commit 9d19d96c85f5e397613d25dbba1c9bcadb701455 Author: ModelHub XC Date: Wed Sep 9 17:32:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/TinyStories-LLaMA2-20M-256h-4l-GQA-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..49493f4 --- /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 +TinyStories-LLaMA2-20M-256h-4l-GQA.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +TinyStories-LLaMA2-20M-256h-4l-GQA.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +TinyStories-LLaMA2-20M-256h-4l-GQA.f16.gguf filter=lfs diff=lfs merge=lfs -text +TinyStories-LLaMA2-20M-256h-4l-GQA.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +TinyStories-LLaMA2-20M-256h-4l-GQA.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TinyStories-LLaMA2-20M-256h-4l-GQA.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +TinyStories-LLaMA2-20M-256h-4l-GQA.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TinyStories-LLaMA2-20M-256h-4l-GQA.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +TinyStories-LLaMA2-20M-256h-4l-GQA.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TinyStories-LLaMA2-20M-256h-4l-GQA.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TinyStories-LLaMA2-20M-256h-4l-GQA.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +TinyStories-LLaMA2-20M-256h-4l-GQA.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..f1ce31e --- /dev/null +++ b/README.md @@ -0,0 +1,67 @@ +--- +base_model: chencindy/TinyStories-LLaMA2-20M-256h-4l-GQA +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/chencindy/TinyStories-LLaMA2-20M-256h-4l-GQA + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/TinyStories-LLaMA2-20M-256h-4l-GQA-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/TinyStories-LLaMA2-20M-256h-4l-GQA-GGUF/resolve/main/TinyStories-LLaMA2-20M-256h-4l-GQA.Q2_K.gguf) | Q2_K | 0.1 | | +| [GGUF](https://huggingface.co/mradermacher/TinyStories-LLaMA2-20M-256h-4l-GQA-GGUF/resolve/main/TinyStories-LLaMA2-20M-256h-4l-GQA.IQ3_XS.gguf) | IQ3_XS | 0.1 | | +| [GGUF](https://huggingface.co/mradermacher/TinyStories-LLaMA2-20M-256h-4l-GQA-GGUF/resolve/main/TinyStories-LLaMA2-20M-256h-4l-GQA.IQ3_S.gguf) | IQ3_S | 0.1 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/TinyStories-LLaMA2-20M-256h-4l-GQA-GGUF/resolve/main/TinyStories-LLaMA2-20M-256h-4l-GQA.Q3_K_S.gguf) | Q3_K_S | 0.1 | | +| [GGUF](https://huggingface.co/mradermacher/TinyStories-LLaMA2-20M-256h-4l-GQA-GGUF/resolve/main/TinyStories-LLaMA2-20M-256h-4l-GQA.IQ3_M.gguf) | IQ3_M | 0.1 | | +| [GGUF](https://huggingface.co/mradermacher/TinyStories-LLaMA2-20M-256h-4l-GQA-GGUF/resolve/main/TinyStories-LLaMA2-20M-256h-4l-GQA.Q3_K_M.gguf) | Q3_K_M | 0.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/TinyStories-LLaMA2-20M-256h-4l-GQA-GGUF/resolve/main/TinyStories-LLaMA2-20M-256h-4l-GQA.Q3_K_L.gguf) | Q3_K_L | 0.1 | | +| [GGUF](https://huggingface.co/mradermacher/TinyStories-LLaMA2-20M-256h-4l-GQA-GGUF/resolve/main/TinyStories-LLaMA2-20M-256h-4l-GQA.IQ4_XS.gguf) | IQ4_XS | 0.1 | | +| [GGUF](https://huggingface.co/mradermacher/TinyStories-LLaMA2-20M-256h-4l-GQA-GGUF/resolve/main/TinyStories-LLaMA2-20M-256h-4l-GQA.Q4_K_S.gguf) | Q4_K_S | 0.