commit 667447fc9f4eae5803abf9eb6b4ac5cfd1cacc3a Author: ModelHub XC Date: Sun Sep 27 18:17:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/short-llama-3.2-3B-final-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..0b5f508 --- /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 +short-llama-3.2-3B-final.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +short-llama-3.2-3B-final.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +short-llama-3.2-3B-final.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +short-llama-3.2-3B-final.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +short-llama-3.2-3B-final.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +short-llama-3.2-3B-final.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +short-llama-3.2-3B-final.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +short-llama-3.2-3B-final.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +short-llama-3.2-3B-final.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +short-llama-3.2-3B-final.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +short-llama-3.2-3B-final.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +short-llama-3.2-3B-final.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..d0d900c --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: Shahrukh0/short-llama-3.2-3B-final +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/Shahrukh0/short-llama-3.2-3B-final + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#short-llama-3.2-3B-final-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/short-llama-3.2-3B-final-GGUF/resolve/main/short-llama-3.2-3B-final.Q2_K.gguf) | Q2_K | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/short-llama-3.2-3B-final-GGUF/resolve/main/short-llama-3.2-3B-final.Q3_K_S.gguf) | Q3_K_S | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/short-llama-3.2-3B-final-GGUF/resolve/main/short-llama-3.2-3B-final.Q3_K_M.gguf) | Q3_K_M | 1.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/short-llama-3.2-3B-final-GGUF/resolve/main/short-llama-3.2-3B-final.Q3_K_L.gguf) | Q3_K_L | 1.7 | | +| [GGUF](https://huggingface.co/mradermacher/short-llama-3.2-3B-final-GGUF/resolve/main/short-llama-3.2-3B-final.IQ4_XS.gguf) | IQ4_XS | 1.7 | | +| [GGUF](https://huggingface.co/mradermacher/short-llama-3.2-3B-final-GGUF/resolve/main/short-llama-3.2-3B-final.Q4_K_S.gguf) | Q4_K_S | 1.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/short-llama-3.2-3B-final-GGUF/resolve/main/short-llama-3.2-3B-final.Q4_K_M.gguf) | Q4_K_M | 1.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/short-llama-3.2-3B-final-GGUF/resolve/main/short-llama-3.2-3B-final.Q5_K_S.gguf) | Q5_K_S | 2.1 | | +| [GGUF](https://huggingface.co/mradermacher/short-llama-3.2-3B-final-GGUF/resolve/main/short-llama-3.2-3B-final.Q5_K_M.gguf) | Q5_K_M | 2.1 | | +| [GGUF](https://huggingface.co/mradermacher/short-llama-3.2-3B-final-GGUF/resolve/main/short-llama-3.2-3B-final.Q6_K.gguf) | Q6_K | 2.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/short-llama-3.2-3B-final-GGUF/resolve/main/short-llama-3.2-3B-final.Q8_0.gguf) | Q8_0 | 3.1 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/short-llama-3.2-3B-final-GGUF/resolve/main/short-llama-3.2-3B-final.f16.gguf) | f16 | 5.7 | 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/short-llama-3.2-3B-final.IQ4_XS.gguf b/short-llama-3.2-3B-final.IQ4_XS.gguf new file mode 100644 index 0000000..91a756a --- /dev/null +++ b/short-llama-3.2-3B-final.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68a6d8aa5ef615e0e7a6f471403c197c829c450dbf7ed19eca8b8d6260ce94b3 +size 1626892928 diff --git a/short-llama-3.2-3B-final.Q2_K.gguf b/short-llama-3.2-3B-final.Q2_K.gguf new file mode 100644 index 0000000..edf3898 --- /dev/null +++ b/short-llama-3.2-3B-final.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:565e6a5e69207b989a139262b0bf6c0e377d582058fe577f6dfc5fdbd96d3d3a +size 1216375424 diff --git a/short-llama-3.2-3B-final.Q3_K_L.gguf b/short-llama-3.2-3B-final.Q3_K_L.gguf new file mode 100644 index 0000000..60d30c5 --- /dev/null +++ b/short-llama-3.2-3B-final.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:225d3de395ff6e6780c81916a5cae7d86f8328138dd4857719f69a45960078e7 +size 1603299968 diff --git a/short-llama-3.2-3B-final.Q3_K_M.gguf b/short-llama-3.2-3B-final.Q3_K_M.gguf new file mode 100644 index 0000000..792fd76 --- /dev/null +++ b/short-llama-3.2-3B-final.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bfa51ffc64295dee9ccbb8d16a46efcbdaff04fc8e2eda6e4a14eb91ecc4f326 +size 1493985920 diff --git a/short-llama-3.2-3B-final.Q3_K_S.gguf b/short-llama-3.2-3B-final.Q3_K_S.gguf new file mode 100644 index 0000000..ca971ef --- /dev/null +++ b/short-llama-3.2-3B-final.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78daf5d0bffd504c09eb55d3ea1a40aea54c0e928d69439b2bf45b8a2e2f26e8 +size 1369729664 diff --git a/short-llama-3.2-3B-final.Q4_K_M.gguf b/short-llama-3.2-3B-final.Q4_K_M.gguf new file mode 100644 index 0000000..812c509 --- /dev/null +++ b/short-llama-3.2-3B-final.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ddbe8a2208945495319feca4111651b335e66e2232fb57ef5c64f2dc9139ff25 +size 1778182784 diff --git a/short-llama-3.2-3B-final.Q4_K_S.gguf b/short-llama-3.2-3B-final.Q4_K_S.gguf new file mode 100644 index 0000000..a56b07f --- /dev/null +++ b/short-llama-3.2-3B-final.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0ef60703e437239c5d261788bb195c7375dc785fdbbab5dc43421aa4269c175 +size 1701603968 diff --git a/short-llama-3.2-3B-final.Q5_K_M.gguf b/short-llama-3.2-3B-final.Q5_K_M.gguf new file mode 100644 index 0000000..10ae04c --- /dev/null +++ b/short-llama-3.2-3B-final.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ed848783544f841a3254e4d12df7011e672a6776be8aabf86b1c81f7a82a397 +size 2037705344 diff --git a/short-llama-3.2-3B-final.Q5_K_S.gguf b/short-llama-3.2-3B-final.Q5_K_S.gguf new file mode 100644 index 0000000..9b4b3d4 --- /dev/null +++ b/short-llama-3.2-3B-final.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ed97a624cff19bf0a96d764c0715e6941f1e2dc921301fd311b0a6b2c0b3bee +size 1992583808 diff --git a/short-llama-3.2-3B-final.Q6_K.gguf b/short-llama-3.2-3B-final.Q6_K.gguf new file mode 100644 index 0000000..7390ac9 --- /dev/null +++ b/short-llama-3.2-3B-final.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:366f31f963a58eebd486769b6c72a613afcc96d20eba4af3a8fada124b50ca94 +size 2313448064 diff --git a/short-llama-3.2-3B-final.Q8_0.gguf b/short-llama-3.2-3B-final.Q8_0.gguf new file mode 100644 index 0000000..944aab3 --- /dev/null +++ b/short-llama-3.2-3B-final.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f97ff1284d0c76a8d58bd7f47e46f71e2c60bd191acc68559f145a73b368b4f +size 2993975936 diff --git a/short-llama-3.2-3B-final.f16.gguf b/short-llama-3.2-3B-final.f16.gguf new file mode 100644 index 0000000..a707203 --- /dev/null +++ b/short-llama-3.2-3B-final.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0dbc162bd968e365bdceb250b6e7ada6f40db2cb2666f847e183f51ac65489a +size 5628277376