commit 111d8a2c591b162fd7e8bde60ea6b7f7ee53de0b Author: ModelHub XC Date: Sat Apr 25 07:50:00 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Sailor2-L-1B-Chat-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..443d4bc --- /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 +Sailor2-L-1B-Chat.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Sailor2-L-1B-Chat.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Sailor2-L-1B-Chat.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Sailor2-L-1B-Chat.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Sailor2-L-1B-Chat.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Sailor2-L-1B-Chat.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Sailor2-L-1B-Chat.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Sailor2-L-1B-Chat.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Sailor2-L-1B-Chat.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Sailor2-L-1B-Chat.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Sailor2-L-1B-Chat.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Sailor2-L-1B-Chat.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..bc663e8 --- /dev/null +++ b/README.md @@ -0,0 +1,82 @@ +--- +base_model: sail/Sailor2-L-1B-Chat +language: +- en +- zh +- id +- th +- vi +- ms +- lo +- my +- jv +- km +- su +- tl +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- multilingual +- sea +- sailor +- sft +- chat +- instruction +--- +## About + + + + + + +static quants of https://huggingface.co/sail/Sailor2-L-1B-Chat + + +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/Sailor2-L-1B-Chat-GGUF/resolve/main/Sailor2-L-1B-Chat.Q3_K_S.gguf) | Q3_K_S | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Sailor2-L-1B-Chat-GGUF/resolve/main/Sailor2-L-1B-Chat.Q2_K.gguf) | Q2_K | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Sailor2-L-1B-Chat-GGUF/resolve/main/Sailor2-L-1B-Chat.IQ4_XS.gguf) | IQ4_XS | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Sailor2-L-1B-Chat-GGUF/resolve/main/Sailor2-L-1B-Chat.Q3_K_M.gguf) | Q3_K_M | 0.7 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Sailor2-L-1B-Chat-GGUF/resolve/main/Sailor2-L-1B-Chat.Q3_K_L.gguf) | Q3_K_L | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Sailor2-L-1B-Chat-GGUF/resolve/main/Sailor2-L-1B-Chat.Q4_K_S.gguf) | Q4_K_S | 0.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Sailor2-L-1B-Chat-GGUF/resolve/main/Sailor2-L-1B-Chat.Q4_K_M.gguf) | Q4_K_M | 0.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Sailor2-L-1B-Chat-GGUF/resolve/main/Sailor2-L-1B-Chat.Q5_K_S.gguf) | Q5_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Sailor2-L-1B-Chat-GGUF/resolve/main/Sailor2-L-1B-Chat.Q5_K_M.gguf) | Q5_K_M | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Sailor2-L-1B-Chat-GGUF/resolve/main/Sailor2-L-1B-Chat.Q6_K.gguf) | Q6_K | 1.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Sailor2-L-1B-Chat-GGUF/resolve/main/Sailor2-L-1B-Chat.Q8_0.gguf) | Q8_0 | 1.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Sailor2-L-1B-Chat-GGUF/resolve/main/Sailor2-L-1B-Chat.f16.gguf) | f16 | 2.1 | 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/Sailor2-L-1B-Chat.IQ4_XS.gguf b/Sailor2-L-1B-Chat.IQ4_XS.gguf new file mode 100644 index 0000000..59fdfd9 --- /dev/null +++ b/Sailor2-L-1B-Chat.