commit 3ce10bac67ce1dfa3f67eb8d5d9636a45ba99ff7 Author: ModelHub XC Date: Mon Apr 13 04:19:55 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Hala-350M-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..9443d8d --- /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-350M.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +Hala-350M.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Hala-350M.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Hala-350M.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Hala-350M.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Hala-350M.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Hala-350M.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Hala-350M.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Hala-350M.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Hala-350M.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Hala-350M.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Hala-350M.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Hala-350M.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Hala-350M.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Hala-350M.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Hala-350M.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Hala-350M.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Hala-350M.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Hala-350M.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Hala-350M.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Hala-350M.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Hala-350M.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Hala-350M.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Hala-350M.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Hala-350M.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Hala-350M.i1-IQ1_M.gguf b/Hala-350M.i1-IQ1_M.gguf new file mode 100644 index 0000000..ea8266c --- /dev/null +++ b/Hala-350M.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e59d2fc348ac504edaa0a046bf6515a3d9bf4e48de494cab8ad3e3d8a2b3abbd +size 113255424 diff --git a/Hala-350M.i1-IQ1_S.gguf b/Hala-350M.i1-IQ1_S.gguf new file mode 100644 index 0000000..ae849e8 --- /dev/null +++ b/Hala-350M.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19a645c543c24718d1adc9e9876f1ff6a6aa787c40b9ec5fcf7a6892f6c1e483 +size 106963968 diff --git a/Hala-350M.i1-IQ2_M.gguf b/Hala-350M.i1-IQ2_M.gguf new file mode 100644 index 0000000..a834cfd --- /dev/null +++ b/Hala-350M.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01c3f987133761defb79b400e04e7023f2c3d5711d0c2b8de710b395d711d580 +size 142877696 diff --git a/Hala-350M.i1-IQ2_S.gguf b/Hala-350M.i1-IQ2_S.gguf new file mode 100644 index 0000000..301ffcc --- /dev/null +++ b/Hala-350M.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:144a1f075b1b6d389569093d6390391045fb84c100f8995a1ee7dbbd9b3ecce7 +size 134489088 diff --git a/Hala-350M.i1-IQ2_XS.gguf b/Hala-350M.i1-IQ2_XS.gguf new file mode 100644 index 0000000..0929b01 --- /dev/null +++ b/Hala-350M.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08a236a3e3a05ee5e81ed24b0962fb9b09b1a48319eea3c174bba1015ad335c8 +size 132326400 diff --git a/Hala-350M.i1-IQ2_XXS.gguf b/Hala-350M.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..83e24fd --- /dev/null +++ b/Hala-350M.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e2c3a8d34a0c2d193a6e191689c6c042d5bd645d9046d23ef6732e6598442ec +size 123741184 diff --git a/Hala-350M.i1-IQ3_M.gguf b/Hala-350M.i1-IQ3_M.gguf new file mode 100644 index 0000000..533a307 --- /dev/null +++ b/Hala-350M.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:511559594fea46cb99eb7b6bda97a11b546899fecc300b32e1411ca1d0cbcb85 +size 183657472 diff --git a/Hala-350M.i1-IQ3_S.gguf b/Hala-350M.i1-IQ3_S.gguf new file mode 100644 index 0000000..8487fa1 --- /dev/null +++ b/Hala-350M.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a365716a738956608125fe4d7543113a3bf89ffc3704dc230b95206de782d280 +size 181150720 diff --git a/Hala-350M.i1-IQ3_XS.gguf b/Hala-350M.i1-IQ3_XS.gguf new file mode 100644 index 0000000..c061afb --- /dev/null +++ b/Hala-350M.