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/TinyStories-LLaMA2-20M-256h-4l-GQA-GGUF/resolve/main/TinyStories-LLaMA2-20M-256h-4l-GQA.Q4_K_M.gguf) | Q4_K_M | 0.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/TinyStories-LLaMA2-20M-256h-4l-GQA-GGUF/resolve/main/TinyStories-LLaMA2-20M-256h-4l-GQA.Q5_K_S.gguf) | Q5_K_S | 0.1 | | +| [GGUF](https://huggingface.co/mradermacher/TinyStories-LLaMA2-20M-256h-4l-GQA-GGUF/resolve/main/TinyStories-LLaMA2-20M-256h-4l-GQA.Q5_K_M.gguf) | Q5_K_M | 0.1 | | +| [GGUF](https://huggingface.co/mradermacher/TinyStories-LLaMA2-20M-256h-4l-GQA-GGUF/resolve/main/TinyStories-LLaMA2-20M-256h-4l-GQA.Q6_K.gguf) | Q6_K | 0.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/TinyStories-LLaMA2-20M-256h-4l-GQA-GGUF/resolve/main/TinyStories-LLaMA2-20M-256h-4l-GQA.Q8_0.gguf) | Q8_0 | 0.1 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/TinyStories-LLaMA2-20M-256h-4l-GQA-GGUF/resolve/main/TinyStories-LLaMA2-20M-256h-4l-GQA.f16.gguf) | f16 | 0.1 | 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/TinyStories-LLaMA2-20M-256h-4l-GQA.IQ3_M.gguf b/TinyStories-LLaMA2-20M-256h-4l-GQA.IQ3_M.gguf new file mode 100644 index 0000000..90740c7 --- /dev/null +++ b/TinyStories-LLaMA2-20M-256h-4l-GQA.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f1b4abcd8bc750abb188789d5b5e409a6b3847f2b9c46dffd30c202f1d4f225 +size 12380128 diff --git a/TinyStories-LLaMA2-20M-256h-4l-GQA.IQ3_S.gguf b/TinyStories-LLaMA2-20M-256h-4l-GQA.IQ3_S.gguf new file mode 100644 index 0000000..301bebd --- /dev/null +++ b/TinyStories-LLaMA2-20M-256h-4l-GQA.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d60be7bb5fb27f30b95f406cc2ae3a432e3be15507e78baa8cb46d3f63a4edeb +size 12327904 diff --git a/TinyStories-LLaMA2-20M-256h-4l-GQA.IQ3_XS.gguf b/TinyStories-LLaMA2-20M-256h-4l-GQA.IQ3_XS.gguf new file mode 100644 index 0000000..76d8c9b --- /dev/null +++ b/TinyStories-LLaMA2-20M-256h-4l-GQA.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b358da92d2d2b888c52e1ec0849f2790d0e9379804eeccd9a5f8680cef6348f +size 12254176 diff --git a/TinyStories-LLaMA2-20M-256h-4l-GQA.IQ4_XS.gguf b/TinyStories-LLaMA2-20M-256h-4l-GQA.IQ4_XS.gguf new file mode 100644 index 0000000..a6b169f --- /dev/null +++ b/TinyStories-LLaMA2-20M-256h-4l-GQA.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f104c64d72f1392e444440621dcb37a48c6e1f9c42238b36c9326ba89e6fef8 +size 13479392 diff --git a/TinyStories-LLaMA2-20M-256h-4l-GQA.Q2_K.gguf b/TinyStories-LLaMA2-20M-256h-4l-GQA.Q2_K.gguf new file mode 100644 index 0000000..e080834 --- /dev/null +++ b/TinyStories-LLaMA2-20M-256h-4l-GQA.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4243c828d2a50c09efebc5b34fe4e699fa4f5c0f0210097416ef642849c48cf4 +size 11296224 diff --git a/TinyStories-LLaMA2-20M-256h-4l-GQA.Q3_K_L.gguf b/TinyStories-LLaMA2-20M-256h-4l-GQA.Q3_K_L.gguf new file mode 100644 index 0000000..b63410e --- /dev/null +++ b/TinyStories-LLaMA2-20M-256h-4l-GQA.