf b/mistral-nemo-instruct-2407-imat-IQ1_S.gguf new file mode 100644 index 0000000..420b524 --- /dev/null +++ b/mistral-nemo-instruct-2407-imat-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bbc46fd360c6d9673f63093594af86e3380f198a0753af75e7b27d6802205166 +size 2999212032 diff --git a/mistral-nemo-instruct-2407-imat-IQ2_L.gguf b/mistral-nemo-instruct-2407-imat-IQ2_L.gguf new file mode 100644 index 0000000..6a4e1cd --- /dev/null +++ b/mistral-nemo-instruct-2407-imat-IQ2_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78c34ecfdd1b7511b3b74d62deaa45d3a88aa3eec2c2812fabcc02a190f969ab +size 6369646592 diff --git a/mistral-nemo-instruct-2407-imat-IQ2_M.gguf b/mistral-nemo-instruct-2407-imat-IQ2_M.gguf new file mode 100644 index 0000000..e200db9 --- /dev/null +++ b/mistral-nemo-instruct-2407-imat-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13c09f3b1f8352af21ffce2c7e48080f15908d552682bb7c6b46a2c0720d8d2d +size 4435023872 diff --git a/mistral-nemo-instruct-2407-imat-IQ2_XXS.gguf b/mistral-nemo-instruct-2407-imat-IQ2_XXS.gguf new file mode 100644 index 0000000..a28a620 --- /dev/null +++ b/mistral-nemo-instruct-2407-imat-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:959b9b06d59cae4f078adade6f4643645df4826f71f008f02bd0b9c0795fa1e9 +size 3592312832 diff --git a/mistral-nemo-instruct-2407-imat-IQ3_L.gguf b/mistral-nemo-instruct-2407-imat-IQ3_L.gguf new file mode 100644 index 0000000..0d198fa --- /dev/null +++ b/mistral-nemo-instruct-2407-imat-IQ3_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7850d5825c526d51d276b308a9a5521c31b734315e64b73d17c912095d3662a4 +size 7567726592 diff --git a/mistral-nemo-instruct-2407-imat-IQ3_M.gguf b/mistral-nemo-instruct-2407-imat-IQ3_M.gguf new file mode 100644 index 0000000..8859d40 --- /dev/null +++ b/mistral-nemo-instruct-2407-imat-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5ac5e3d00134f4912dcebec1686d90c60d27f2e8661534efafefb6a0c5bcf38 +size 5722232832 diff --git a/mistral-nemo-instruct-2407-imat-IQ3_XXS.gguf b/mistral-nemo-instruct-2407-imat-IQ3_XXS.gguf new file mode 100644 index 0000000..8157b1f --- /dev/null +++ b/mistral-nemo-instruct-2407-imat-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6c8164ff0b38d0c9e9b9a055692345b0b00652d2ef713a78b483c69641a7997 +size 4945385472 diff --git a/mistral-nemo-instruct-2407-imat-IQ4_XS.gguf b/mistral-nemo-instruct-2407-imat-IQ4_XS.gguf new file mode 100644 index 0000000..ca70654 --- /dev/null +++ b/mistral-nemo-instruct-2407-imat-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ec951c386bf51693ad855925a8139e6ae30e5b2a8e21354f35ac52f1026f808 +size 6742710272 diff --git a/mistral-nemo-instruct-2407-imat-Q4_0.gguf b/mistral-nemo-instruct-2407-imat-Q4_0.gguf new file mode 100644 index 0000000..46a7986 --- /dev/null +++ b/mistral-nemo-instruct-2407-imat-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e36362a4862ff247ef2a61e46194faa54609456b110f835cedaf2867bd2e4f4 +size 7094638592 diff --git a/mistral-nemo-instruct-2407-imat-Q4_K_L.gguf b/mistral-nemo-instruct-2407-imat-Q4_K_L.gguf new file mode 100644 index 0000000..e8934a4 --- /dev/null +++ b/mistral-nemo-instruct-2407-imat-Q4_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6dbf223562be723a047610511df85103c74f21a4a3d1073549bd18da5b423781 +size 9233569792 diff --git a/mistral-nemo-instruct-2407-imat-Q4_K_M.gguf b/mistral-nemo-instruct-2407-imat-Q4_K_M.gguf new file mode 100644 index 0000000..a4a9d23 --- /dev/null +++ b/mistral-nemo-instruct-2407-imat-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f78dd3b1f876d3e14350515d837162583d72554ac937bcc2d1716cab9de80ae +size 7477204992 diff --git a/mistral-nemo-instruct-2407-imat-Q5_K_L.gguf b/mistral-nemo-instruct-2407-imat-Q5_K_L.gguf new file mode 100644 index 0000000..051e882 --- /dev/null +++ b/mistral-nemo-instruct-2407-imat-Q5_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d35476b6b79a2bbe236fea44719311f7252eaa674e08ce3f6aac639bf00045e +size 10400110592 diff --git a/mistral-nemo-instruct-2407-imat-Q5_K_M.gguf b/mistral-nemo-instruct-2407-imat-Q5_K_M.gguf new file mode 100644 index 0000000..970c9bc --- /dev/null +++ b/mistral-nemo-instruct-2407-imat-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e5717dc3f1add9400c9eb0dd0a8ca550751848cfdb9924c255619ed0ecb1514 +size 8727631872 diff --git a/mistral-nemo-instruct-2407-imat-Q6_K.gguf b/mistral-nemo-instruct-2407-imat-Q6_K.gguf new file mode 100644 index 0000000..de78e5f --- /dev/null +++ b/mistral-nemo-instruct-2407-imat-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2084bd4070e963b8a12a7f3ab40d6e9f935dc9866ec4e1a2b787daf536a3408 +size 10056210432 diff --git a/mistral-nemo-instruct-2407-imat-Q6_K_L.gguf b/mistral-nemo-instruct-2407-imat-Q6_K_L.gguf new file mode 100644 index 0000000..36d7195 --- /dev/null +++ b/mistral-nemo-instruct-2407-imat-Q6_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f5349b05c09b44f2d1b36ebd32c705fa6c8bd221e113578aa51b74ae0da0705 +size 11639560192 diff --git a/mistral-nemo-instruct-2407-imat-Q8_0.gguf b/mistral-nemo-instruct-2407-imat-Q8_0.gguf new file mode 100644 index 0000000..a0958c1 --- /dev/null +++ b/mistral-nemo-instruct-2407-imat-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:63215822435cdfe1207f9d527a5efa9e37299cef69af9c28230a480176c05a91 +size 13022369792 diff --git a/mistral-nemo-instruct-2407-imat-Q8_0_L.gguf b/mistral-nemo-instruct-2407-imat-Q8_0_L.gguf new file mode 100644 index 0000000..1b68759 --- /dev/null +++ b/mistral-nemo-instruct-2407-imat-Q8_0_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3dc1600d59a6285ce09948ee00da4bac72606412a8dd9ffaceafbc9f09cce5f +size 14280660992 diff --git a/mistral-nemo-instruct-2407.imatrix b/mistral-nemo-instruct-2407.imatrix new file mode 100644 index 0000000..05035ba --- /dev/null +++ b/mistral-nemo-instruct-2407.imatrix @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0897f1e887b60fec766a28142273cb41733fb26bbe624978431ea9841bba5404 +size 7054438