commit 4a16083571749007baed68fde6446722cd9c1d9d Author: ModelHub XC Date: Mon Apr 13 06:19:57 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Hala-700M-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..9a7bc62 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,60 @@ +*.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 +Hala-700M.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +Hala-700M.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Hala-700M.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Hala-700M.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Hala-700M.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Hala-700M.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Hala-700M.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Hala-700M.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Hala-700M.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Hala-700M.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Hala-700M.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Hala-700M.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Hala-700M.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Hala-700M.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Hala-700M.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Hala-700M.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Hala-700M.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Hala-700M.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Hala-700M.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Hala-700M.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Hala-700M.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Hala-700M.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Hala-700M.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Hala-700M.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Hala-700M.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Hala-700M.i1-IQ1_M.gguf b/Hala-700M.i1-IQ1_M.gguf new file mode 100644 index 0000000..022f66d --- /dev/null +++ b/Hala-700M.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8446b8c128c1302a7404783846fe2c9aa45933e1facb877584c32ca8b98e0046 +size 215751680 diff --git a/Hala-700M.i1-IQ1_S.gguf b/Hala-700M.i1-IQ1_S.gguf new file mode 100644 index 0000000..b74d105 --- /dev/null +++ b/Hala-700M.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29327a6530792f911d99c3ef771a711161211e90419254d1506cf334ba97eb58 +size 201651200 diff --git a/Hala-700M.i1-IQ2_M.gguf b/Hala-700M.i1-IQ2_M.gguf new file mode 100644 index 0000000..ed92689 --- /dev/null +++ b/Hala-700M.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4f9cf50982567cd9d928c6a980341530e5a20fd701b41cb33d8b72de76ab1bc +size 281922560 diff --git a/Hala-700M.i1-IQ2_S.gguf b/Hala-700M.i1-IQ2_S.gguf new file mode 100644 index 0000000..42c24a4 --- /dev/null +++ b/Hala-700M.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8c073b296b15f314cb7cf7ee82a08a49908ba9087a322061f290cff284ad5af +size 263121920 diff --git a/Hala-700M.i1-IQ2_XS.gguf b/Hala-700M.i1-IQ2_XS.gguf new file mode 100644 index 0000000..1ceb6d2 --- /dev/null +++ b/Hala-700M.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0496c3732a6923a38b69b4eab1c886597df35a0dd55bb502d7cb5af3e2ae643b +size 258495488 diff --git a/Hala-700M.i1-IQ2_XXS.gguf b/Hala-700M.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..1cdf334 --- /dev/null +++ b/Hala-700M.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38b09ac0a708e0c11c2e11031786b3564ab225f1aab7b8054b07257ede8a03ff +size 239252480 diff --git a/Hala-700M.i1-IQ3_M.gguf b/Hala-700M.i1-IQ3_M.gguf new file mode 100644 index 0000000..5768eff --- /dev/null +++ b/Hala-700M.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e39bbc309d3d3d30400ffb2134a9d55fde71babfb16dcabfe73b683a2a118332 +size 366420992 diff --git a/Hala-700M.i1-IQ3_S.gguf b/Hala-700M.i1-IQ3_S.gguf new file mode 100644 index 0000000..b8afb57 --- /dev/null +++ b/Hala-700M.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f1acd0f4a554e2aa204e6d94d409700717c56d2067227b68f6b6d5070de1bfd +size 361094144 diff --git a/Hala-700M.i1-IQ3_XS.gguf b/Hala-700M.i1-IQ3_XS.gguf new file mode 100644 index 0000000..cad48f6 --- /dev/null +++ b/Hala-700M.