commit 8a9b3b2f32d8fca297a759cf864ccf2f4c08bcef Author: ModelHub XC Date: Wed Apr 22 11:43:04 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: mradermacher/IPythia-70m-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..19b7637 --- /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 +IPythia-70m.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +IPythia-70m.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +IPythia-70m.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +IPythia-70m.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +IPythia-70m.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +IPythia-70m.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +IPythia-70m.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +IPythia-70m.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +IPythia-70m.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +IPythia-70m.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +IPythia-70m.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +IPythia-70m.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +IPythia-70m.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +IPythia-70m.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +IPythia-70m.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +IPythia-70m.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +IPythia-70m.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +IPythia-70m.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +IPythia-70m.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +IPythia-70m.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +IPythia-70m.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +IPythia-70m.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +IPythia-70m.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +IPythia-70m.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/IPythia-70m.i1-IQ1_M.gguf b/IPythia-70m.i1-IQ1_M.gguf new file mode 100644 index 0000000..f7cd36c --- /dev/null +++ b/IPythia-70m.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc8c02f8b7eedd9ec201bd3bc1fe28d72bdaad099f17294e5281d38a91cc88a8 +size 32285920 diff --git a/IPythia-70m.i1-IQ1_S.gguf b/IPythia-70m.i1-IQ1_S.gguf new file mode 100644 index 0000000..d10bbf0 --- /dev/null +++ b/IPythia-70m.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df3b53fa2840e6ddd8a43dd988442063ea6e7fd831e230fa8bc7abc1fc24bb45 +size 31880416 diff --git a/IPythia-70m.i1-IQ2_M.gguf b/IPythia-70m.i1-IQ2_M.gguf new file mode 100644 index 0000000..7c3b446 --- /dev/null +++ b/IPythia-70m.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5aaf2a7690f919b4b98a5ee00f37c36f6b91548609abc77af1b51c21cbb4064 +size 36929248 diff --git a/IPythia-70m.i1-IQ2_S.gguf b/IPythia-70m.i1-IQ2_S.gguf new file mode 100644 index 0000000..92d8ff8 --- /dev/null +++ b/IPythia-70m.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4866e3bc9c6da980239ab7b98ea80ae1babcd0e47cf9eb796c99a352d9fb6b09 +size 36388576 diff --git a/IPythia-70m.i1-IQ2_XS.gguf b/IPythia-70m.i1-IQ2_XS.gguf new file mode 100644 index 0000000..9ade716 --- /dev/null +++ b/IPythia-70m.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:092dd23b73a5a19db8a19d3e838a975ed8b4ddef5b40c9570f5f41b4d74c1068 +size 33551584 diff --git a/IPythia-70m.i1-IQ2_XXS.gguf b/IPythia-70m.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..e102cd1 --- /dev/null +++ b/IPythia-70m.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4e5d3d1b3e75325083cb3257e3f93f91f87e2936afff6e6f86f6a7be6a99b71 +size 32961760 diff --git a/IPythia-70m.i1-IQ3_M.gguf b/IPythia-70m.i1-IQ3_M.gguf new file mode 100644 index 0000000..88ff1ad --- /dev/null +++ b/IPythia-70m.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:743a58162011c7e95b640494fd956ec18c84a3ae0f8303b7bb628fef41a585ab +size 43077856 diff --git a/IPythia-70m.i1-IQ3_S.gguf b/IPythia-70m.i1-IQ3_S.gguf new file mode 100644 index 0000000..8fdf3c8 --- /dev/null +++ b/IPythia-70m.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc138cc40a46d0dab7b1c3e42b441bcc5484f82e6e4ad7718c1abf0b66961cf7 +size 42242272 diff --git a/IPythia-70m.i1-IQ3_XS.gguf b/IPythia-70m.i1-IQ3_XS.gguf new file mode 100644 index 0000000..8c280e5 --- /dev/null +++ b/IPythia-70m.