commit a502e1e80b53df18a55c8f216d85532ea2bef8d1 Author: ModelHub XC Date: Thu Aug 27 03:20:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/TinyLlama-1.1B-intermediate-step-480k-1T-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..6a8e027 --- /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-1.1B-intermediate-step-480k-1T.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-intermediate-step-480k-1T.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-intermediate-step-480k-1T.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-intermediate-step-480k-1T.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-intermediate-step-480k-1T.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-intermediate-step-480k-1T.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-intermediate-step-480k-1T.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-intermediate-step-480k-1T.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-intermediate-step-480k-1T.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-intermediate-step-480k-1T.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-intermediate-step-480k-1T.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-intermediate-step-480k-1T.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..79e4e20 --- /dev/null +++ b/README.md @@ -0,0 +1,67 @@ +--- +base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-480k-1T +datasets: +- cerebras/SlimPajama-627B +- bigcode/starcoderdata +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/TinyLlama/TinyLlama-1.1B-intermediate-step-480k-1T + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/TinyLlama-1.1B-intermediate-step-480k-1T-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-1.1B-intermediate-step-480k-1T-GGUF/resolve/main/TinyLlama-1.1B-intermediate-step-480k-1T.Q2_K.gguf) | Q2_K | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-intermediate-step-480k-1T-GGUF/resolve/main/TinyLlama-1.1B-intermediate-step-480k-1T.Q3_K_S.gguf) | Q3_K_S | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-intermediate-step-480k-1T-GGUF/resolve/main/TinyLlama-1.1B-intermediate-step-480k-1T.Q3_K_M.gguf) | Q3_K_M | 0.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-intermediate-step-480k-1T-GGUF/resolve/main/TinyLlama-1.1B-intermediate-step-480k-1T.Q3_K_L.gguf) | Q3_K_L | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-intermediate-step-480k-1T-GGUF/resolve/main/TinyLlama-1.1B-intermediate-step-480k-1T.IQ4_XS.gguf) | IQ4_XS | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-intermediate-step-480k-1T-GGUF/resolve/main/TinyLlama-1.1B-intermediate-step-480k-1T.Q4_K_S.gguf) | Q4_K_S | 0.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-intermediate-step-480k-1T-GGUF/resolve/main/TinyLlama-1.1B-intermediate-step-480k-1T.Q4_K_M.gguf) | Q4_K_M | 0.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-intermediate-step-480k-1T-GGUF/resolve/main/TinyLlama-1.1B-intermediate-step-480k-1T.Q5_K_S.gguf) | Q5_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-intermediate-step-480k-1T-GGUF/resolve/main/TinyLlama-1.1B-intermediate-step-480k-1T.Q5_K_M.gguf) | Q5_K_M | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-intermediate-step-480k-1T-GGUF/resolve/main/TinyLlama-1.1B-intermediate-step-480k-1T.Q6_K.gguf) | Q6_K | 1.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-intermediate-step-480k-1T-GGUF/resolve/main/TinyLlama-1.1B-intermediate-step-480k-1T.Q8_0.gguf) | Q8_0 | 1.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-intermediate-step-480k-1T-GGUF/resolve/main/TinyLlama-1.1B-intermediate-step-480k-1T.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-1.1B-intermediate-step-480k-1T.IQ4_XS.gguf b/TinyLlama-1.1B-intermediate-step-480k-1T.IQ4_XS.gguf new file mode 100644 index 0000000..5ebc456 --- /dev/null +++ b/TinyLlama-1.1B-intermediate-step-480k-1T.