commit d2bf1fba20b048278dfc1254965c821bacb45f25 Author: ModelHub XC Date: Wed Jun 3 22:57:21 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/CHEETAH-350M-Merged-FP16-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..e86dca8 --- /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 +CHEETAH-350M-Merged-FP16.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +CHEETAH-350M-Merged-FP16.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +CHEETAH-350M-Merged-FP16.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +CHEETAH-350M-Merged-FP16.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +CHEETAH-350M-Merged-FP16.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +CHEETAH-350M-Merged-FP16.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +CHEETAH-350M-Merged-FP16.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +CHEETAH-350M-Merged-FP16.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +CHEETAH-350M-Merged-FP16.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +CHEETAH-350M-Merged-FP16.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +CHEETAH-350M-Merged-FP16.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +CHEETAH-350M-Merged-FP16.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/CHEETAH-350M-Merged-FP16.IQ4_XS.gguf b/CHEETAH-350M-Merged-FP16.IQ4_XS.gguf new file mode 100644 index 0000000..d2f18b1 --- /dev/null +++ b/CHEETAH-350M-Merged-FP16.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:debfe054d473c7d121547e11a3564f574df6753b3b92bea73d9108a3d35be77e +size 211805152 diff --git a/CHEETAH-350M-Merged-FP16.Q2_K.gguf b/CHEETAH-350M-Merged-FP16.Q2_K.gguf new file mode 100644 index 0000000..9024112 --- /dev/null +++ b/CHEETAH-350M-Merged-FP16.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c0aceccdbe421981207b104320d56e772a657d09caa2839055faa474e424ed5 +size 160596960 diff --git a/CHEETAH-350M-Merged-FP16.Q3_K_L.gguf b/CHEETAH-350M-Merged-FP16.Q3_K_L.gguf new file mode 100644 index 0000000..02d7d1c --- /dev/null +++ b/CHEETAH-350M-Merged-FP16.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af0aa782e0ba5dd578ecc2efd50d62ed46194060ffbddb0c3e4a99438bc64c0e +size 203047904 diff --git a/CHEETAH-350M-Merged-FP16.Q3_K_M.gguf b/CHEETAH-350M-Merged-FP16.Q3_K_M.gguf new file mode 100644 index 0000000..4b1b9d5 --- /dev/null +++ b/CHEETAH-350M-Merged-FP16.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6dd1d0a2eba023d986881a362bee176b17bdf6b384d84103c5694a7a485f752 +size 193151968 diff --git a/CHEETAH-350M-Merged-FP16.Q3_K_S.gguf b/CHEETAH-350M-Merged-FP16.Q3_K_S.gguf new file mode 100644 index 0000000..e1892c4 --- /dev/null +++ b/CHEETAH-350M-Merged-FP16.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:111896bb0b1de4a5fa62a662cbb3d28a9b299a1c31dea4c13e94b418e8b42b77 +size 181150688 diff --git a/CHEETAH-350M-Merged-FP16.Q4_K_M.gguf b/CHEETAH-350M-Merged-FP16.Q4_K_M.gguf new file mode 100644 index 0000000..5aaf866 --- /dev/null +++ b/CHEETAH-350M-Merged-FP16.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cbaaa4b1635e32dabed6d5a30b00f8df3bfa16621ee6a58ab616b677ba1fc5b2 +size 229311456 diff --git a/CHEETAH-350M-Merged-FP16.Q4_K_S.gguf b/CHEETAH-350M-Merged-FP16.Q4_K_S.gguf new file mode 100644 index 0000000..3305d27 --- /dev/null +++ b/CHEETAH-350M-Merged-FP16.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62b233db69db1e8f31c9d2800744307520855ea7daa4c37c2214e791f59ea8fb +size 220750816 diff --git a/CHEETAH-350M-Merged-FP16.Q5_K_M.gguf b/CHEETAH-350M-Merged-FP16.Q5_K_M.gguf new file mode 100644 index 0000000..f3cd7f4 --- /dev/null +++ b/CHEETAH-350M-Merged-FP16.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9029c1c640835d095164b2cc60d75b8f742f2abe8bb29e30fde8c8a61cadd4d +size 260375520 diff --git a/CHEETAH-350M-Merged-FP16.Q5_K_S.gguf b/CHEETAH-350M-Merged-FP16.Q5_K_S.gguf new file mode 100644 index 0000000..23802bb --- /dev/null +++ b/CHEETAH-350M-Merged-FP16.