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1948465ad2b0a8f86995c47aef72d7060e88e6e61af6d2c105d907e631f7a9f +size 41996512 diff --git a/IPythia-70m.i1-IQ3_XXS.gguf b/IPythia-70m.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..e27ffb9 --- /dev/null +++ b/IPythia-70m.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e3c3c29eb67b1cae3616cd75f9ffe8adc8e1a57e9d0fe984e13a5b6f226cdb0 +size 38010592 diff --git a/IPythia-70m.i1-IQ4_NL.gguf b/IPythia-70m.i1-IQ4_NL.gguf new file mode 100644 index 0000000..092b034 --- /dev/null +++ b/IPythia-70m.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ad767b22475597a6dbbc393bfcb89cf6cbf9d42f17fa66db859d79031dd33a8 +size 48169696 diff --git a/IPythia-70m.i1-IQ4_XS.gguf b/IPythia-70m.i1-IQ4_XS.gguf new file mode 100644 index 0000000..44a01df --- /dev/null +++ b/IPythia-70m.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2ac8d5d8c0af239363eadb49a416b69d4fbd90ab813338ba15f017b98fedb0b +size 46775008 diff --git a/IPythia-70m.i1-Q2_K.gguf b/IPythia-70m.i1-Q2_K.gguf new file mode 100644 index 0000000..f455544 --- /dev/null +++ b/IPythia-70m.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6210221b7d4b8e29b074dd0e30d65afbfe20bfce55f24beb4f95abf503e081fd +size 38508256 diff --git a/IPythia-70m.i1-Q2_K_S.gguf b/IPythia-70m.i1-Q2_K_S.gguf new file mode 100644 index 0000000..d58a3e1 --- /dev/null +++ b/IPythia-70m.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e92b5c60b82b17d9eaf56cbfb348cade0ae8c07795e501401731a427ca3c96b +size 37709536 diff --git a/IPythia-70m.i1-Q3_K_L.gguf b/IPythia-70m.i1-Q3_K_L.gguf new file mode 100644 index 0000000..6caa401 --- /dev/null +++ b/IPythia-70m.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:315bcb026e598ff06698c233318060b4ebeb8356f9bf6e23a9b06a2f436e5a84 +size 44896480 diff --git a/IPythia-70m.i1-Q3_K_M.gguf b/IPythia-70m.i1-Q3_K_M.gguf new file mode 100644 index 0000000..1c47ab1 --- /dev/null +++ b/IPythia-70m.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c147d753a71173553ae98e1f9f5c20be7fa22005bfe109e7eaa2a91d4286b33 +size 43913440 diff --git a/IPythia-70m.i1-Q3_K_S.gguf b/IPythia-70m.i1-Q3_K_S.gguf new file mode 100644 index 0000000..7d4426b --- /dev/null +++ b/IPythia-70m.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:589b9150433a6be07ef37011eb8489fec49a3dd4987f2865e4f95d426c82aac6 +size 42242272 diff --git a/IPythia-70m.i1-Q4_0.gguf b/IPythia-70m.i1-Q4_0.gguf new file mode 100644 index 0000000..1c23868 --- /dev/null +++ b/IPythia-70m.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71e4f2b08df529fd5604cf9d8e8a924d4435dfdda2beca0fab2801af17013431 +size 48169696 diff --git a/IPythia-70m.i1-Q4_1.gguf b/IPythia-70m.i1-Q4_1.gguf new file mode 100644 index 0000000..34b0afb --- /dev/null +++ b/IPythia-70m.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8898c1b736409e24eb60a9dbdc9ae5b9b02ed1a7ec24389654f3b1ff7bd90e5a +size 50959072 diff --git a/IPythia-70m.i1-Q4_K_M.gguf b/IPythia-70m.i1-Q4_K_M.gguf new file mode 100644 index 0000000..d1ab7a3 --- /dev/null +++ b/IPythia-70m.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:931f38f89f81064c5f4735b4773fb42c1cad0170d64513ccfc2b2c4eedb02b03 +size 49300192 diff --git a/IPythia-70m.i1-Q4_K_S.gguf b/IPythia-70m.i1-Q4_K_S.gguf new file mode 100644 index 0000000..3282e0f --- /dev/null +++ b/IPythia-70m.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0bb3a5db48bcc1f319143a09e63df9cd3520fdcdd03c5318fd7764415fce88ae +size 48169696 diff --git a/IPythia-70m.i1-Q5_K_M.gguf b/IPythia-70m.i1-Q5_K_M.gguf new file mode 100644 index 0000000..719fc43 --- /dev/null +++ b/IPythia-70m.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd11a4aa70783c3c3e035b2ab69710805950f53d996514c22236b8e1cc2bbb84 +size 54653664 diff --git a/IPythia-70m.i1-Q5_K_S.gguf b/IPythia-70m.i1-Q5_K_S.gguf new file mode 100644 index 0000000..20fb7f3 --- /dev/null +++ b/IPythia-70m.