commit f4caf01a4ba4bead694249d8d537cdf56d5a9e7f Author: ModelHub XC Date: Tue Jun 30 07:43:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/TinyLlama-R1-LIMO-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..367bc53 --- /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 +TinyLlama-R1-LIMO.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-R1-LIMO.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-R1-LIMO.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-R1-LIMO.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-R1-LIMO.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-R1-LIMO.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-R1-LIMO.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-R1-LIMO.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-R1-LIMO.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-R1-LIMO.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-R1-LIMO.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-R1-LIMO.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..734eb91 --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: Josephgflowers/TinyLlama-R1-LIMO +datasets: +- GAIR/LIMO +language: +- en +library_name: transformers +license: mit +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/Josephgflowers/TinyLlama-R1-LIMO + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/TinyLlama-R1-LIMO-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/TinyLlama-R1-LIMO-GGUF/resolve/main/TinyLlama-R1-LIMO.Q2_K.gguf) | Q2_K | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-R1-LIMO-GGUF/resolve/main/TinyLlama-R1-LIMO.Q3_K_S.gguf) | Q3_K_S | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-R1-LIMO-GGUF/resolve/main/TinyLlama-R1-LIMO.Q3_K_M.gguf) | Q3_K_M | 0.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-R1-LIMO-GGUF/resolve/main/TinyLlama-R1-LIMO.Q3_K_L.gguf) | Q3_K_L | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-R1-LIMO-GGUF/resolve/main/TinyLlama-R1-LIMO.IQ4_XS.gguf) | IQ4_XS | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-R1-LIMO-GGUF/resolve/main/TinyLlama-R1-LIMO.Q4_K_S.gguf) | Q4_K_S | 0.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-R1-LIMO-GGUF/resolve/main/TinyLlama-R1-LIMO.Q4_K_M.gguf) | Q4_K_M | 0.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-R1-LIMO-GGUF/resolve/main/TinyLlama-R1-LIMO.Q5_K_S.gguf) | Q5_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-R1-LIMO-GGUF/resolve/main/TinyLlama-R1-LIMO.Q5_K_M.gguf) | Q5_K_M | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-R1-LIMO-GGUF/resolve/main/TinyLlama-R1-LIMO.Q6_K.gguf) | Q6_K | 1.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-R1-LIMO-GGUF/resolve/main/TinyLlama-R1-LIMO.Q8_0.gguf) | Q8_0 | 1.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-R1-LIMO-GGUF/resolve/main/TinyLlama-R1-LIMO.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. + + diff --git a/TinyLlama-R1-LIMO.IQ4_XS.gguf b/TinyLlama-R1-LIMO.IQ4_XS.gguf new file mode 100644 index 0000000..da03a80 --- /dev/null +++ b/TinyLlama-R1-LIMO.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08822e8c7abfa5af2b83666ef8ac8bf42235299ac46c0452d8e018f55079d41a +size 609808832 diff --git a/TinyLlama-R1-LIMO.Q2_K.gguf b/TinyLlama-R1-LIMO.Q2_K.gguf new file mode 100644 index 0000000..b8d4e36 --- /dev/null +++ b/TinyLlama-R1-LIMO.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:321ee0bfb7f79c8be787736d5382e064601985af14eca6926df82bfcfb9d9b23 +size 432132544 diff --git a/TinyLlama-R1-LIMO.Q3_K_L.gguf b/TinyLlama-R1-LIMO.Q3_K_L.gguf new file mode 100644 index 0000000..34320f0 --- /dev/null +++ b/TinyLlama-R1-LIMO.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d080961108b10e0b8f0cb3ecbe9c831258ca25d93504947de946cefa50d258d +size 591528384 diff --git a/TinyLlama-R1-LIMO.Q3_K_M.gguf b/TinyLlama-R1-LIMO.Q3_K_M.gguf new file mode 100644 index 0000000..02572a3 --- /dev/null +++ b/TinyLlama-R1-LIMO.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6f4107d75011d87105927f4dfdcfdc7a1c42c1c2d55b03ebc45afd292ec93c5 +size 548405696 diff --git a/TinyLlama-R1-LIMO.Q3_K_S.gguf b/TinyLlama-R1-LIMO.Q3_K_S.gguf new file mode 100644 index 0000000..700de16 --- /dev/null +++ b/TinyLlama-R1-LIMO.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:015af402546065d2ee7dda2eb8b40796c7fa597be154457061a82c754ba62430 +size 499343808 diff --git a/TinyLlama-R1-LIMO.Q4_K_M.gguf b/TinyLlama-R1-LIMO.Q4_K_M.gguf new file mode 100644 index 0000000..2d547a6 --- /dev/null +++ b/TinyLlama-R1-LIMO.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2df03f5b0893920eeb21b29ee6f0edc4663f552f7daa250acfc05a82701fce8b +size 667816384 diff --git a/TinyLlama-R1-LIMO.Q4_K_S.gguf b/TinyLlama-R1-LIMO.Q4_K_S.gguf new file mode 100644 index 0000000..faf8722 --- /dev/null +++ b/TinyLlama-R1-LIMO.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:baee474c6dc32ded39cadba8b67bdf743e92938a05457a083eb454731c3d69b3 +size 639873472 diff --git a/TinyLlama-R1-LIMO.Q5_K_M.gguf b/TinyLlama-R1-LIMO.Q5_K_M.gguf new file mode 100644 index 0000000..247a666 --- /dev/null +++ b/TinyLlama-R1-LIMO.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d5989cb4bebb51c20375018719ff2c719820cfd79bf0eb02944ae2dbcea6865 +size 782045632 diff --git a/TinyLlama-R1-LIMO.Q5_K_S.gguf b/TinyLlama-R1-LIMO.Q5_K_S.gguf new file mode 100644 index 0000000..d2f3a0d --- /dev/null +++ b/TinyLlama-R1-LIMO.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43217d3bc76ddf462f27abe5f7c27a4deb76419a5cb9271362bdc7a954ca93b4 +size 766030272 diff --git a/TinyLlama-R1-LIMO.Q6_K.gguf b/TinyLlama-R1-LIMO.Q6_K.gguf new file mode 100644 index 0000000..f304a0d --- /dev/null +++ b/TinyLlama-R1-LIMO.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5eb48408351d6cc8854349b90f5311aeba6558c1591adbef4d565e9860066fb +size 903414208 diff --git a/TinyLlama-R1-LIMO.Q8_0.gguf b/TinyLlama-R1-LIMO.Q8_0.gguf new file mode 100644 index 0000000..d449499 --- /dev/null +++ b/TinyLlama-R1-LIMO.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d8178c5ab87cc54193c663d2c6354d05d0dc6cf555617a07fcf8720b07f1962 +size 1169809856 diff --git a/TinyLlama-R1-LIMO.f16.gguf b/TinyLlama-R1-LIMO.f16.gguf new file mode 100644 index 0000000..1aceba2 --- /dev/null +++ b/TinyLlama-R1-LIMO.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:495404815103e01cb788e67f666008c843ec1356d6123613e3fa431df5e981a2 +size 2201018816