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82d02e9edd73f104139dc866eb117d8ac1ec77a7803d42b7bd0979185866d900 +size 255222752 diff --git a/CHEETAH-350M-Merged-FP16.Q6_K.gguf b/CHEETAH-350M-Merged-FP16.Q6_K.gguf new file mode 100644 index 0000000..7a1ca55 --- /dev/null +++ b/CHEETAH-350M-Merged-FP16.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:676c0405be3fb5fffba79a3b27d04d83a7cd390ab2e36896f622fa8cef6e0524 +size 293381088 diff --git a/CHEETAH-350M-Merged-FP16.Q8_0.gguf b/CHEETAH-350M-Merged-FP16.Q8_0.gguf new file mode 100644 index 0000000..5b68a94 --- /dev/null +++ b/CHEETAH-350M-Merged-FP16.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3389a4065960d6a20f9dc2118fe21e9eba1c2f042aadb876c360ccb0ec9efb15 +size 379216864 diff --git a/CHEETAH-350M-Merged-FP16.f16.gguf b/CHEETAH-350M-Merged-FP16.f16.gguf new file mode 100644 index 0000000..ae7e35d --- /dev/null +++ b/CHEETAH-350M-Merged-FP16.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89f365db79cb25720415a0fccbb504c6961d10539db24f2f3c953553dad29344 +size 711484384 diff --git a/README.md b/README.md new file mode 100644 index 0000000..2219a38 --- /dev/null +++ b/README.md @@ -0,0 +1,84 @@ +--- +base_model: Tralalabs/CHEETAH-350M-Merged-FP16 +datasets: +- HuggingFaceTB/smol-smoltalk +language: +- en +library_name: transformers +license: other +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- cheetah +- cheetah-350m +- lfm2 +- liquid-ai +- merged +- fp16 +- instruction-tuned +- text-generation +- modal +--- +## About + + + + + + + + + +static quants of https://huggingface.co/Tralalabs/CHEETAH-350M-Merged-FP16 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#CHEETAH-350M-Merged-FP16-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/CHEETAH-350M-Merged-FP16-i1-GGUF +## 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/CHEETAH-350M-Merged-FP16-GGUF/resolve/main/CHEETAH-350M-Merged-FP16.Q2_K.gguf) | Q2_K | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/CHEETAH-350M-Merged-FP16-GGUF/resolve/main/CHEETAH-350M-Merged-FP16.Q3_K_S.gguf) | Q3_K_S | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/CHEETAH-350M-Merged-FP16-GGUF/resolve/main/CHEETAH-350M-Merged-FP16.Q3_K_M.gguf) | Q3_K_M | 0.3 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/CHEETAH-350M-Merged-FP16-GGUF/resolve/main/CHEETAH-350M-Merged-FP16.Q3_K_L.gguf) | Q3_K_L | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/CHEETAH-350M-Merged-FP16-GGUF/resolve/main/CHEETAH-350M-Merged-FP16.IQ4_XS.gguf) | IQ4_XS | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/CHEETAH-350M-Merged-FP16-GGUF/resolve/main/CHEETAH-350M-Merged-FP16.Q4_K_S.gguf) | Q4_K_S | 0.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/CHEETAH-350M-Merged-FP16-GGUF/resolve/main/CHEETAH-350M-Merged-FP16.Q4_K_M.gguf) | Q4_K_M | 0.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/CHEETAH-350M-Merged-FP16-GGUF/resolve/main/CHEETAH-350M-Merged-FP16.Q5_K_S.gguf) | Q5_K_S | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/CHEETAH-350M-Merged-FP16-GGUF/resolve/main/CHEETAH-350M-Merged-FP16.Q5_K_M.gguf) | Q5_K_M | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/CHEETAH-350M-Merged-FP16-GGUF/resolve/main/CHEETAH-350M-Merged-FP16.Q6_K.gguf) | Q6_K | 0.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/CHEETAH-350M-Merged-FP16-GGUF/resolve/main/CHEETAH-350M-Merged-FP16.Q8_0.gguf) | Q8_0 | 0.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/CHEETAH-350M-Merged-FP16-GGUF/resolve/main/CHEETAH-350M-Merged-FP16.f16.gguf) | f16 | 0.8 | 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. + +