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a59e302e29a22956f4a1ab49e511310533df32316570cf20ffc5a25353fe21b +size 609807840 diff --git a/TinyLlama-1.1B-intermediate-step-480k-1T.Q2_K.gguf b/TinyLlama-1.1B-intermediate-step-480k-1T.Q2_K.gguf new file mode 100644 index 0000000..6912cd2 --- /dev/null +++ b/TinyLlama-1.1B-intermediate-step-480k-1T.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:134f8531ca884b0fd11bc31da4f813c5fab4e0e7cccfdef72ea56809682b2887 +size 432131552 diff --git a/TinyLlama-1.1B-intermediate-step-480k-1T.Q3_K_L.gguf b/TinyLlama-1.1B-intermediate-step-480k-1T.Q3_K_L.gguf new file mode 100644 index 0000000..6ed78b8 --- /dev/null +++ b/TinyLlama-1.1B-intermediate-step-480k-1T.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e732ece5ddf35b2b8aa2cd00e658d7ab6ce8ade659a09bb0d1795c5641cc1f4f +size 591527392 diff --git a/TinyLlama-1.1B-intermediate-step-480k-1T.Q3_K_M.gguf b/TinyLlama-1.1B-intermediate-step-480k-1T.Q3_K_M.gguf new file mode 100644 index 0000000..46c6e93 --- /dev/null +++ b/TinyLlama-1.1B-intermediate-step-480k-1T.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c98d4a67c700b312233f9541fed032e9a07bafb812aacb3b7fa4f76ee4ca708a +size 548404704 diff --git a/TinyLlama-1.1B-intermediate-step-480k-1T.Q3_K_S.gguf b/TinyLlama-1.1B-intermediate-step-480k-1T.Q3_K_S.gguf new file mode 100644 index 0000000..7989457 --- /dev/null +++ b/TinyLlama-1.1B-intermediate-step-480k-1T.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3cc8adb63e508a60eb24f515902b7c3fc2c8a194d6afdbd23f75e3a61242bc9f +size 499342816 diff --git a/TinyLlama-1.1B-intermediate-step-480k-1T.Q4_K_M.gguf b/TinyLlama-1.1B-intermediate-step-480k-1T.Q4_K_M.gguf new file mode 100644 index 0000000..2fd4775 --- /dev/null +++ b/TinyLlama-1.1B-intermediate-step-480k-1T.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c61a3347937d54aeba6fb45caf8b8709212a21c77934ddd6d4a8394066e1c99d +size 667815392 diff --git a/TinyLlama-1.1B-intermediate-step-480k-1T.Q4_K_S.gguf b/TinyLlama-1.1B-intermediate-step-480k-1T.Q4_K_S.gguf new file mode 100644 index 0000000..3c81b60 --- /dev/null +++ b/TinyLlama-1.1B-intermediate-step-480k-1T.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:237214fad427c041423f8f02c90f3e63330c9d2bb187f78e2b0286af895b3008 +size 639872480 diff --git a/TinyLlama-1.1B-intermediate-step-480k-1T.Q5_K_M.gguf b/TinyLlama-1.1B-intermediate-step-480k-1T.Q5_K_M.gguf new file mode 100644 index 0000000..2e3101b --- /dev/null +++ b/TinyLlama-1.1B-intermediate-step-480k-1T.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:385f8093a23c6a42269482f427b92c976014b43a2a46f7653ea0f81ce3ae8791 +size 782044640 diff --git a/TinyLlama-1.1B-intermediate-step-480k-1T.Q5_K_S.gguf b/TinyLlama-1.1B-intermediate-step-480k-1T.Q5_K_S.gguf new file mode 100644 index 0000000..15fac5b --- /dev/null +++ b/TinyLlama-1.1B-intermediate-step-480k-1T.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a90287df0eb3da7ba910a8f35728c0b537ebb91c51f8d56af52196bf0216494 +size 766029280 diff --git a/TinyLlama-1.1B-intermediate-step-480k-1T.Q6_K.gguf b/TinyLlama-1.1B-intermediate-step-480k-1T.Q6_K.gguf new file mode 100644 index 0000000..ef684f1 --- /dev/null +++ b/TinyLlama-1.1B-intermediate-step-480k-1T.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d45a8f6c3966d0a7ffb9ce348ed9f060c5cd5415693fbdeb155c759e7e59666 +size 903413216 diff --git a/TinyLlama-1.1B-intermediate-step-480k-1T.Q8_0.gguf b/TinyLlama-1.1B-intermediate-step-480k-1T.Q8_0.gguf new file mode 100644 index 0000000..040d574 --- /dev/null +++ b/TinyLlama-1.1B-intermediate-step-480k-1T.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97f408a0ef18e721285fb29d31d170a4da2a8172c7bffcc7dd40f076a3f54a36 +size 1169808864 diff --git a/TinyLlama-1.1B-intermediate-step-480k-1T.f16.gguf b/TinyLlama-1.1B-intermediate-step-480k-1T.f16.gguf new file mode 100644 index 0000000..12b1778 --- /dev/null +++ b/TinyLlama-1.1B-intermediate-step-480k-1T.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2b95cfb761db2cd21637829188e05616efc1782fe820e5f29c3c340b16c97a2 +size 2201017824