commit 2de7f9d8f440f1e79ad439cf867aadc2958b0b29 Author: ModelHub XC Date: Thu May 14 21:59:54 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Hare-1.1B-base-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..76dc9b8 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,50 @@ +*.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 +Hare-1.1B-base.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Hare-1.1B-base.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Hare-1.1B-base.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Hare-1.1B-base.f16.gguf filter=lfs diff=lfs merge=lfs -text +Hare-1.1B-base.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Hare-1.1B-base.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Hare-1.1B-base.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Hare-1.1B-base.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Hare-1.1B-base.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Hare-1.1B-base.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Hare-1.1B-base.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Hare-1.1B-base.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Hare-1.1B-base.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Hare-1.1B-base.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Hare-1.1B-base.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Hare-1.1B-base.IQ3_M.gguf b/Hare-1.1B-base.IQ3_M.gguf new file mode 100644 index 0000000..3c81504 --- /dev/null +++ b/Hare-1.1B-base.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:64630edc31f044435205df1a63f316693d6884b9173e03fc3a493988000bf39e +size 527631360 diff --git a/Hare-1.1B-base.IQ3_S.gguf b/Hare-1.1B-base.IQ3_S.gguf new file mode 100644 index 0000000..50c7ac7 --- /dev/null +++ b/Hare-1.1B-base.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0be5f8c362f2db380717011aeb7d545801d4bde1a08a14cc6211d8741dd51a8f +size 512312320 diff --git a/Hare-1.1B-base.IQ3_XS.gguf b/Hare-1.1B-base.IQ3_XS.gguf new file mode 100644 index 0000000..2c9e344 --- /dev/null +++ b/Hare-1.1B-base.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eaab65e5cd88b3708d7f664c4228c5acac58cb08affcc872bed6bfdd8dc394b3 +size 488522752 diff --git a/Hare-1.1B-base.IQ4_XS.gguf b/Hare-1.1B-base.IQ4_XS.gguf new file mode 100644 index 0000000..3e53397 --- /dev/null +++ b/Hare-1.1B-base.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:afe2190d48dd57527dde0c8da155a0ff8a661b0697f8cc56f52b50fa1cc4aee2 +size 623858688 diff --git a/Hare-1.1B-base.Q2_K.gguf b/Hare-1.1B-base.Q2_K.gguf new file mode 100644 index 0000000..648ad54 --- /dev/null +++ b/Hare-1.1B-base.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81296e6aa8d25db1ee987bf10d88d57bcb09294fc229af8cc75e0f2033fb92aa +size 442397696 diff --git a/Hare-1.1B-base.Q3_K_L.gguf b/Hare-1.1B-base.Q3_K_L.gguf new file mode 100644 index 0000000..d75cbdc --- /dev/null +++ b/Hare-1.1B-base.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e893abc892eea97b83d1fc5d1d56cae7f22a9e49bf8974cb34f0a048c1dea0eb +size 604406784 diff --git a/Hare-1.1B-base.Q3_K_M.gguf b/Hare-1.1B-base.Q3_K_M.gguf new file mode 100644 index 0000000..26c37e7 --- /dev/null +++ b/Hare-1.1B-base.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85ae437c86230035d414190d4b5dd698852148655875f7263bd0de54ab214f15 +size 559973376 diff --git a/Hare-1.1B-base.Q3_K_S.gguf b/Hare-1.1B-base.Q3_K_S.gguf new file mode 100644 index 0000000..775a9c5 --- /dev/null +++ b/Hare-1.1B-base.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e76496698e8932073ae1e6bbe18641884ac336f24a8531b67ecf97f4aef86a0 +size 509248512 diff --git a/Hare-1.1B-base.Q4_K_M.gguf b/Hare-1.1B-base.Q4_K_M.gguf new file mode 100644 index 0000000..060172c --- /dev/null +++ b/Hare-1.1B-base.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9bd6cea12aac02cc2b1574a89a61bdb543f633d1bd647dca747b7996deecc0df +size 682136576 diff --git a/Hare-1.1B-base.Q4_K_S.gguf b/Hare-1.1B-base.Q4_K_S.gguf new file mode 100644 index 0000000..2763fd9 --- /dev/null +++ b/Hare-1.1B-base.