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a3538380f439cfd43604baee8c0b2594d12beca8cfcee4ac7bc362c920771a7 +size 348265472 diff --git a/Hala-700M.i1-IQ3_XXS.gguf b/Hala-700M.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..079d2c4 --- /dev/null +++ b/Hala-700M.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:251d9937881ec3d3448c90092be1f5c78809c9ca64e42a006b3e4da9600b9d7b +size 317127680 diff --git a/Hala-700M.i1-IQ4_NL.gguf b/Hala-700M.i1-IQ4_NL.gguf new file mode 100644 index 0000000..7bb3d4b --- /dev/null +++ b/Hala-700M.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2fe2aea77d06ba0bd39abe2dcbabc78a5711d4b267238f3f55ce738611be2ff5 +size 446323712 diff --git a/Hala-700M.i1-IQ4_XS.gguf b/Hala-700M.i1-IQ4_XS.gguf new file mode 100644 index 0000000..049326c --- /dev/null +++ b/Hala-700M.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42ba0dc110a0c84c5e51e5ad15aeb2f26e36ac931c6c56cb2ebfb802e66476e4 +size 426269696 diff --git a/Hala-700M.i1-Q2_K.gguf b/Hala-700M.i1-Q2_K.gguf new file mode 100644 index 0000000..2b1ba10 --- /dev/null +++ b/Hala-700M.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9db304f4e087f9e52610f716b3602d6baeb8c1499b8552a1410589291a74f8d1 +size 315087872 diff --git a/Hala-700M.i1-Q2_K_S.gguf b/Hala-700M.i1-Q2_K_S.gguf new file mode 100644 index 0000000..530a9c1 --- /dev/null +++ b/Hala-700M.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e08cbc10462941ca7f2833cb33b619d8dd3ceea031ee406a2a5e1f05b61d897a +size 300895232 diff --git a/Hala-700M.i1-Q3_K_L.gguf b/Hala-700M.i1-Q3_K_L.gguf new file mode 100644 index 0000000..e788ec4 --- /dev/null +++ b/Hala-700M.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:330fc7815c71ac4155cfd58f334d55dc52beee9faff86bc9c08e209d7e095a95 +size 409754624 diff --git a/Hala-700M.i1-Q3_K_M.gguf b/Hala-700M.i1-Q3_K_M.gguf new file mode 100644 index 0000000..060753b --- /dev/null +++ b/Hala-700M.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f836db6119f27b24d564420cb0e9d5b9a8f9528113952ced67d5f7fac50b1b2f +size 387685376 diff --git a/Hala-700M.i1-Q3_K_S.gguf b/Hala-700M.i1-Q3_K_S.gguf new file mode 100644 index 0000000..6267ffe --- /dev/null +++ b/Hala-700M.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7a953353cd628dcdd2b901d2b4529340a695e8da18580fae5ecb88a34f1d714 +size 361094144 diff --git a/Hala-700M.i1-Q4_0.gguf b/Hala-700M.i1-Q4_0.gguf new file mode 100644 index 0000000..ce4a2ce --- /dev/null +++ b/Hala-700M.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e86ebce125bb40fb1a5515cf45e5e34c96681ac78e25fb33403625909879f9c +size 447650816 diff --git a/Hala-700M.i1-Q4_1.gguf b/Hala-700M.i1-Q4_1.gguf new file mode 100644 index 0000000..c5a7355 --- /dev/null +++ b/Hala-700M.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58fd76db26f9b0f5356a98c0a2183cac88bfa62cc7641514bead000b6a38b0c0 +size 486431744 diff --git a/Hala-700M.i1-Q4_K_M.gguf b/Hala-700M.i1-Q4_K_M.gguf new file mode 100644 index 0000000..6099eff --- /dev/null +++ b/Hala-700M.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c909bff0614af9e136e5dac6259f475173f5aab3cae406b99bfa9863302dd02 +size 468626432 diff --git a/Hala-700M.i1-Q4_K_S.gguf b/Hala-700M.i1-Q4_K_S.gguf new file mode 100644 index 0000000..5162494 --- /dev/null +++ b/Hala-700M.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a9e528c0ad025b7f4471bc7971837af290f50fae9c07745b66d241d6fc3c09d +size 449371136 diff --git a/Hala-700M.i1-Q5_K_M.gguf b/Hala-700M.i1-Q5_K_M.gguf new file mode 100644 index 0000000..2133d0f --- /dev/null +++ b/Hala-700M.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:447d5a69c1bfe1328802751f127f0436658f81f379746ffac09aed7730a382ac +size 538029056 diff --git a/Hala-700M.i1-Q5_K_S.gguf b/Hala-700M.i1-Q5_K_S.gguf new file mode 100644 index 0000000..c962edc --- /dev/null +++ b/Hala-700M.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:066395dae26ac91ed2cf7b21c7a711c07d2047f621bba71d7441f72d84461726 +size 526539776 diff --git a/Hala-700M.i1-Q6_K.gguf b/Hala-700M.i1-Q6_K.gguf new file mode 100644 index 0000000..7075969 --- /dev/null +++ b/Hala-700M.