commit 177e09dff39f1b6b5d710c667ab115cbb1383417 Author: ModelHub XC Date: Fri May 8 09:19:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Tiny_Llama_Storyteller-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..1adb9fa --- /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 +Tiny_Llama_Storyteller.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Tiny_Llama_Storyteller.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Tiny_Llama_Storyteller.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Tiny_Llama_Storyteller.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Tiny_Llama_Storyteller.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Tiny_Llama_Storyteller.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Tiny_Llama_Storyteller.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Tiny_Llama_Storyteller.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Tiny_Llama_Storyteller.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Tiny_Llama_Storyteller.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Tiny_Llama_Storyteller.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Tiny_Llama_Storyteller.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..971cf6a --- /dev/null +++ b/README.md @@ -0,0 +1,76 @@ +--- +base_model: Arivukkarasu/Tiny_Llama_Storyteller +datasets: +- jaydenccc/AI_Storyteller_Dataset +language: +- en +library_name: transformers +license: gpl-3.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- generated_from_trainer +--- +## About + + + + + + + + + +static quants of https://huggingface.co/Arivukkarasu/Tiny_Llama_Storyteller + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Tiny_Llama_Storyteller-GGUF).*** + +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/Tiny_Llama_Storyteller-GGUF/resolve/main/Tiny_Llama_Storyteller.Q2_K.gguf) | Q2_K | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Tiny_Llama_Storyteller-GGUF/resolve/main/Tiny_Llama_Storyteller.Q3_K_S.gguf) | Q3_K_S | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/Tiny_Llama_Storyteller-GGUF/resolve/main/Tiny_Llama_Storyteller.Q3_K_M.gguf) | Q3_K_M | 0.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Tiny_Llama_Storyteller-GGUF/resolve/main/Tiny_Llama_Storyteller.Q3_K_L.gguf) | Q3_K_L | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Tiny_Llama_Storyteller-GGUF/resolve/main/Tiny_Llama_Storyteller.IQ4_XS.gguf) | IQ4_XS | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Tiny_Llama_Storyteller-GGUF/resolve/main/Tiny_Llama_Storyteller.Q4_K_S.gguf) | Q4_K_S | 0.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Tiny_Llama_Storyteller-GGUF/resolve/main/Tiny_Llama_Storyteller.Q4_K_M.gguf) | Q4_K_M | 0.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Tiny_Llama_Storyteller-GGUF/resolve/main/Tiny_Llama_Storyteller.Q5_K_S.gguf) | Q5_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Tiny_Llama_Storyteller-GGUF/resolve/main/Tiny_Llama_Storyteller.Q5_K_M.gguf) | Q5_K_M | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Tiny_Llama_Storyteller-GGUF/resolve/main/Tiny_Llama_Storyteller.Q6_K.gguf) | Q6_K | 1.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Tiny_Llama_Storyteller-GGUF/resolve/main/Tiny_Llama_Storyteller.Q8_0.gguf) | Q8_0 | 1.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Tiny_Llama_Storyteller-GGUF/resolve/main/Tiny_Llama_Storyteller.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/Tiny_Llama_Storyteller.IQ4_XS.gguf b/Tiny_Llama_Storyteller.IQ4_XS.gguf new file mode 100644 index 0000000..903b479 --- /dev/null +++ b/Tiny_Llama_Storyteller.