commit 06838735a44c54ffe02e58942825f3a8c0a26cee Author: ModelHub XC Date: Fri Oct 30 19:42:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/llama-3.2-1B-spinquant-hf-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..d231d24 --- /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 +llama-3.2-1B-spinquant-hf.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-1B-spinquant-hf.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-1B-spinquant-hf.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-1B-spinquant-hf.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-1B-spinquant-hf.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-1B-spinquant-hf.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-1B-spinquant-hf.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-1B-spinquant-hf.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-1B-spinquant-hf.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-1B-spinquant-hf.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-1B-spinquant-hf.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-1B-spinquant-hf.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..b553d01 --- /dev/null +++ b/README.md @@ -0,0 +1,65 @@ +--- +base_model: Hjgugugjhuhjggg/llama-3.2-1B-spinquant-hf +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/Hjgugugjhuhjggg/llama-3.2-1B-spinquant-hf + + +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/llama-3.2-1B-spinquant-hf-GGUF/resolve/main/llama-3.2-1B-spinquant-hf.Q2_K.gguf) | Q2_K | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-1B-spinquant-hf-GGUF/resolve/main/llama-3.2-1B-spinquant-hf.Q3_K_S.gguf) | Q3_K_S | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-1B-spinquant-hf-GGUF/resolve/main/llama-3.2-1B-spinquant-hf.Q3_K_M.gguf) | Q3_K_M | 0.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-1B-spinquant-hf-GGUF/resolve/main/llama-3.2-1B-spinquant-hf.Q3_K_L.gguf) | Q3_K_L | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-1B-spinquant-hf-GGUF/resolve/main/llama-3.2-1B-spinquant-hf.IQ4_XS.gguf) | IQ4_XS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-1B-spinquant-hf-GGUF/resolve/main/llama-3.2-1B-spinquant-hf.Q4_0_4_4.gguf) | Q4_0_4_4 | 0.9 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-1B-spinquant-hf-GGUF/resolve/main/llama-3.2-1B-spinquant-hf.Q4_K_S.gguf) | Q4_K_S | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-1B-spinquant-hf-GGUF/resolve/main/llama-3.2-1B-spinquant-hf.Q4_K_M.gguf) | Q4_K_M | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-1B-spinquant-hf-GGUF/resolve/main/llama-3.2-1B-spinquant-hf.Q5_K_S.gguf) | Q5_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-1B-spinquant-hf-GGUF/resolve/main/llama-3.2-1B-spinquant-hf.Q5_K_M.gguf) | Q5_K_M | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-1B-spinquant-hf-GGUF/resolve/main/llama-3.2-1B-spinquant-hf.Q6_K.gguf) | Q6_K | 1.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-1B-spinquant-hf-GGUF/resolve/main/llama-3.2-1B-spinquant-hf.Q8_0.gguf) | Q8_0 | 1.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-1B-spinquant-hf-GGUF/resolve/main/llama-3.2-1B-spinquant-hf.f16.gguf) | f16 | 2.6 | 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/llama-3.2-1B-spinquant-hf.IQ4_XS.gguf b/llama-3.2-1B-spinquant-hf.IQ4_XS.gguf new file mode 100644 index 0000000..70131fe --- /dev/null +++ b/llama-3.2-1B-spinquant-hf.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72f9e09fb843243ea4b66f7d7750c9f990124f43db2ab549ebe5e0029c76511a +size 748384352 diff --git a/llama-3.2-1B-spinquant-hf.Q2_K.gguf b/llama-3.2-1B-spinquant-hf.Q2_K.gguf new file mode 100644 index 0000000..4dc2b83 --- /dev/null +++ b/llama-3.2-1B-spinquant-hf.