commit f10a89f3b2a0020f8effbc3967c65b9393e12f7e Author: ModelHub XC Date: Mon Jun 15 18:44:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/llama3.2-1b-neuspell-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..147ff85 --- /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 +llama3.2-1b-neuspell.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +llama3.2-1b-neuspell.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama3.2-1b-neuspell.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama3.2-1b-neuspell.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3.2-1b-neuspell.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3.2-1b-neuspell.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3.2-1b-neuspell.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3.2-1b-neuspell.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3.2-1b-neuspell.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3.2-1b-neuspell.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama3.2-1b-neuspell.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llama3.2-1b-neuspell.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..ffaede6 --- /dev/null +++ b/README.md @@ -0,0 +1,76 @@ +--- +base_model: manav-glean/llama3.2-1b-neuspell +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- trl +- sft +--- +## About + + + + + + +static quants of https://huggingface.co/manav-glean/llama3.2-1b-neuspell + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#llama3.2-1b-neuspell-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/llama3.2-1b-neuspell-GGUF/resolve/main/llama3.2-1b-neuspell.Q2_K.gguf) | Q2_K | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.2-1b-neuspell-GGUF/resolve/main/llama3.2-1b-neuspell.Q3_K_S.gguf) | Q3_K_S | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.2-1b-neuspell-GGUF/resolve/main/llama3.2-1b-neuspell.Q3_K_M.gguf) | Q3_K_M | 0.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama3.2-1b-neuspell-GGUF/resolve/main/llama3.2-1b-neuspell.Q3_K_L.gguf) | Q3_K_L | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.2-1b-neuspell-GGUF/resolve/main/llama3.2-1b-neuspell.IQ4_XS.gguf) | IQ4_XS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.2-1b-neuspell-GGUF/resolve/main/llama3.2-1b-neuspell.Q4_K_S.gguf) | Q4_K_S | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama3.2-1b-neuspell-GGUF/resolve/main/llama3.2-1b-neuspell.Q4_K_M.gguf) | Q4_K_M | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama3.2-1b-neuspell-GGUF/resolve/main/llama3.2-1b-neuspell.Q5_K_S.gguf) | Q5_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.2-1b-neuspell-GGUF/resolve/main/llama3.2-1b-neuspell.Q5_K_M.gguf) | Q5_K_M | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.2-1b-neuspell-GGUF/resolve/main/llama3.2-1b-neuspell.Q6_K.gguf) | Q6_K | 1.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/llama3.2-1b-neuspell-GGUF/resolve/main/llama3.2-1b-neuspell.Q8_0.gguf) | Q8_0 | 1.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/llama3.2-1b-neuspell-GGUF/resolve/main/llama3.2-1b-neuspell.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/llama3.2-1b-neuspell.IQ4_XS.gguf b/llama3.2-1b-neuspell.IQ4_XS.gguf new file mode 100644 index 0000000..1a23f7b --- /dev/null +++ b/llama3.2-1b-neuspell.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8728dcd047d29630302388f12a06c5253cc1451d6d74686bbac816b8924cf840 +size 748385632 diff --git a/llama3.2-1b-neuspell.Q2_K.gguf b/llama3.2-1b-neuspell.Q2_K.gguf new file mode 100644 index 0000000..62f015a --- /dev/null +++ b/llama3.2-1b-neuspell.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34c6a52ae605d69576e2b0435065cb2addd8584b455137063852414d5f92ccce +size 580875616 diff --git a/llama3.2-1b-neuspell.Q3_K_L.gguf b/llama3.2-1b-neuspell.Q3_K_L.gguf new file mode 100644 index 0000000..869268f --- /dev/null +++ b/llama3.2-1b-neuspell.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc1bd73a6153592442c3130f7af647ec96a2f5ce3a95d1832e811f416c90f2d0 +size 732525920 diff --git a/llama3.2-1b-neuspell.Q3_K_M.gguf b/llama3.2-1b-neuspell.Q3_K_M.gguf new file mode 100644 index 0000000..3abf72f --- /dev/null +++ b/llama3.2-1b-neuspell.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f4acede2a8fa6cb30973cd138930d0c5d54d8aa5dfb037dcac0d64f70a11541 +size 690845024 diff --git a/llama3.2-1b-neuspell.Q3_K_S.gguf b/llama3.2-1b-neuspell.Q3_K_S.gguf new file mode 100644 index 0000000..0baff3f --- /dev/null +++ b/llama3.2-1b-neuspell.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b155bef93f4596d8eb29ce603188066d1954ef9ebe8a415281a218eb1500cff3 +size 641693024 diff --git a/llama3.2-1b-neuspell.Q4_K_M.gguf b/llama3.2-1b-neuspell.Q4_K_M.gguf new file mode 100644 index 0000000..c971498 --- /dev/null +++ b/llama3.2-1b-neuspell.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a51694a053f035b77e38fe632fc5227bf9aa08167711f1edf21335f910e31bd +size 807695712 diff --git a/llama3.2-1b-neuspell.Q4_K_S.gguf b/llama3.2-1b-neuspell.Q4_K_S.gguf new file mode 100644 index 0000000..8f8b99d --- /dev/null +++ b/llama3.2-1b-neuspell.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8884dff38b373e96a348d29ba237cb23cbbb10d30b38efad887079c8b0a580a9 +size 775648608 diff --git a/llama3.2-1b-neuspell.Q5_K_M.gguf b/llama3.2-1b-neuspell.Q5_K_M.gguf new file mode 100644 index 0000000..3156c22 --- /dev/null +++ b/llama3.2-1b-neuspell.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ac5fcab4fc9aef2d9230ec0a1318d6a2d5de2c34b812dc4a5dac91a441f0a0b +size 911504736 diff --git a/llama3.2-1b-neuspell.Q5_K_S.gguf b/llama3.2-1b-neuspell.Q5_K_S.gguf new file mode 100644 index 0000000..a836451 --- /dev/null +++ b/llama3.2-1b-neuspell.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da4d19d9e37084d4351a97320de2bfb77f2ebf65c28bb0d318ef3d6e1fa09da8 +size 892564832 diff --git a/llama3.2-1b-neuspell.Q6_K.gguf b/llama3.2-1b-neuspell.Q6_K.gguf new file mode 100644 index 0000000..450b693 --- /dev/null +++ b/llama3.2-1b-neuspell.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9aeb1b299dd5c25f1477b0c1ebb5c91f433c60ba37e3e47d62380e1039e4711a +size 1021801824 diff --git a/llama3.2-1b-neuspell.Q8_0.gguf b/llama3.2-1b-neuspell.Q8_0.gguf new file mode 100644 index 0000000..b8ce177 --- /dev/null +++ b/llama3.2-1b-neuspell.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9548fee8a42404a6bb3ba66113c9846b23e022831e566885da694581001289a +size 1321084256 diff --git a/llama3.2-1b-neuspell.f16.gguf b/llama3.2-1b-neuspell.f16.gguf new file mode 100644 index 0000000..40edce5 --- /dev/null +++ b/llama3.2-1b-neuspell.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd0c9c5450a6d2b4c50cdb937b425bbfefb6ec3da0b61b215ecb1d14104a2b28 +size 2479596896