commit f5d95f37ec95a3e9e93956500104b61d5a64ed6b Author: ModelHub XC Date: Sun Jun 14 23:02:20 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/UST-1.5B-LORA-v1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..56750a8 --- /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 +UST-1.5B-LORA-v1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +UST-1.5B-LORA-v1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +UST-1.5B-LORA-v1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +UST-1.5B-LORA-v1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +UST-1.5B-LORA-v1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +UST-1.5B-LORA-v1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +UST-1.5B-LORA-v1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +UST-1.5B-LORA-v1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +UST-1.5B-LORA-v1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +UST-1.5B-LORA-v1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +UST-1.5B-LORA-v1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +UST-1.5B-LORA-v1.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..061c467 --- /dev/null +++ b/README.md @@ -0,0 +1,63 @@ +--- +base_model: Cartinoe5930/UST-1.5B-LORA-v1 +language: +- en +library_name: transformers +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/Cartinoe5930/UST-1.5B-LORA-v1 + + +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/UST-1.5B-LORA-v1-GGUF/resolve/main/UST-1.5B-LORA-v1.Q2_K.gguf) | Q2_K | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/UST-1.5B-LORA-v1-GGUF/resolve/main/UST-1.5B-LORA-v1.Q3_K_S.gguf) | Q3_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/UST-1.5B-LORA-v1-GGUF/resolve/main/UST-1.5B-LORA-v1.Q3_K_M.gguf) | Q3_K_M | 0.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/UST-1.5B-LORA-v1-GGUF/resolve/main/UST-1.5B-LORA-v1.Q3_K_L.gguf) | Q3_K_L | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/UST-1.5B-LORA-v1-GGUF/resolve/main/UST-1.5B-LORA-v1.IQ4_XS.gguf) | IQ4_XS | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/UST-1.5B-LORA-v1-GGUF/resolve/main/UST-1.5B-LORA-v1.Q4_K_S.gguf) | Q4_K_S | 1.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/UST-1.5B-LORA-v1-GGUF/resolve/main/UST-1.5B-LORA-v1.Q4_K_M.gguf) | Q4_K_M | 1.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/UST-1.5B-LORA-v1-GGUF/resolve/main/UST-1.5B-LORA-v1.Q5_K_S.gguf) | Q5_K_S | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/UST-1.5B-LORA-v1-GGUF/resolve/main/UST-1.5B-LORA-v1.Q5_K_M.gguf) | Q5_K_M | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/UST-1.5B-LORA-v1-GGUF/resolve/main/UST-1.5B-LORA-v1.Q6_K.gguf) | Q6_K | 1.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/UST-1.5B-LORA-v1-GGUF/resolve/main/UST-1.5B-LORA-v1.Q8_0.gguf) | Q8_0 | 1.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/UST-1.5B-LORA-v1-GGUF/resolve/main/UST-1.5B-LORA-v1.f16.gguf) | f16 | 3.2 | 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/UST-1.5B-LORA-v1.IQ4_XS.gguf b/UST-1.5B-LORA-v1.IQ4_XS.gguf new file mode 100644 index 0000000..6afb5ef --- /dev/null +++ b/UST-1.5B-LORA-v1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c82aeef0fc1aa7cceffc3c6b57cebacae49ec9d563775063ab8a87a906daba70 +size 902182816 diff --git a/UST-1.5B-LORA-v1.Q2_K.gguf b/UST-1.5B-LORA-v1.Q2_K.gguf new file mode 100644 index 0000000..2dd3a8a --- /dev/null +++ b/UST-1.5B-LORA-v1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85ad6cb34434e728c0e8791c84b1216635f33f44ba26d58cfecdfdb5a73fd6c5 +size 676304800 diff --git a/UST-1.5B-LORA-v1.Q3_K_L.gguf b/UST-1.5B-LORA-v1.Q3_K_L.gguf new file mode 100644 index 0000000..593b21b --- /dev/null +++ b/UST-1.5B-LORA-v1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f60d7dc44e46fadf2297a7f4cdae74db3e24876c5b7c3d50cafdb6d40000b1e2 +size 880162720 diff --git a/UST-1.5B-LORA-v1.Q3_K_M.gguf b/UST-1.5B-LORA-v1.Q3_K_M.gguf new file mode 100644 index 0000000..b072893 --- /dev/null +++ b/UST-1.5B-LORA-v1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:342309eb2c9444a26761e00d75eca23be757bcd87ac2cefe700942f0f377e635 +size 824178592 diff --git a/UST-1.5B-LORA-v1.Q3_K_S.gguf b/UST-1.5B-LORA-v1.Q3_K_S.gguf new file mode 100644 index 0000000..188b489 --- /dev/null +++ b/UST-1.5B-LORA-v1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e88fb2f331615867b6321410b5fa7a9ae3f7e9852c08c9050b9e440c1333abc1 +size 760944544 diff --git a/UST-1.5B-LORA-v1.Q4_K_M.gguf b/UST-1.5B-LORA-v1.Q4_K_M.gguf new file mode 100644 index 0000000..4c52196 --- /dev/null +++ b/UST-1.5B-LORA-v1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe74b7929d226d209a9332c271b5c0ea18cfc7eaa2c558103d1e0c05145e1d96 +size 986048416 diff --git a/UST-1.5B-LORA-v1.Q4_K_S.gguf b/UST-1.5B-LORA-v1.Q4_K_S.gguf new file mode 100644 index 0000000..c911d35 --- /dev/null +++ b/UST-1.5B-LORA-v1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd6e326d64ef3e5a0ad68c77fa0f8e3b4b34f0d309ecf95fb65db832bf7940da +size 940312480 diff --git a/UST-1.5B-LORA-v1.Q5_K_M.gguf b/UST-1.5B-LORA-v1.Q5_K_M.gguf new file mode 100644 index 0000000..b042cff --- /dev/null +++ b/UST-1.5B-LORA-v1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d250539a8720ba77855cec6e43f30c325383431d5543898c540a5861ede675ec +size 1125050272 diff --git a/UST-1.5B-LORA-v1.Q5_K_S.gguf b/UST-1.5B-LORA-v1.Q5_K_S.gguf new file mode 100644 index 0000000..6d7062c --- /dev/null +++ b/UST-1.5B-LORA-v1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c1c2382a218db317f07d01111d354fd14b0c96783eb8b998c3ca0a6682edac2 +size 1098729376 diff --git a/UST-1.5B-LORA-v1.Q6_K.gguf b/UST-1.5B-LORA-v1.Q6_K.gguf new file mode 100644 index 0000000..8cddbf6 --- /dev/null +++ b/UST-1.5B-LORA-v1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f97d7a5aa5ee25caa05e0c61afe9f8e7c901df6f4bf6c583b6e8c5a9d7a4387b +size 1272739744 diff --git a/UST-1.5B-LORA-v1.Q8_0.gguf b/UST-1.5B-LORA-v1.Q8_0.gguf new file mode 100644 index 0000000..1b65dd6 --- /dev/null +++ b/UST-1.5B-LORA-v1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc9b1588a923e8199d9defd9f71cd3e863387c576dfd0db3dc15d76a16ae7b69 +size 1646572960 diff --git a/UST-1.5B-LORA-v1.f16.gguf b/UST-1.5B-LORA-v1.f16.gguf new file mode 100644 index 0000000..cc081da --- /dev/null +++ b/UST-1.5B-LORA-v1.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:289f2495572523b753431d1079790446063b307212029ac1edc30c53f2d64362 +size 3093669280