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e413badff5c10c3cfe2560f7f6f77a22127325562bcd0df1b976dd4559bf2d2 +size 175399936 diff --git a/Hala-350M.i1-IQ3_XXS.gguf b/Hala-350M.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..226419d --- /dev/null +++ b/Hala-350M.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95e4d79c97b52d4820741baa29014f7350c607acd57e7322d8161ab2a4941a04 +size 158475264 diff --git a/Hala-350M.i1-IQ4_NL.gguf b/Hala-350M.i1-IQ4_NL.gguf new file mode 100644 index 0000000..49e7bf8 --- /dev/null +++ b/Hala-350M.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c6c1ddeea1b60628b90fed8e9018029af1ebd167b067cd64ff7586705a951a0 +size 219309056 diff --git a/Hala-350M.i1-IQ4_XS.gguf b/Hala-350M.i1-IQ4_XS.gguf new file mode 100644 index 0000000..e8e5a1c --- /dev/null +++ b/Hala-350M.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee1d918074ee57ec1b571cf3ff4b7c7d46fa400bd135d5da5d031ff671de4cca +size 210330624 diff --git a/Hala-350M.i1-Q2_K.gguf b/Hala-350M.i1-Q2_K.gguf new file mode 100644 index 0000000..72ec97f --- /dev/null +++ b/Hala-350M.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab5385b7bc67a09a11feab74ca550a67eaad71f376096f11e5e2ef0250054000 +size 160596992 diff --git a/Hala-350M.i1-Q2_K_S.gguf b/Hala-350M.i1-Q2_K_S.gguf new file mode 100644 index 0000000..2ca5a14 --- /dev/null +++ b/Hala-350M.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3290592abdd08e92d5765afe596f3752c73aca0c3b9dbc046092b5519a29bdc +size 154182656 diff --git a/Hala-350M.i1-Q3_K_L.gguf b/Hala-350M.i1-Q3_K_L.gguf new file mode 100644 index 0000000..68e8e74 --- /dev/null +++ b/Hala-350M.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:30ce338dfd60ec08061152d2054f6d40d71e55f6df7753449ea6b54a671e0111 +size 203047936 diff --git a/Hala-350M.i1-Q3_K_M.gguf b/Hala-350M.i1-Q3_K_M.gguf new file mode 100644 index 0000000..44aa542 --- /dev/null +++ b/Hala-350M.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4596b793a55a8c0cecb2b999ec7be273e186bd983762e7207aecaadc6f9186f1 +size 193152000 diff --git a/Hala-350M.i1-Q3_K_S.gguf b/Hala-350M.i1-Q3_K_S.gguf new file mode 100644 index 0000000..99f7d95 --- /dev/null +++ b/Hala-350M.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:490c3f248d828867353fd5153665b7cd4f1bf5c4290cf0c51c484b777f792edf +size 181150720 diff --git a/Hala-350M.i1-Q4_0.gguf b/Hala-350M.i1-Q4_0.gguf new file mode 100644 index 0000000..b06771f --- /dev/null +++ b/Hala-350M.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15d8b1590867be1c260e6a0ce1a06a77d276610e8fdc4aae60b4294f8246734d +size 219898880 diff --git a/Hala-350M.i1-Q4_1.gguf b/Hala-350M.i1-Q4_1.gguf new file mode 100644 index 0000000..20f20fd --- /dev/null +++ b/Hala-350M.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f8df5123fc4174d223e01aa372f36b147a86295e38ee3152558f113320e55d9 +size 237265920 diff --git a/Hala-350M.i1-Q4_K_M.gguf b/Hala-350M.i1-Q4_K_M.gguf new file mode 100644 index 0000000..e73b81a --- /dev/null +++ b/Hala-350M.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0061925e8207aa61e909717ed098d1e18ea4e2a8ae7a09fa9bb502e4f38d1c60 +size 229311488 diff --git a/Hala-350M.i1-Q4_K_S.gguf b/Hala-350M.i1-Q4_K_S.gguf new file mode 100644 index 0000000..de87214 --- /dev/null +++ b/Hala-350M.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59c42b045cc067488be2fc86b957bd7ab681c398ebcce60d21199c60afe961c1 +size 220750848 diff --git a/Hala-350M.i1-Q5_K_M.gguf b/Hala-350M.i1-Q5_K_M.gguf new file mode 100644 index 0000000..f313e91 --- /dev/null +++ b/Hala-350M.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e20a7043d8ee1d7c65dd41587d7eed42f2f9710806b54ba9eb15bd358e778b40 +size 260375552 diff --git a/Hala-350M.i1-Q5_K_S.gguf b/Hala-350M.i1-Q5_K_S.gguf new file mode 100644 index 0000000..1960bd6 --- /dev/null +++ b/Hala-350M.