commit 76fbba7726f2b67794f19268ac0f77ce21c3b728 Author: ModelHub XC Date: Sat May 9 11:15:41 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/ARM-3B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..0b5fde7 --- /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 +ARM-3B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +ARM-3B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +ARM-3B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +ARM-3B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ARM-3B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ARM-3B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ARM-3B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ARM-3B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ARM-3B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ARM-3B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +ARM-3B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +ARM-3B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/ARM-3B.IQ4_XS.gguf b/ARM-3B.IQ4_XS.gguf new file mode 100644 index 0000000..99259aa --- /dev/null +++ b/ARM-3B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:228d2696460b268499e18dc44c6c7e6ed4b604dcede0e4aae10591ce6612cf2e +size 1753182944 diff --git a/ARM-3B.Q2_K.gguf b/ARM-3B.Q2_K.gguf new file mode 100644 index 0000000..2f3eb4e --- /dev/null +++ b/ARM-3B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cffa0565265ba802c515ec9fa8cb80f4b917282cb00e9b6d6d37fbb9d93aa509 +size 1274753760 diff --git a/ARM-3B.Q3_K_L.gguf b/ARM-3B.Q3_K_L.gguf new file mode 100644 index 0000000..133281c --- /dev/null +++ b/ARM-3B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4409c30b9ddfd26df25982ba36e2e1b5c66c78e747df0102a48cfea0954f06fd +size 1707389664 diff --git a/ARM-3B.Q3_K_M.gguf b/ARM-3B.Q3_K_M.gguf new file mode 100644 index 0000000..27d1e92 --- /dev/null +++ b/ARM-3B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10cb3543a96a002c6a838dd5eaf8013e44c72495f85e0cebd91f0ce66f28ca73 +size 1590473440 diff --git a/ARM-3B.Q3_K_S.gguf b/ARM-3B.Q3_K_S.gguf new file mode 100644 index 0000000..3c09540 --- /dev/null +++ b/ARM-3B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad1de59f6d40e4f6f78713b27b652ecfc1143c98183fb7ce33a8d6f5c9c826a1 +size 1454355168 diff --git a/ARM-3B.Q4_K_M.gguf b/ARM-3B.Q4_K_M.gguf new file mode 100644 index 0000000..1d77833 --- /dev/null +++ b/ARM-3B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0bafbaf37ca6b35bdd91296bfaf4142925f3099e658d0ac12f95dafb3e911d82 +size 1929900768 diff --git a/ARM-3B.Q4_K_S.gguf b/ARM-3B.Q4_K_S.gguf new file mode 100644 index 0000000..8b4ce64 --- /dev/null +++ b/ARM-3B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab76812c7473fe3047da10a49fa6cde0a7bff4656ff0bdf3972e1b74b14ed253 +size 1834382048 diff --git a/ARM-3B.Q5_K_M.gguf b/ARM-3B.Q5_K_M.gguf new file mode 100644 index 0000000..ce4ba0a --- /dev/null +++ b/ARM-3B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4aba3b83389419f5936365120bd9e76c78a3b14ec4723ff7626895f253907d67 +size 2224812768 diff --git a/ARM-3B.Q5_K_S.gguf b/ARM-3B.Q5_K_S.gguf new file mode 100644 index 0000000..a7d7949 --- /dev/null +++ b/ARM-3B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b8a7b3075c8e50bc966a2fac96dcf987341f0dd095bdf0c3b62b0851e4cfd2f +size 2169664224 diff --git a/ARM-3B.Q6_K.gguf b/ARM-3B.Q6_K.gguf new file mode 100644 index 0000000..2f3fdfd --- /dev/null +++ b/ARM-3B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9d097a0c194bf79b723bc13ff76619b4d4d2fda79debe9b088373d4404e4361 +size 2538156768 diff --git a/ARM-3B.Q8_0.gguf b/ARM-3B.Q8_0.gguf new file mode 100644 index 0000000..fed21bb --- /dev/null +++ b/ARM-3B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b1d7de90130d9b1bad389744d6653beba64aade32dd86c2bbb2973885531fe1 +size 3285474016 diff --git a/ARM-3B.f16.gguf b/ARM-3B.f16.gguf new file mode 100644 index 0000000..58c6f6a --- /dev/null +++ b/ARM-3B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ebdacdcc84221366a51ad9a5772bcc556020a739962bc287fd0d5af27b0d4eeb +size 6178314976 diff --git a/README.md b/README.md new file mode 100644 index 0000000..8dfc7bc --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: arm-team/ARM-3B +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/arm-team/ARM-3B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#ARM-3B-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/ARM-3B-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/ARM-3B-GGUF/resolve/main/ARM-3B.Q2_K.gguf) | Q2_K | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/ARM-3B-GGUF/resolve/main/ARM-3B.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/ARM-3B-GGUF/resolve/main/ARM-3B.Q3_K_M.gguf) | Q3_K_M | 1.7 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/ARM-3B-GGUF/resolve/main/ARM-3B.Q3_K_L.gguf) | Q3_K_L | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/ARM-3B-GGUF/resolve/main/ARM-3B.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/ARM-3B-GGUF/resolve/main/ARM-3B.Q4_K_S.gguf) | Q4_K_S | 1.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/ARM-3B-GGUF/resolve/main/ARM-3B.Q4_K_M.gguf) | Q4_K_M | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/ARM-3B-GGUF/resolve/main/ARM-3B.Q5_K_S.gguf) | Q5_K_S | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/ARM-3B-GGUF/resolve/main/ARM-3B.Q5_K_M.gguf) | Q5_K_M | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/ARM-3B-GGUF/resolve/main/ARM-3B.Q6_K.gguf) | Q6_K | 2.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/ARM-3B-GGUF/resolve/main/ARM-3B.Q8_0.gguf) | Q8_0 | 3.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/ARM-3B-GGUF/resolve/main/ARM-3B.f16.gguf) | f16 | 6.3 | 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. + +