commit b34fdb560cab5795b772be462cdfd74470f6dc94 Author: ModelHub XC Date: Sun May 31 06:56:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Sailor-1.8B-chatml-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..871cf32 --- /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 +Sailor-1.8B-chatml.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Sailor-1.8B-chatml.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Sailor-1.8B-chatml.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Sailor-1.8B-chatml.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Sailor-1.8B-chatml.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Sailor-1.8B-chatml.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Sailor-1.8B-chatml.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Sailor-1.8B-chatml.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Sailor-1.8B-chatml.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Sailor-1.8B-chatml.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Sailor-1.8B-chatml.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Sailor-1.8B-chatml.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..c4d6950 --- /dev/null +++ b/README.md @@ -0,0 +1,75 @@ +--- +base_model: DuongTrongChi/Sailor-1.8B-chatml +datasets: +- generator +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- trl +- sft +- generated_from_trainer +--- +## About + + + + + + +static quants of https://huggingface.co/DuongTrongChi/Sailor-1.8B-chatml + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Sailor-1.8B-chatml-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/Sailor-1.8B-chatml-GGUF/resolve/main/Sailor-1.8B-chatml.Q2_K.gguf) | Q2_K | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Sailor-1.8B-chatml-GGUF/resolve/main/Sailor-1.8B-chatml.Q3_K_S.gguf) | Q3_K_S | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/Sailor-1.8B-chatml-GGUF/resolve/main/Sailor-1.8B-chatml.Q3_K_M.gguf) | Q3_K_M | 1.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Sailor-1.8B-chatml-GGUF/resolve/main/Sailor-1.8B-chatml.Q3_K_L.gguf) | Q3_K_L | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Sailor-1.8B-chatml-GGUF/resolve/main/Sailor-1.8B-chatml.IQ4_XS.gguf) | IQ4_XS | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Sailor-1.8B-chatml-GGUF/resolve/main/Sailor-1.8B-chatml.Q4_K_S.gguf) | Q4_K_S | 1.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Sailor-1.8B-chatml-GGUF/resolve/main/Sailor-1.8B-chatml.Q4_K_M.gguf) | Q4_K_M | 1.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Sailor-1.8B-chatml-GGUF/resolve/main/Sailor-1.8B-chatml.Q5_K_S.gguf) | Q5_K_S | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/Sailor-1.8B-chatml-GGUF/resolve/main/Sailor-1.8B-chatml.Q5_K_M.gguf) | Q5_K_M | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Sailor-1.8B-chatml-GGUF/resolve/main/Sailor-1.8B-chatml.Q6_K.gguf) | Q6_K | 1.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Sailor-1.8B-chatml-GGUF/resolve/main/Sailor-1.8B-chatml.Q8_0.gguf) | Q8_0 | 2.1 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Sailor-1.8B-chatml-GGUF/resolve/main/Sailor-1.8B-chatml.f16.gguf) | f16 | 3.8 | 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/Sailor-1.8B-chatml.IQ4_XS.gguf b/Sailor-1.8B-chatml.IQ4_XS.gguf new file mode 100644 index 0000000..e546b2c --- /dev/null +++ b/Sailor-1.8B-chatml.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d8b95c6aba84f3eb2900e4d9de900dee06c798b7e28732b2535e114ddd60fa3 +size 1086552576 diff --git a/Sailor-1.8B-chatml.Q2_K.gguf b/Sailor-1.8B-chatml.Q2_K.gguf new file mode 100644 index 0000000..0e2b7ae --- /dev/null +++ b/Sailor-1.8B-chatml.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:083231d678ae96fe4ee030c4d7354f1c0f304d3d7e1ccd2cf5b8f1d7d68afa3b +size 845881664 diff --git a/Sailor-1.8B-chatml.Q3_K_L.gguf b/Sailor-1.8B-chatml.Q3_K_L.gguf new file mode 100644 index 0000000..4370177 --- /dev/null +++ b/Sailor-1.8B-chatml.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc81b8884f25766490350f7a4357328123ed205310cd8fdcfa58b40ab60a50c2 +size 1055452576 diff --git a/Sailor-1.8B-chatml.Q3_K_M.gguf b/Sailor-1.8B-chatml.Q3_K_M.gguf new file mode 100644 index 0000000..2e822e0 --- /dev/null +++ b/Sailor-1.8B-chatml.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e6a9c318d44b963c9a54f890c70e6f5c385125f38f8aa1b6df4eedc6965c198 +size 1015131552 diff --git a/Sailor-1.8B-chatml.Q3_K_S.gguf b/Sailor-1.8B-chatml.Q3_K_S.gguf new file mode 100644 index 0000000..03cc5cc --- /dev/null +++ b/Sailor-1.8B-chatml.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1137a58edb90182a9f2605cd5566d5dafdac89c4bda95f2bc1fc86a28c99c02 +size 952823200 diff --git a/Sailor-1.8B-chatml.Q4_K_M.gguf b/Sailor-1.8B-chatml.Q4_K_M.gguf new file mode 100644 index 0000000..e5ed802 --- /dev/null +++ b/Sailor-1.8B-chatml.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7507d52c871b5b177b774bd3fae959ff2a6f074cf4d6f357826f362f7bd5597e +size 1216926080 diff --git a/Sailor-1.8B-chatml.Q4_K_S.gguf b/Sailor-1.8B-chatml.Q4_K_S.gguf new file mode 100644 index 0000000..94ac796 --- /dev/null +++ b/Sailor-1.8B-chatml.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e4cfcd9cd1f95a60075f4a724d86af64201e3e7d9494709bf5d86b27ca1a019 +size 1157435776 diff --git a/Sailor-1.8B-chatml.Q5_K_M.gguf b/Sailor-1.8B-chatml.Q5_K_M.gguf new file mode 100644 index 0000000..bd0fad5 --- /dev/null +++ b/Sailor-1.8B-chatml.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8b3edb62787dc61d3b46923a4849a340a12113a8f8fe10c35feda62c0d6bf42 +size 1375874944 diff --git a/Sailor-1.8B-chatml.Q5_K_S.gguf b/Sailor-1.8B-chatml.Q5_K_S.gguf new file mode 100644 index 0000000..cf71cfb --- /dev/null +++ b/Sailor-1.8B-chatml.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d0db1a9aecd9226b8caf66497ec3cc794533ea56ac295f84a8fbdf855f50b80 +size 1326919552 diff --git a/Sailor-1.8B-chatml.Q6_K.gguf b/Sailor-1.8B-chatml.Q6_K.gguf new file mode 100644 index 0000000..a12becc --- /dev/null +++ b/Sailor-1.8B-chatml.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa8c4dbabdd6517cd08ecb9400b0b7f7e55c45b2bd21541c7bcff7b4f5f287d6 +size 1578046304 diff --git a/Sailor-1.8B-chatml.Q8_0.gguf b/Sailor-1.8B-chatml.Q8_0.gguf new file mode 100644 index 0000000..c3d82ab --- /dev/null +++ b/Sailor-1.8B-chatml.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16b3690be85fb2f178a4393d74ea627e91c2ef00647f625dc9478446c0fd8d06 +size 1957035936 diff --git a/Sailor-1.8B-chatml.f16.gguf b/Sailor-1.8B-chatml.f16.gguf new file mode 100644 index 0000000..f84f8da --- /dev/null +++ b/Sailor-1.8B-chatml.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c80dcf08db5fac3965c9f65f31277c4ceaa748d0d4cae723d8541778b2fbdad2 +size 3677716896