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ee318cfcec558339e9bd49e7148f3cbca10108ea1e0e7a78be40a60b6031cd4 +size 255222784 diff --git a/Hala-350M.i1-Q6_K.gguf b/Hala-350M.i1-Q6_K.gguf new file mode 100644 index 0000000..5ba7205 --- /dev/null +++ b/Hala-350M.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c5ff49cb52e9e1f197282f23ce715a0b43ce32abb914679f4f71e7ad6e7ccb2 +size 293381120 diff --git a/Hala-350M.imatrix.gguf b/Hala-350M.imatrix.gguf new file mode 100644 index 0000000..53deac5 --- /dev/null +++ b/Hala-350M.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5cac47eac7b322eb2abcd4e9983bcad7aeb6a083cfa65f995a2552a1fedacab3 +size 620864 diff --git a/README.md b/README.md new file mode 100644 index 0000000..f1b6cfc --- /dev/null +++ b/README.md @@ -0,0 +1,87 @@ +--- +base_model: hammh0a/Hala-350M +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-350M + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Hala-350M-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/Hala-350M-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-350M-i1-GGUF/resolve/main/Hala-350M.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/Hala-350M-i1-GGUF/resolve/main/Hala-350M.i1-IQ1_S.gguf) | i1-IQ1_S | 0.2 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Hala-350M-i1-GGUF/resolve/main/Hala-350M.i1-IQ1_M.gguf) | i1-IQ1_M | 0.2 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Hala-350M-i1-GGUF/resolve/main/Hala-350M.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/Hala-350M-i1-GGUF/resolve/main/Hala-350M.i1-IQ2_XS.gguf) | i1-IQ2_XS | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/Hala-350M-i1-GGUF/resolve/main/Hala-350M.i1-IQ2_S.gguf) | i1-IQ2_S | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/Hala-350M-i1-GGUF/resolve/main/Hala-350M.i1-IQ2_M.gguf) | i1-IQ2_M | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/Hala-350M-i1-GGUF/resolve/main/Hala-350M.i1-Q2_K_S.gguf) | i1-Q2_K_S | 0.3 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Hala-350M-i1-GGUF/resolve/main/Hala-350M.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 0.3 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Hala-350M-i1-GGUF/resolve/main/Hala-350M.i1-Q2_K.gguf) | i1-Q2_K | 0.3 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Hala-350M-i1-GGUF/resolve/main/Hala-350M.i1-IQ3_XS.gguf) | i1-IQ3_XS | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/Hala-350M-i1-GGUF/resolve/main/Hala-350M.i1-IQ3_S.gguf) | i1-IQ3_S | 0.3 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Hala-350M-i1-GGUF/resolve/main/Hala-350M.i1-Q3_K_S.gguf) | i1-Q3_K_S | 0.3 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Hala-350M-i1-GGUF/resolve/main/Hala-350M.i1-IQ3_M.gguf) | i1-IQ3_M | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/Hala-350M-i1-GGUF/resolve/main/Hala-350M.i1-Q3_K_M.gguf) | i1-Q3_K_M | 0.3 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Hala-350M-i1-GGUF/resolve/main/Hala-350M.i1-Q3_K_L.gguf) | i1-Q3_K_L | 0.3 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Hala-350M-i1-GGUF/resolve/main/Hala-350M.i1-IQ4_XS.gguf) | i1-IQ4_XS | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/Hala-350M-i1-GGUF/resolve/main/Hala-350M.i1-IQ4_NL.gguf) | i1-IQ4_NL | 0.3 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Hala-350M-i1-GGUF/resolve/main/Hala-350M.i1-Q4_0.gguf) | i1-Q4_0 | 0.3 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Hala-350M-i1-GGUF/resolve/main/Hala-350M.i1-Q4_K_S.gguf) | i1-Q4_K_S | 0.3 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Hala-350M-i1-GGUF/resolve/main/Hala-350M.i1-Q4_K_M.gguf) | i1-Q4_K_M | 0.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Hala-350M-i1-GGUF/resolve/main/Hala-350M.i1-Q4_1.gguf) | i1-Q4_1 | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/Hala-350M-i1-GGUF/resolve/main/Hala-350M.i1-Q5_K_S.gguf) | i1-Q5_K_S | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Hala-350M-i1-GGUF/resolve/main/Hala-350M.i1-Q5_K_M.gguf) | i1-Q5_K_M | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Hala-350M-i1-GGUF/resolve/main/Hala-350M.i1-Q6_K.gguf) | i1-Q6_K | 0.4 | 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. + +