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ddb2ea1cfaa1c54acff1b36d9b318e106c0c6534ea7aecc87afbe4f92543e4d4 +size 53748448 diff --git a/IPythia-70m.i1-Q6_K.gguf b/IPythia-70m.i1-Q6_K.gguf new file mode 100644 index 0000000..a411de1 --- /dev/null +++ b/IPythia-70m.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11c848d9e2a1d9c780f6c89f9dd82e66e03ba0f6ffe2c1c6edad78c05a3dd603 +size 59675872 diff --git a/README.md b/README.md new file mode 100644 index 0000000..19e0e60 --- /dev/null +++ b/README.md @@ -0,0 +1,84 @@ +--- +base_model: GerbilLab/IPythia-70m +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- alpaca +- instruction +- pythia +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/GerbilLab/IPythia-70m + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#IPythia-70m-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/IPythia-70m-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/IPythia-70m-i1-GGUF/resolve/main/IPythia-70m.i1-IQ1_S.gguf) | i1-IQ1_S | 0.1 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/IPythia-70m-i1-GGUF/resolve/main/IPythia-70m.i1-IQ1_M.gguf) | i1-IQ1_M | 0.1 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/IPythia-70m-i1-GGUF/resolve/main/IPythia-70m.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 0.1 | | +| [GGUF](https://huggingface.co/mradermacher/IPythia-70m-i1-GGUF/resolve/main/IPythia-70m.i1-IQ2_XS.gguf) | i1-IQ2_XS | 0.1 | | +| [GGUF](https://huggingface.co/mradermacher/IPythia-70m-i1-GGUF/resolve/main/IPythia-70m.i1-IQ2_S.gguf) | i1-IQ2_S | 0.1 | | +| [GGUF](https://huggingface.co/mradermacher/IPythia-70m-i1-GGUF/resolve/main/IPythia-70m.i1-IQ2_M.gguf) | i1-IQ2_M | 0.1 | | +| [GGUF](https://huggingface.co/mradermacher/IPythia-70m-i1-GGUF/resolve/main/IPythia-70m.i1-Q2_K_S.gguf) | i1-Q2_K_S | 0.1 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/IPythia-70m-i1-GGUF/resolve/main/IPythia-70m.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 0.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/IPythia-70m-i1-GGUF/resolve/main/IPythia-70m.i1-Q2_K.gguf) | i1-Q2_K | 0.1 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/IPythia-70m-i1-GGUF/resolve/main/IPythia-70m.i1-IQ3_XS.gguf) | i1-IQ3_XS | 0.1 | | +| [GGUF](https://huggingface.co/mradermacher/IPythia-70m-i1-GGUF/resolve/main/IPythia-70m.i1-IQ3_S.gguf) | i1-IQ3_S | 0.1 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/IPythia-70m-i1-GGUF/resolve/main/IPythia-70m.i1-Q3_K_S.gguf) | i1-Q3_K_S | 0.1 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/IPythia-70m-i1-GGUF/resolve/main/IPythia-70m.i1-IQ3_M.gguf) | i1-IQ3_M | 0.1 | | +| [GGUF](https://huggingface.co/mradermacher/IPythia-70m-i1-GGUF/resolve/main/IPythia-70m.i1-Q3_K_M.gguf) | i1-Q3_K_M | 0.1 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/IPythia-70m-i1-GGUF/resolve/main/IPythia-70m.i1-Q3_K_L.gguf) | i1-Q3_K_L | 0.1 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/IPythia-70m-i1-GGUF/resolve/main/IPythia-70m.i1-IQ4_XS.gguf) | i1-IQ4_XS | 0.1 | | +| [GGUF](https://huggingface.co/mradermacher/IPythia-70m-i1-GGUF/resolve/main/IPythia-70m.i1-IQ4_NL.gguf) | i1-IQ4_NL | 0.1 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/IPythia-70m-i1-GGUF/resolve/main/IPythia-70m.i1-Q4_0.gguf) | i1-Q4_0 | 0.1 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/IPythia-70m-i1-GGUF/resolve/main/IPythia-70m.i1-Q4_K_S.gguf) | i1-Q4_K_S | 0.1 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/IPythia-70m-i1-GGUF/resolve/main/IPythia-70m.i1-Q4_K_M.gguf) | i1-Q4_K_M | 0.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/IPythia-70m-i1-GGUF/resolve/main/IPythia-70m.i1-Q4_1.gguf) | i1-Q4_1 | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/IPythia-70m-i1-GGUF/resolve/main/IPythia-70m.i1-Q5_K_S.gguf) | i1-Q5_K_S | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/IPythia-70m-i1-GGUF/resolve/main/IPythia-70m.i1-Q5_K_M.gguf) | i1-Q5_K_M | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/IPythia-70m-i1-GGUF/resolve/main/IPythia-70m.i1-Q6_K.gguf) | i1-Q6_K | 0.2 | 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/imatrix.dat b/imatrix.dat new file mode 100644 index 0000000..fa6ec73 Binary files /dev/null and b/imatrix.dat differ