commit 66b669dc8ceaf825e5b57ddb1f428904781fa0ac Author: ModelHub XC Date: Fri Jun 26 03:57:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Saka-3.8B-Coder-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..53504a1 --- /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 +Saka-3.8B-Coder.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Saka-3.8B-Coder.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Saka-3.8B-Coder.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Saka-3.8B-Coder.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Saka-3.8B-Coder.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Saka-3.8B-Coder.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Saka-3.8B-Coder.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Saka-3.8B-Coder.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Saka-3.8B-Coder.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Saka-3.8B-Coder.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Saka-3.8B-Coder.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Saka-3.8B-Coder.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..c0ec9a1 --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: Sakalti/Saka-3.8B-Coder +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/Sakalti/Saka-3.8B-Coder + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Saka-3.8B-Coder-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/Saka-3.8B-Coder-GGUF/resolve/main/Saka-3.8B-Coder.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Saka-3.8B-Coder-GGUF/resolve/main/Saka-3.8B-Coder.Q3_K_S.gguf) | Q3_K_S | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Saka-3.8B-Coder-GGUF/resolve/main/Saka-3.8B-Coder.Q3_K_M.gguf) | Q3_K_M | 2.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Saka-3.8B-Coder-GGUF/resolve/main/Saka-3.8B-Coder.IQ4_XS.gguf) | IQ4_XS | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/Saka-3.8B-Coder-GGUF/resolve/main/Saka-3.8B-Coder.Q3_K_L.gguf) | Q3_K_L | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/Saka-3.8B-Coder-GGUF/resolve/main/Saka-3.8B-Coder.Q4_K_S.gguf) | Q4_K_S | 2.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Saka-3.8B-Coder-GGUF/resolve/main/Saka-3.8B-Coder.Q4_K_M.gguf) | Q4_K_M | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Saka-3.8B-Coder-GGUF/resolve/main/Saka-3.8B-Coder.Q5_K_S.gguf) | Q5_K_S | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Saka-3.8B-Coder-GGUF/resolve/main/Saka-3.8B-Coder.Q5_K_M.gguf) | Q5_K_M | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Saka-3.8B-Coder-GGUF/resolve/main/Saka-3.8B-Coder.Q6_K.gguf) | Q6_K | 3.2 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Saka-3.8B-Coder-GGUF/resolve/main/Saka-3.8B-Coder.Q8_0.gguf) | Q8_0 | 4.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Saka-3.8B-Coder-GGUF/resolve/main/Saka-3.8B-Coder.f16.gguf) | f16 | 7.7 | 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. + + diff --git a/Saka-3.8B-Coder.IQ4_XS.gguf b/Saka-3.8B-Coder.IQ4_XS.gguf new file mode 100644 index 0000000..2c590f7 --- /dev/null +++ b/Saka-3.8B-Coder.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5406f05bea1f33d269d6fe8be90cd1d793de16eba3bad92f8504bd6b3ec9a4c +size 2075582176 diff --git a/Saka-3.8B-Coder.Q2_K.gguf b/Saka-3.8B-Coder.Q2_K.gguf new file mode 100644 index 0000000..1bd611b --- /dev/null +++ b/Saka-3.8B-Coder.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66f62f9010b567727164a4a8977ab8d745f4b018fed4c5aecb2853ec6e7e61e1 +size 1416205024 diff --git a/Saka-3.8B-Coder.Q3_K_L.gguf b/Saka-3.8B-Coder.Q3_K_L.gguf new file mode 100644 index 0000000..3056c1d --- /dev/null +++ b/Saka-3.8B-Coder.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08322078a838fc271e07c0552c9d9ce488ea7bc738b6a1a0484eb0334db40611 +size 2087598304 diff --git a/Saka-3.8B-Coder.Q3_K_M.gguf b/Saka-3.8B-Coder.Q3_K_M.gguf new file mode 100644 index 0000000..312614f --- /dev/null +++ b/Saka-3.8B-Coder.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f4abeefd21faec5c5936e6bc2d5812e1119a40c794ce7763b721856c0d743bb +size 1955477728 diff --git a/Saka-3.8B-Coder.Q3_K_S.gguf b/Saka-3.8B-Coder.Q3_K_S.gguf new file mode 100644 index 0000000..78af9b8 --- /dev/null +++ b/Saka-3.8B-Coder.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dcbf9531e5849e13d9a9eaeb902ff9e4f09d87c776de622fd3127381bd8251da +size 1681799392 diff --git a/Saka-3.8B-Coder.Q4_K_M.gguf b/Saka-3.8B-Coder.Q4_K_M.gguf new file mode 100644 index 0000000..bcd27c5 --- /dev/null +++ b/Saka-3.8B-Coder.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9015f989b682e9b9183cab73f59fcd069c1cbce1e44cb0e6d7a73c5e946a7a5 +size 2393233120 diff --git a/Saka-3.8B-Coder.Q4_K_S.gguf b/Saka-3.8B-Coder.Q4_K_S.gguf new file mode 100644 index 0000000..76ddd3e --- /dev/null +++ b/Saka-3.8B-Coder.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9dcdd49d59d238b99bd65d69121adb1a9b9431de61afca36ab14cce25d1b10e3 +size 2188760800 diff --git a/Saka-3.8B-Coder.Q5_K_M.gguf b/Saka-3.8B-Coder.Q5_K_M.gguf new file mode 100644 index 0000000..9452a13 --- /dev/null +++ b/Saka-3.8B-Coder.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34c4154fa0506c19a43482aae899b0741afa4ea5f3700ae2151ad8c448533141 +size 2815276768 diff --git a/Saka-3.8B-Coder.Q5_K_S.gguf b/Saka-3.8B-Coder.Q5_K_S.gguf new file mode 100644 index 0000000..91c7d78 --- /dev/null +++ b/Saka-3.8B-Coder.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b15d73f285789405f9adbed46dfde963e808b0e1e95591d8fc3921d1abf715f0 +size 2641475296 diff --git a/Saka-3.8B-Coder.Q6_K.gguf b/Saka-3.8B-Coder.Q6_K.gguf new file mode 100644 index 0000000..9743a26 --- /dev/null +++ b/Saka-3.8B-Coder.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:666ec9e47f676ccdfe608b4e72f3dfc5ffa597edb0b503e7bc2fde148184b451 +size 3135853792 diff --git a/Saka-3.8B-Coder.Q8_0.gguf b/Saka-3.8B-Coder.Q8_0.gguf new file mode 100644 index 0000000..762e822 --- /dev/null +++ b/Saka-3.8B-Coder.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:050d6a5765388ee7f189087de2f99f39a0163bb3e8e6ba4af4c71c96ed56d7af +size 4061223136 diff --git a/Saka-3.8B-Coder.f16.gguf b/Saka-3.8B-Coder.f16.gguf new file mode 100644 index 0000000..befbc47 --- /dev/null +++ b/Saka-3.8B-Coder.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e78169b5ef19e3721f2694404dc2adf218e2f89e8ff7b6eb37206ff52a18a020 +size 7643298016