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b571c4248a9edb050ae4bb6562f3daad05f896372e6a7e48e7e64c1b13c1311 +size 611769344 diff --git a/Hala-700M.imatrix.gguf b/Hala-700M.imatrix.gguf new file mode 100644 index 0000000..a8aafaa --- /dev/null +++ b/Hala-700M.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1867fb1a547d882a5e82d150dfe8a1ba2a2550ab4586838ce1c36bcd0e0cd45c +size 923968 diff --git a/README.md b/README.md new file mode 100644 index 0000000..c78a770 --- /dev/null +++ b/README.md @@ -0,0 +1,87 @@ +--- +base_model: hammh0a/Hala-700M +datasets: +- hammh0a/Hala-4.6M-SFT +language: +- ar +library_name: transformers +license: cc-by-nc-4.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/hammh0a/Hala-700M + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Hala-700M-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/Hala-700M-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/Hala-700M-i1-GGUF/resolve/main/Hala-700M.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/Hala-700M-i1-GGUF/resolve/main/Hala-700M.i1-IQ1_S.gguf) | i1-IQ1_S | 0.3 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Hala-700M-i1-GGUF/resolve/main/Hala-700M.i1-IQ1_M.gguf) | i1-IQ1_M | 0.3 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Hala-700M-i1-GGUF/resolve/main/Hala-700M.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/Hala-700M-i1-GGUF/resolve/main/Hala-700M.i1-IQ2_XS.gguf) | i1-IQ2_XS | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Hala-700M-i1-GGUF/resolve/main/Hala-700M.i1-IQ2_S.gguf) | i1-IQ2_S | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Hala-700M-i1-GGUF/resolve/main/Hala-700M.i1-IQ2_M.gguf) | i1-IQ2_M | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Hala-700M-i1-GGUF/resolve/main/Hala-700M.i1-Q2_K_S.gguf) | i1-Q2_K_S | 0.4 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Hala-700M-i1-GGUF/resolve/main/Hala-700M.i1-Q2_K.gguf) | i1-Q2_K | 0.4 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Hala-700M-i1-GGUF/resolve/main/Hala-700M.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 0.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Hala-700M-i1-GGUF/resolve/main/Hala-700M.i1-IQ3_XS.gguf) | i1-IQ3_XS | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Hala-700M-i1-GGUF/resolve/main/Hala-700M.i1-IQ3_S.gguf) | i1-IQ3_S | 0.5 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Hala-700M-i1-GGUF/resolve/main/Hala-700M.i1-Q3_K_S.gguf) | i1-Q3_K_S | 0.5 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Hala-700M-i1-GGUF/resolve/main/Hala-700M.i1-IQ3_M.gguf) | i1-IQ3_M | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Hala-700M-i1-GGUF/resolve/main/Hala-700M.i1-Q3_K_M.gguf) | i1-Q3_K_M | 0.5 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Hala-700M-i1-GGUF/resolve/main/Hala-700M.i1-Q3_K_L.gguf) | i1-Q3_K_L | 0.5 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Hala-700M-i1-GGUF/resolve/main/Hala-700M.i1-IQ4_XS.gguf) | i1-IQ4_XS | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Hala-700M-i1-GGUF/resolve/main/Hala-700M.i1-IQ4_NL.gguf) | i1-IQ4_NL | 0.5 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Hala-700M-i1-GGUF/resolve/main/Hala-700M.i1-Q4_0.gguf) | i1-Q4_0 | 0.5 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Hala-700M-i1-GGUF/resolve/main/Hala-700M.i1-Q4_K_S.gguf) | i1-Q4_K_S | 0.5 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Hala-700M-i1-GGUF/resolve/main/Hala-700M.i1-Q4_K_M.gguf) | i1-Q4_K_M | 0.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Hala-700M-i1-GGUF/resolve/main/Hala-700M.i1-Q4_1.gguf) | i1-Q4_1 | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/Hala-700M-i1-GGUF/resolve/main/Hala-700M.i1-Q5_K_S.gguf) | i1-Q5_K_S | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/Hala-700M-i1-GGUF/resolve/main/Hala-700M.i1-Q5_K_M.gguf) | i1-Q5_K_M | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/Hala-700M-i1-GGUF/resolve/main/Hala-700M.i1-Q6_K.gguf) | i1-Q6_K | 0.7 | 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. + +