commit 455269c23a984d5376b42c60e7e8c4b139d4b0e3 Author: ModelHub XC Date: Mon Apr 13 09:23:59 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/SJT-4B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..9391003 --- /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 +SJT-4B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +SJT-4B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +SJT-4B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +SJT-4B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SJT-4B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SJT-4B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SJT-4B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SJT-4B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SJT-4B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SJT-4B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +SJT-4B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +SJT-4B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..285264f --- /dev/null +++ b/README.md @@ -0,0 +1,79 @@ +--- +base_model: Sakalti/SJT-4B +datasets: +- yahma/alpaca-cleaned +- HachiML/Hachi-Alpaca +language: +- en +library_name: transformers +license: mit +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- trl +- sft +--- +## About + + + + + + +static quants of https://huggingface.co/Sakalti/SJT-4B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#SJT-4B-GGUF).*** + +weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. +## 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/SJT-4B-GGUF/resolve/main/SJT-4B.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/SJT-4B-GGUF/resolve/main/SJT-4B.Q3_K_S.gguf) | Q3_K_S | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/SJT-4B-GGUF/resolve/main/SJT-4B.Q3_K_M.gguf) | Q3_K_M | 2.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/SJT-4B-GGUF/resolve/main/SJT-4B.Q3_K_L.gguf) | Q3_K_L | 2.1 | | +| [GGUF](https://huggingface.co/mradermacher/SJT-4B-GGUF/resolve/main/SJT-4B.IQ4_XS.gguf) | IQ4_XS | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/SJT-4B-GGUF/resolve/main/SJT-4B.Q4_K_S.gguf) | Q4_K_S | 2.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/SJT-4B-GGUF/resolve/main/SJT-4B.Q4_K_M.gguf) | Q4_K_M | 2.4 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/SJT-4B-GGUF/resolve/main/SJT-4B.Q5_K_S.gguf) | Q5_K_S | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/SJT-4B-GGUF/resolve/main/SJT-4B.Q5_K_M.gguf) | Q5_K_M | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/SJT-4B-GGUF/resolve/main/SJT-4B.Q6_K.gguf) | Q6_K | 3.2 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/SJT-4B-GGUF/resolve/main/SJT-4B.Q8_0.gguf) | Q8_0 | 4.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/SJT-4B-GGUF/resolve/main/SJT-4B.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/SJT-4B.IQ4_XS.gguf b/SJT-4B.IQ4_XS.gguf new file mode 100644 index 0000000..2305d2d --- /dev/null +++ b/SJT-4B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:786ce54073d7a24433f21ffac9eae826d3329f8c76d2f7488600f457b0f7b580 +size 2075588288 diff --git a/SJT-4B.Q2_K.gguf b/SJT-4B.Q2_K.gguf new file mode 100644 index 0000000..75e3c17 --- /dev/null +++ b/SJT-4B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dec9d187b09a339d54eb2323651777348cef85044e861cb98a5eb66f91f7f06e +size 1446881984 diff --git a/SJT-4B.Q3_K_L.gguf b/SJT-4B.Q3_K_L.gguf new file mode 100644 index 0000000..2289bbf --- /dev/null +++ b/SJT-4B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b93518b9e43f3be9d097af2064e6d0a081cab692679ce4be270670ac5fbd221 +size 2045137088 diff --git a/SJT-4B.Q3_K_M.gguf b/SJT-4B.Q3_K_M.gguf new file mode 100644 index 0000000..0a3de27 --- /dev/null +++ b/SJT-4B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1fd0a7780a473934c49f6718b76992d7720736c5eb9f3569efd52a02fcc50624 +size 1877627072 diff --git a/SJT-4B.Q3_K_S.gguf b/SJT-4B.Q3_K_S.gguf new file mode 100644 index 0000000..bf3655e --- /dev/null +++ b/SJT-4B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de0785cbee9c48cbac825e488190b7a2a4153c0843f1fe93791fafc1dbf60426 +size 1681805504 diff --git a/SJT-4B.Q4_K_M.gguf b/SJT-4B.Q4_K_M.gguf new file mode 100644 index 0000000..b9c0544 --- /dev/null +++ b/SJT-4B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91a051060f906c0a3f43db54385b2bf366522256b91d1f08e9b00e26aef7a489 +size 2318921408 diff --git a/SJT-4B.Q4_K_S.gguf b/SJT-4B.Q4_K_S.gguf new file mode 100644 index 0000000..58bb815 --- /dev/null +++ b/SJT-4B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8997c1c01c9cd25bb440ba961aec717bc655330027d08b0d014ba25c8ad82eb2 +size 2193485504 diff --git a/SJT-4B.Q5_K_M.gguf b/SJT-4B.Q5_K_M.gguf new file mode 100644 index 0000000..b087521 --- /dev/null +++ b/SJT-4B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0601937ece84553e7e35c8a42c7c851eee92cde5a321dbd6d6b3b5e2f00993e2 +size 2715012800 diff --git a/SJT-4B.Q5_K_S.gguf b/SJT-4B.Q5_K_S.gguf new file mode 100644 index 0000000..c448410 --- /dev/null +++ b/SJT-4B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24df7d9076cf5e2bfbf89585d5f699c5ee174e182ab8ed331d38f706929251af +size 2641481408 diff --git a/SJT-4B.Q6_K.gguf b/SJT-4B.Q6_K.gguf new file mode 100644 index 0000000..47cf643 --- /dev/null +++ b/SJT-4B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e10178e39cab62df90c0ee2fe3ea06fcfe2a9c228d340f462710b9f93a683212 +size 3135859904 diff --git a/SJT-4B.Q8_0.gguf b/SJT-4B.Q8_0.gguf new file mode 100644 index 0000000..f8e0391 --- /dev/null +++ b/SJT-4B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8eda02070817953f99a672f71507b477cabb4747ad0ce4893cb093cdba40e0d7 +size 4061229248 diff --git a/SJT-4B.f16.gguf b/SJT-4B.f16.gguf new file mode 100644 index 0000000..2ecf4dc --- /dev/null +++ b/SJT-4B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b562bdd2b7eb408ffe836d2c5aae021d3bc94b95af25b88ade6f7512c3df025 +size 7643304128