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b1ed67f745c9b48c669418b3181489d93bd8ce32b8c103d34e30e990b2c6148 +size 12632032 diff --git a/TinyStories-LLaMA2-20M-256h-4l-GQA.Q3_K_M.gguf b/TinyStories-LLaMA2-20M-256h-4l-GQA.Q3_K_M.gguf new file mode 100644 index 0000000..3c91cf7 --- /dev/null +++ b/TinyStories-LLaMA2-20M-256h-4l-GQA.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8937c8b3670e026527c44f228301b8ca0b0f6b9a432834af97329a13b170881 +size 12492768 diff --git a/TinyStories-LLaMA2-20M-256h-4l-GQA.Q3_K_S.gguf b/TinyStories-LLaMA2-20M-256h-4l-GQA.Q3_K_S.gguf new file mode 100644 index 0000000..b3698da --- /dev/null +++ b/TinyStories-LLaMA2-20M-256h-4l-GQA.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f32cdc468feae6203924d134615823897209e66ef79e66859c35711bcdfa0499 +size 12327904 diff --git a/TinyStories-LLaMA2-20M-256h-4l-GQA.Q4_K_M.gguf b/TinyStories-LLaMA2-20M-256h-4l-GQA.Q4_K_M.gguf new file mode 100644 index 0000000..6cc5650 --- /dev/null +++ b/TinyStories-LLaMA2-20M-256h-4l-GQA.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c2810355d7dcb471d12c6bb468c1663ae98615c7c2336c4489cedb983ce0ba5 +size 13951968 diff --git a/TinyStories-LLaMA2-20M-256h-4l-GQA.Q4_K_S.gguf b/TinyStories-LLaMA2-20M-256h-4l-GQA.Q4_K_S.gguf new file mode 100644 index 0000000..be2335e --- /dev/null +++ b/TinyStories-LLaMA2-20M-256h-4l-GQA.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ae9e2e8fc3e9863babe5cb66f16ac973331a91ced008cc4514e2f4fe51e6d05 +size 13850080 diff --git a/TinyStories-LLaMA2-20M-256h-4l-GQA.Q5_K_M.gguf b/TinyStories-LLaMA2-20M-256h-4l-GQA.Q5_K_M.gguf new file mode 100644 index 0000000..6706a23 --- /dev/null +++ b/TinyStories-LLaMA2-20M-256h-4l-GQA.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba4229be5d9c8a1f85f387effaf2a6f767ed39b77110dd4227f94f9907bedd26 +size 15311840 diff --git a/TinyStories-LLaMA2-20M-256h-4l-GQA.Q5_K_S.gguf b/TinyStories-LLaMA2-20M-256h-4l-GQA.Q5_K_S.gguf new file mode 100644 index 0000000..2308e14 --- /dev/null +++ b/TinyStories-LLaMA2-20M-256h-4l-GQA.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19428141880ceecaf5ebb6a50bd694b0abd28178d148fb62413f963cea6906f3 +size 15250912 diff --git a/TinyStories-LLaMA2-20M-256h-4l-GQA.Q6_K.gguf b/TinyStories-LLaMA2-20M-256h-4l-GQA.Q6_K.gguf new file mode 100644 index 0000000..861a937 --- /dev/null +++ b/TinyStories-LLaMA2-20M-256h-4l-GQA.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cfca6ff7328178f9d3e974a023b6d9d7125af1dc799e6601bad30176a7f445c8 +size 16756704 diff --git a/TinyStories-LLaMA2-20M-256h-4l-GQA.Q8_0.gguf b/TinyStories-LLaMA2-20M-256h-4l-GQA.Q8_0.gguf new file mode 100644 index 0000000..ba6008d --- /dev/null +++ b/TinyStories-LLaMA2-20M-256h-4l-GQA.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86cd37850fa561d5ae2a368b9d85fcb87949c0468eda5a6da1cfab45469b1b9b +size 21486560 diff --git a/TinyStories-LLaMA2-20M-256h-4l-GQA.f16.gguf b/TinyStories-LLaMA2-20M-256h-4l-GQA.f16.gguf new file mode 100644 index 0000000..8821e26 --- /dev/null +++ b/TinyStories-LLaMA2-20M-256h-4l-GQA.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b184734cdf0e9860e15b32ba785865554ff61976a9665f66f55762e675e791a +size 39795680