commit 85884afa6084d632fe25b94dacf01a06bcd9bae1 Author: ModelHub XC Date: Tue May 19 13:30:06 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Hala-9B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..ad06f8e --- /dev/null +++ b/.gitattributes @@ -0,0 +1,47 @@ +*.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-9B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Hala-9B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Hala-9B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Hala-9B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Hala-9B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Hala-9B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Hala-9B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Hala-9B.f16.gguf filter=lfs diff=lfs merge=lfs -text +Hala-9B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Hala-9B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Hala-9B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Hala-9B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Hala-9B.IQ4_XS.gguf b/Hala-9B.IQ4_XS.gguf new file mode 100644 index 0000000..eb555d1 --- /dev/null +++ b/Hala-9B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef33da52e2d9ccbb5d845d9c67a7785edb62c4eece8e2375aacce041823b56c7 +size 4844594272 diff --git a/Hala-9B.Q2_K.gguf b/Hala-9B.Q2_K.gguf new file mode 100644 index 0000000..1cff9ec --- /dev/null +++ b/Hala-9B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a5712b54225301120f4297e0c73199add8fcff32c48efbbf1cb6b81f6c9dde7 +size 3426821216 diff --git a/Hala-9B.Q3_K_L.gguf b/Hala-9B.Q3_K_L.gguf new file mode 100644 index 0000000..eaaad62 --- /dev/null +++ b/Hala-9B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a947ef050806f1c6b726549ae1582c746d4e6af0b9530bf6482792d212828ce +size 4753876064 diff --git a/Hala-9B.Q3_K_M.gguf b/Hala-9B.Q3_K_M.gguf new file mode 100644 index 0000000..7932abe --- /dev/null +++ b/Hala-9B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3060f6fff5e867da3dac36e4ff2a90129043142cec75f90440119610d73c8c09 +size 4383204448 diff --git a/Hala-9B.Q3_K_S.gguf b/Hala-9B.Q3_K_S.gguf new file mode 100644 index 0000000..6df2fda --- /dev/null +++ b/Hala-9B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49d2a6429b007b65534c28502f300946ea91abbc4b77ff11c4b549ec3c1f3546 +size 3959088224 diff --git a/Hala-9B.Q4_K_M.gguf b/Hala-9B.Q4_K_M.gguf new file mode 100644 index 0000000..c0601a0 --- /dev/null +++ b/Hala-9B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93712f5a9495309afd7e50614328f8ae0c51820ae795fd2279ca63f567f41247 +size 5382480992 diff --git a/Hala-9B.Q4_K_S.gguf b/Hala-9B.Q4_K_S.gguf new file mode 100644 index 0000000..7597807 --- /dev/null +++ b/Hala-9B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb63592a5fd2433b847a69417ad3aaf837cca31b9911268cb9f118ee5b6d3619 +size 5100348512 diff --git a/Hala-9B.Q5_K_M.gguf b/Hala-9B.Q5_K_M.gguf new file mode 100644 index 0000000..bc11153 --- /dev/null +++ b/Hala-9B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:784975dfa1bdb513315cd3e7916c44897408fa0fd991c5115a3e77dd32fe9d00 +size 6268789856 diff --git a/Hala-9B.Q5_K_S.gguf b/Hala-9B.Q5_K_S.gguf new file mode 100644 index 0000000..388a095 --- /dev/null +++ b/Hala-9B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6625aa71a047d91749b63794b4ebfd20543bf99ac3b047ffb7c8471dc59c1dc +size 6105015392 diff --git a/Hala-9B.Q6_K.gguf b/Hala-9B.Q6_K.gguf new file mode 100644 index 0000000..7433080 --- /dev/null +++ b/Hala-9B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8647081dc236123e8f63dd743b4613f9b3b2c258e946b1b220df465c25557d5c +size 7210493024 diff --git a/Hala-9B.Q8_0.gguf b/Hala-9B.Q8_0.gguf new file mode 100644 index 0000000..6b8ee45 --- /dev/null +++ b/Hala-9B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44c25d17be1a11f6d5e63a4a3116d122944bdb9348b50e1b205c81626072712d +size 9337690208 diff --git a/Hala-9B.f16.gguf b/Hala-9B.f16.gguf new file mode 100644 index 0000000..7864028 --- /dev/null +++ b/Hala-9B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0469f90600603f19e43beb4502665fa20973fafd7431c9accf21e821cb532e46 +size 17572001888 diff --git a/README.md b/README.md new file mode 100644 index 0000000..b4142d1 --- /dev/null +++ b/README.md @@ -0,0 +1,74 @@ +--- +base_model: hammh0a/Hala-9B +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 + + + + + + + + + +static quants of https://huggingface.co/hammh0a/Hala-9B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Hala-9B-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Hala-9B-i1-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-9B-GGUF/resolve/main/Hala-9B.Q2_K.gguf) | Q2_K | 3.5 | | +| [GGUF](https://huggingface.co/mradermacher/Hala-9B-GGUF/resolve/main/Hala-9B.Q3_K_S.gguf) | Q3_K_S | 4.1 | | +| [GGUF](https://huggingface.co/mradermacher/Hala-9B-GGUF/resolve/main/Hala-9B.Q3_K_M.gguf) | Q3_K_M | 4.5 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Hala-9B-GGUF/resolve/main/Hala-9B.Q3_K_L.gguf) | Q3_K_L | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/Hala-9B-GGUF/resolve/main/Hala-9B.IQ4_XS.gguf) | IQ4_XS | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/Hala-9B-GGUF/resolve/main/Hala-9B.Q4_K_S.gguf) | Q4_K_S | 5.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Hala-9B-GGUF/resolve/main/Hala-9B.Q4_K_M.gguf) | Q4_K_M | 5.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Hala-9B-GGUF/resolve/main/Hala-9B.Q5_K_S.gguf) | Q5_K_S | 6.2 | | +| [GGUF](https://huggingface.co/mradermacher/Hala-9B-GGUF/resolve/main/Hala-9B.Q5_K_M.gguf) | Q5_K_M | 6.4 | | +| [GGUF](https://huggingface.co/mradermacher/Hala-9B-GGUF/resolve/main/Hala-9B.Q6_K.gguf) | Q6_K | 7.3 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Hala-9B-GGUF/resolve/main/Hala-9B.Q8_0.gguf) | Q8_0 | 9.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Hala-9B-GGUF/resolve/main/Hala-9B.f16.gguf) | f16 | 17.7 | 16 bpw, overkill | + +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. + +