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8fb5070733026d5c3327ed6792ea9f1bc73f62fcac5bd66e4aa47ee19ed8ed98 +size 580874336 diff --git a/llama-3.2-1B-spinquant-hf.Q3_K_L.gguf b/llama-3.2-1B-spinquant-hf.Q3_K_L.gguf new file mode 100644 index 0000000..f5fb9dc --- /dev/null +++ b/llama-3.2-1B-spinquant-hf.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96e5130de36448f0b6523c79f7defcb3d4b50e77fdc60e38de3917247960f8b7 +size 732524640 diff --git a/llama-3.2-1B-spinquant-hf.Q3_K_M.gguf b/llama-3.2-1B-spinquant-hf.Q3_K_M.gguf new file mode 100644 index 0000000..7cef36f --- /dev/null +++ b/llama-3.2-1B-spinquant-hf.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d04242a0d7bd8a0e0c322ef0d89b5491be32d0da7ee36c663c262cc3d79392c5 +size 690843744 diff --git a/llama-3.2-1B-spinquant-hf.Q3_K_S.gguf b/llama-3.2-1B-spinquant-hf.Q3_K_S.gguf new file mode 100644 index 0000000..99c5be3 --- /dev/null +++ b/llama-3.2-1B-spinquant-hf.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61ee25fc514f2f8d59817016bce160b99839848226b78714a057a47027fe7ad2 +size 641691744 diff --git a/llama-3.2-1B-spinquant-hf.Q4_0_4_4.gguf b/llama-3.2-1B-spinquant-hf.Q4_0_4_4.gguf new file mode 100644 index 0000000..fbc8c4c --- /dev/null +++ b/llama-3.2-1B-spinquant-hf.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc9830ed2ca91e8ec1477642e82abeeed0251a4693f0cb4ab46026f091828f65 +size 770928736 diff --git a/llama-3.2-1B-spinquant-hf.Q4_K_M.gguf b/llama-3.2-1B-spinquant-hf.Q4_K_M.gguf new file mode 100644 index 0000000..e5a20d1 --- /dev/null +++ b/llama-3.2-1B-spinquant-hf.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd589fc0aa5818126607f82d4dbca815231a94e049b3c11ed10f105e5a535263 +size 807694432 diff --git a/llama-3.2-1B-spinquant-hf.Q4_K_S.gguf b/llama-3.2-1B-spinquant-hf.Q4_K_S.gguf new file mode 100644 index 0000000..b49be6f --- /dev/null +++ b/llama-3.2-1B-spinquant-hf.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34ae09b52c43462163fca8200ba1b556b200035c0179c8c74c0de6a274b82011 +size 775647328 diff --git a/llama-3.2-1B-spinquant-hf.Q5_K_M.gguf b/llama-3.2-1B-spinquant-hf.Q5_K_M.gguf new file mode 100644 index 0000000..04394f7 --- /dev/null +++ b/llama-3.2-1B-spinquant-hf.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4a30ab42cd7cb13449a29e3f220f7da1fb849f359a416bfc5725950ac3558ad +size 911503456 diff --git a/llama-3.2-1B-spinquant-hf.Q5_K_S.gguf b/llama-3.2-1B-spinquant-hf.Q5_K_S.gguf new file mode 100644 index 0000000..d0b16fb --- /dev/null +++ b/llama-3.2-1B-spinquant-hf.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:446ef8dfe4b1c953088eb0b87241eabca876edc9777080f3c7d0b04f70195a81 +size 892563552 diff --git a/llama-3.2-1B-spinquant-hf.Q6_K.gguf b/llama-3.2-1B-spinquant-hf.Q6_K.gguf new file mode 100644 index 0000000..7554328 --- /dev/null +++ b/llama-3.2-1B-spinquant-hf.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf5fda58e48df39020ffb7947dfff1073c600438911df4694067bc5e0e883ed3 +size 1021800544 diff --git a/llama-3.2-1B-spinquant-hf.Q8_0.gguf b/llama-3.2-1B-spinquant-hf.Q8_0.gguf new file mode 100644 index 0000000..921d780 --- /dev/null +++ b/llama-3.2-1B-spinquant-hf.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d5b51d6edd89444583d5a0e0d8f9f7e5e57e10cf87598f5cf36ced4c496d5d3 +size 1321082976 diff --git a/llama-3.2-1B-spinquant-hf.f16.gguf b/llama-3.2-1B-spinquant-hf.f16.gguf new file mode 100644 index 0000000..a352809 --- /dev/null +++ b/llama-3.2-1B-spinquant-hf.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4245ccb92ef0c87d4ae43cac795a5a4b57b1ece5140b1e4571c9d1e1056596d3 +size 2479595616