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:324a8b9fcab30e5e95cc23c6d9e14b85232c47f9a87f38dd7bfc113c03c4c579 +size 609808768 diff --git a/Tiny_Llama_Storyteller.Q2_K.gguf b/Tiny_Llama_Storyteller.Q2_K.gguf new file mode 100644 index 0000000..36de680 --- /dev/null +++ b/Tiny_Llama_Storyteller.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5f4b83c9fdd7a02ffd34edb22d438c67e125b8e5231f981f61234b48b188a44 +size 432132480 diff --git a/Tiny_Llama_Storyteller.Q3_K_L.gguf b/Tiny_Llama_Storyteller.Q3_K_L.gguf new file mode 100644 index 0000000..fa50c7d --- /dev/null +++ b/Tiny_Llama_Storyteller.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27d5f638117619dced244f21efc28431d33b9c9641d18cd35bb37710f1c9d261 +size 591528320 diff --git a/Tiny_Llama_Storyteller.Q3_K_M.gguf b/Tiny_Llama_Storyteller.Q3_K_M.gguf new file mode 100644 index 0000000..8061cb2 --- /dev/null +++ b/Tiny_Llama_Storyteller.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a2c76c5cfa2e6c21d88f1ad137165d2a5a972d689dcc8bb9f159cc635af98ad +size 548405632 diff --git a/Tiny_Llama_Storyteller.Q3_K_S.gguf b/Tiny_Llama_Storyteller.Q3_K_S.gguf new file mode 100644 index 0000000..34786ee --- /dev/null +++ b/Tiny_Llama_Storyteller.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da9e5f1713aa71f5717e7f8075e0014220579392d22a2ccbb700c1cd6bc8e1b8 +size 499343744 diff --git a/Tiny_Llama_Storyteller.Q4_K_M.gguf b/Tiny_Llama_Storyteller.Q4_K_M.gguf new file mode 100644 index 0000000..9208053 --- /dev/null +++ b/Tiny_Llama_Storyteller.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d802158e84e7018f8ba62b0863d0294668061e257574518290dffdf4fdbff491 +size 667816320 diff --git a/Tiny_Llama_Storyteller.Q4_K_S.gguf b/Tiny_Llama_Storyteller.Q4_K_S.gguf new file mode 100644 index 0000000..00b1109 --- /dev/null +++ b/Tiny_Llama_Storyteller.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a44ecc6d29c5fb556006997f3a299e55bfdb468b0bad7d8b86e5752c8274832 +size 639873408 diff --git a/Tiny_Llama_Storyteller.Q5_K_M.gguf b/Tiny_Llama_Storyteller.Q5_K_M.gguf new file mode 100644 index 0000000..6b2f990 --- /dev/null +++ b/Tiny_Llama_Storyteller.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4ef8b222d2bb8b36b20fef1acc7e5c4fa2bf03d9952c41518e2813d8c7e7c3a +size 782045568 diff --git a/Tiny_Llama_Storyteller.Q5_K_S.gguf b/Tiny_Llama_Storyteller.Q5_K_S.gguf new file mode 100644 index 0000000..84511e4 --- /dev/null +++ b/Tiny_Llama_Storyteller.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d03c8efda0e9ce1a3f1671ceccb4ea7bd062d551f01561a1cef6a97dd01f624a +size 766030208 diff --git a/Tiny_Llama_Storyteller.Q6_K.gguf b/Tiny_Llama_Storyteller.Q6_K.gguf new file mode 100644 index 0000000..1ffe846 --- /dev/null +++ b/Tiny_Llama_Storyteller.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b676b235613813a8f56aea1aa645f4421007cc9f4fce3e268c5fcdba8fa43596 +size 903414144 diff --git a/Tiny_Llama_Storyteller.Q8_0.gguf b/Tiny_Llama_Storyteller.Q8_0.gguf new file mode 100644 index 0000000..67a18c8 --- /dev/null +++ b/Tiny_Llama_Storyteller.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98d62b1663fa91f5ff57c2d56effda7ad57c213918c125fdf7155b3e4cc32a7a +size 1169809792 diff --git a/Tiny_Llama_Storyteller.f16.gguf b/Tiny_Llama_Storyteller.f16.gguf new file mode 100644 index 0000000..92756c2 --- /dev/null +++ b/Tiny_Llama_Storyteller.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48d1c8389d0fea566019eb030584e0c0e9818c1b682195ffedad3656204bbf68 +size 2201018752