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:359144f315c9707f6c1ad08f33638bc20ae86a22b108e137b6098e9b16dae679 +size 653104128 diff --git a/Hare-1.1B-base.Q5_K_M.gguf b/Hare-1.1B-base.Q5_K_M.gguf new file mode 100644 index 0000000..9fc1214 --- /dev/null +++ b/Hare-1.1B-base.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0cd682dc12b3531587ff985d01463b524021aa3a236799dbc735edce25c4ca48 +size 798594048 diff --git a/Hare-1.1B-base.Q5_K_S.gguf b/Hare-1.1B-base.Q5_K_S.gguf new file mode 100644 index 0000000..9220bcd --- /dev/null +++ b/Hare-1.1B-base.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bbf1546ed9670ba6875f5821d852fb721a38a7731a85b345a7ebb1aa69d021d2 +size 781882368 diff --git a/Hare-1.1B-base.Q6_K.gguf b/Hare-1.1B-base.Q6_K.gguf new file mode 100644 index 0000000..798d90d --- /dev/null +++ b/Hare-1.1B-base.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9d348f40cea4aff3dfc29ce1c1912bcc49cb45fa224a5f89ef67fbbd23ba5af +size 922330112 diff --git a/Hare-1.1B-base.Q8_0.gguf b/Hare-1.1B-base.Q8_0.gguf new file mode 100644 index 0000000..0a7207b --- /dev/null +++ b/Hare-1.1B-base.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b233c63acb7511f97704c00cff6300598ba5b1c44e73edaacd871985e24fd1f8 +size 1194312704 diff --git a/Hare-1.1B-base.f16.gguf b/Hare-1.1B-base.f16.gguf new file mode 100644 index 0000000..bc8539e --- /dev/null +++ b/Hare-1.1B-base.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4572e429d821b19b1cb9fccfbd780d2e5f3023b1faded06688b4d08f558d7b0c +size 2247148544 diff --git a/README.md b/README.md new file mode 100644 index 0000000..ccf7b6a --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +arxiv: 2406.11410 +base_model: LiteAI-Team/Hare-1.1B-base +datasets: +- cerebras/SlimPajama-627B +- HuggingFaceTB/cosmopedia +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- Hare +--- +## About + + + + + + +static quants of https://huggingface.co/LiteAI-Team/Hare-1.1B-base + + +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/Hare-1.1B-base-GGUF/resolve/main/Hare-1.1B-base.Q2_K.gguf) | Q2_K | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Hare-1.1B-base-GGUF/resolve/main/Hare-1.1B-base.IQ3_XS.gguf) | IQ3_XS | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/Hare-1.1B-base-GGUF/resolve/main/Hare-1.1B-base.Q3_K_S.gguf) | Q3_K_S | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/Hare-1.1B-base-GGUF/resolve/main/Hare-1.1B-base.IQ3_S.gguf) | IQ3_S | 0.6 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Hare-1.1B-base-GGUF/resolve/main/Hare-1.1B-base.IQ3_M.gguf) | IQ3_M | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/Hare-1.1B-base-GGUF/resolve/main/Hare-1.1B-base.Q3_K_M.gguf) | Q3_K_M | 0.7 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Hare-1.1B-base-GGUF/resolve/main/Hare-1.1B-base.Q3_K_L.gguf) | Q3_K_L | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Hare-1.1B-base-GGUF/resolve/main/Hare-1.1B-base.IQ4_XS.gguf) | IQ4_XS | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Hare-1.1B-base-GGUF/resolve/main/Hare-1.1B-base.Q4_K_S.gguf) | Q4_K_S | 0.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Hare-1.1B-base-GGUF/resolve/main/Hare-1.1B-base.Q4_K_M.gguf) | Q4_K_M | 0.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Hare-1.1B-base-GGUF/resolve/main/Hare-1.1B-base.Q5_K_S.gguf) | Q5_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Hare-1.1B-base-GGUF/resolve/main/Hare-1.1B-base.Q5_K_M.gguf) | Q5_K_M | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Hare-1.1B-base-GGUF/resolve/main/Hare-1.1B-base.Q6_K.gguf) | Q6_K | 1.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Hare-1.1B-base-GGUF/resolve/main/Hare-1.1B-base.Q8_0.gguf) | Q8_0 | 1.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Hare-1.1B-base-GGUF/resolve/main/Hare-1.1B-base.f16.gguf) | f16 | 2.3 | 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. + +