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ede82b844e37c5776a9eaaf18dcce926ec7f360ad2bfae26ef9236c6dbef42e +size 628886048 diff --git a/Sailor2-L-1B-Chat.Q2_K.gguf b/Sailor2-L-1B-Chat.Q2_K.gguf new file mode 100644 index 0000000..97cd68d --- /dev/null +++ b/Sailor2-L-1B-Chat.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45339f8a0ce73f76eaf17ddde6a819cb772df58f557992089a6e47c1e6722a53 +size 603210272 diff --git a/Sailor2-L-1B-Chat.Q3_K_L.gguf b/Sailor2-L-1B-Chat.Q3_K_L.gguf new file mode 100644 index 0000000..5ae742f --- /dev/null +++ b/Sailor2-L-1B-Chat.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7781ef822561aacdcdc3c459f174e0ccd93c73990fa8f6aee71ebda6ae19ccd1 +size 664711712 diff --git a/Sailor2-L-1B-Chat.Q3_K_M.gguf b/Sailor2-L-1B-Chat.Q3_K_M.gguf new file mode 100644 index 0000000..05541c8 --- /dev/null +++ b/Sailor2-L-1B-Chat.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56f79420a96aa12c169c65ff9f73638c8708280d3202dfab53b5be1250aceee3 +size 637458976 diff --git a/Sailor2-L-1B-Chat.Q3_K_S.gguf b/Sailor2-L-1B-Chat.Q3_K_S.gguf new file mode 100644 index 0000000..02e9c87 --- /dev/null +++ b/Sailor2-L-1B-Chat.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce273be08a1de3bf66446abba79a8ba6a18873f74369bb5eaab67411f8f0ee56 +size 602522144 diff --git a/Sailor2-L-1B-Chat.Q4_K_M.gguf b/Sailor2-L-1B-Chat.Q4_K_M.gguf new file mode 100644 index 0000000..e3caa23 --- /dev/null +++ b/Sailor2-L-1B-Chat.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:947b98c20b24c686d1f85c49d3268e104b0b8a8eb983a81d71dacd4dc2011743 +size 738628128 diff --git a/Sailor2-L-1B-Chat.Q4_K_S.gguf b/Sailor2-L-1B-Chat.Q4_K_S.gguf new file mode 100644 index 0000000..bf815a6 --- /dev/null +++ b/Sailor2-L-1B-Chat.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20cca6ec2a7f36710bb428a282200ae52116f4674984aef7b01624c263b7a9ab +size 713927200 diff --git a/Sailor2-L-1B-Chat.Q5_K_M.gguf b/Sailor2-L-1B-Chat.Q5_K_M.gguf new file mode 100644 index 0000000..594cd20 --- /dev/null +++ b/Sailor2-L-1B-Chat.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d53a40cd7a91d7505d0cccf49ff0a12a9f0d0ba1f899c19cffd18c1b0c0490c +size 791692832 diff --git a/Sailor2-L-1B-Chat.Q5_K_S.gguf b/Sailor2-L-1B-Chat.Q5_K_S.gguf new file mode 100644 index 0000000..20f3681 --- /dev/null +++ b/Sailor2-L-1B-Chat.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33e99c101e7248909e35f039e793d35b70466d4d9e67fbf6816eb378ec86810e +size 776941088 diff --git a/Sailor2-L-1B-Chat.Q6_K.gguf b/Sailor2-L-1B-Chat.Q6_K.gguf new file mode 100644 index 0000000..e186d78 --- /dev/null +++ b/Sailor2-L-1B-Chat.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac7f2a07c87148b35be8fd1388b13372b24175532facbb98fdb0cd24af6e2f69 +size 1005535776 diff --git a/Sailor2-L-1B-Chat.Q8_0.gguf b/Sailor2-L-1B-Chat.Q8_0.gguf new file mode 100644 index 0000000..a0c5748 --- /dev/null +++ b/Sailor2-L-1B-Chat.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8ed6c8571b5678be896cdba0e8bb89873d8a585beae2911441853742664e4d9 +size 1056199200 diff --git a/Sailor2-L-1B-Chat.f16.gguf b/Sailor2-L-1B-Chat.f16.gguf new file mode 100644 index 0000000..73f3c94 --- /dev/null +++ b/Sailor2-L-1B-Chat.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34db59cf150c1e06bf24548f298d9b84d622fc63426f099d24d5e0029fdec72c +size 1982376480