commit 95a44c7bebff90398ae7870a8576be3a28a00bc8 Author: ModelHub XC Date: Wed Jul 8 09:08:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/tinyllama-Fine-tuned-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..e615e13 --- /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-Fine-tuned.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +tinyllama-Fine-tuned.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +tinyllama-Fine-tuned.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +tinyllama-Fine-tuned.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +tinyllama-Fine-tuned.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +tinyllama-Fine-tuned.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +tinyllama-Fine-tuned.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +tinyllama-Fine-tuned.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +tinyllama-Fine-tuned.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +tinyllama-Fine-tuned.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +tinyllama-Fine-tuned.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +tinyllama-Fine-tuned.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..fa89e29 --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: Yufeng1231/tinyllama-Fine-tuned +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + + + + +static quants of https://huggingface.co/Yufeng1231/tinyllama-Fine-tuned + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#tinyllama-Fine-tuned-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/tinyllama-Fine-tuned-GGUF/resolve/main/tinyllama-Fine-tuned.Q2_K.gguf) | Q2_K | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/tinyllama-Fine-tuned-GGUF/resolve/main/tinyllama-Fine-tuned.Q3_K_S.gguf) | Q3_K_S | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/tinyllama-Fine-tuned-GGUF/resolve/main/tinyllama-Fine-tuned.Q3_K_M.gguf) | Q3_K_M | 0.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/tinyllama-Fine-tuned-GGUF/resolve/main/tinyllama-Fine-tuned.Q3_K_L.gguf) | Q3_K_L | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/tinyllama-Fine-tuned-GGUF/resolve/main/tinyllama-Fine-tuned.IQ4_XS.gguf) | IQ4_XS | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/tinyllama-Fine-tuned-GGUF/resolve/main/tinyllama-Fine-tuned.Q4_K_S.gguf) | Q4_K_S | 0.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/tinyllama-Fine-tuned-GGUF/resolve/main/tinyllama-Fine-tuned.Q4_K_M.gguf) | Q4_K_M | 0.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/tinyllama-Fine-tuned-GGUF/resolve/main/tinyllama-Fine-tuned.Q5_K_S.gguf) | Q5_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/tinyllama-Fine-tuned-GGUF/resolve/main/tinyllama-Fine-tuned.Q5_K_M.gguf) | Q5_K_M | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/tinyllama-Fine-tuned-GGUF/resolve/main/tinyllama-Fine-tuned.Q6_K.gguf) | Q6_K | 1.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/tinyllama-Fine-tuned-GGUF/resolve/main/tinyllama-Fine-tuned.Q8_0.gguf) | Q8_0 | 1.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/tinyllama-Fine-tuned-GGUF/resolve/main/tinyllama-Fine-tuned.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-Fine-tuned.IQ4_XS.gguf b/tinyllama-Fine-tuned.IQ4_XS.gguf new file mode 100644 index 0000000..7083244 --- /dev/null +++ b/tinyllama-Fine-tuned.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f675fc5b7398040f457960968946a082dc833287281db5e4abc9af8177524c8b +size 609808192 diff --git a/tinyllama-Fine-tuned.Q2_K.gguf b/tinyllama-Fine-tuned.Q2_K.gguf new file mode 100644 index 0000000..1f95770 --- /dev/null +++ b/tinyllama-Fine-tuned.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b2406fbefb307409198a231b4d672777b35c9049cc29955dbba6fdef8e6d1ea +size 432131904 diff --git a/tinyllama-Fine-tuned.Q3_K_L.gguf b/tinyllama-Fine-tuned.Q3_K_L.gguf new file mode 100644 index 0000000..11b9ae9 --- /dev/null +++ b/tinyllama-Fine-tuned.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d26092d2b6148a934bfbccce2c4fa204d790dc5154fbb33a97f74e05218ba9aa +size 591527744 diff --git a/tinyllama-Fine-tuned.Q3_K_M.gguf b/tinyllama-Fine-tuned.Q3_K_M.gguf new file mode 100644 index 0000000..6d2144b --- /dev/null +++ b/tinyllama-Fine-tuned.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:425416130a85ec2fad394ec6a29335f8d91acacd36cd73a5c98b5fdddb9ea86c +size 548405056 diff --git a/tinyllama-Fine-tuned.Q3_K_S.gguf b/tinyllama-Fine-tuned.Q3_K_S.gguf new file mode 100644 index 0000000..129b284 --- /dev/null +++ b/tinyllama-Fine-tuned.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:157fa027069734763c00655f9a4b63b41c72b2dd710eead1cb8f2d8f9960a065 +size 499343168 diff --git a/tinyllama-Fine-tuned.Q4_K_M.gguf b/tinyllama-Fine-tuned.Q4_K_M.gguf new file mode 100644 index 0000000..5dcceaf --- /dev/null +++ b/tinyllama-Fine-tuned.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02eaeab2b0cfa3e03adb549361e578d329912f7d9bc7795f9a4ebd9ad75e9f5b +size 667815744 diff --git a/tinyllama-Fine-tuned.Q4_K_S.gguf b/tinyllama-Fine-tuned.Q4_K_S.gguf new file mode 100644 index 0000000..39ff45c --- /dev/null +++ b/tinyllama-Fine-tuned.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4641a3ae5cbf9aa382b47af753ca372be96913a2e5b262b542bc9d09ef6daf56 +size 639872832 diff --git a/tinyllama-Fine-tuned.Q5_K_M.gguf b/tinyllama-Fine-tuned.Q5_K_M.gguf new file mode 100644 index 0000000..25990b0 --- /dev/null +++ b/tinyllama-Fine-tuned.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd7b8574373ddbe27d91eda62ee6c7a21c5b1fa0d75acf5e7e05dbff160b18e4 +size 782044992 diff --git a/tinyllama-Fine-tuned.Q5_K_S.gguf b/tinyllama-Fine-tuned.Q5_K_S.gguf new file mode 100644 index 0000000..83fa287 --- /dev/null +++ b/tinyllama-Fine-tuned.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3219a5ec6d89549eae0ef48aded283a513804f38576c2bbb1aa225cebd1640c4 +size 766029632 diff --git a/tinyllama-Fine-tuned.Q6_K.gguf b/tinyllama-Fine-tuned.Q6_K.gguf new file mode 100644 index 0000000..984a34c --- /dev/null +++ b/tinyllama-Fine-tuned.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8989ce1077f05f8af42bf83b07397515a9e7c6858402b5f92e90e0092eb55de4 +size 903413568 diff --git a/tinyllama-Fine-tuned.Q8_0.gguf b/tinyllama-Fine-tuned.Q8_0.gguf new file mode 100644 index 0000000..3c54df9 --- /dev/null +++ b/tinyllama-Fine-tuned.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b37a3d06c2ebb8c8ecd31b6c3a534b9fdfed5b1e396b55f502ccb97fc952e72 +size 1169809216 diff --git a/tinyllama-Fine-tuned.f16.gguf b/tinyllama-Fine-tuned.f16.gguf new file mode 100644 index 0000000..a0a4242 --- /dev/null +++ b/tinyllama-Fine-tuned.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d69c4ebac486d03d443339ff2d6008936e7a2ba2b15d31165cc60b8e948a51b4 +size 2201018176