commit 8557c04f7a456edae124a002c1d259d41f34547c Author: ModelHub XC Date: Sun Jun 14 07:50:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/epstein-llama-3.2-3B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..4a4d70d --- /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 +epstein-llama-3.2-3B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +epstein-llama-3.2-3B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +epstein-llama-3.2-3B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +epstein-llama-3.2-3B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +epstein-llama-3.2-3B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +epstein-llama-3.2-3B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +epstein-llama-3.2-3B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +epstein-llama-3.2-3B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +epstein-llama-3.2-3B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +epstein-llama-3.2-3B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +epstein-llama-3.2-3B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +epstein-llama-3.2-3B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..c1b2163 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: nyanya3/epstein-llama-3.2-3B +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/nyanya3/epstein-llama-3.2-3B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#epstein-llama-3.2-3B-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/epstein-llama-3.2-3B-GGUF/resolve/main/epstein-llama-3.2-3B.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/epstein-llama-3.2-3B-GGUF/resolve/main/epstein-llama-3.2-3B.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/epstein-llama-3.2-3B-GGUF/resolve/main/epstein-llama-3.2-3B.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/epstein-llama-3.2-3B-GGUF/resolve/main/epstein-llama-3.2-3B.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/epstein-llama-3.2-3B-GGUF/resolve/main/epstein-llama-3.2-3B.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/epstein-llama-3.2-3B-GGUF/resolve/main/epstein-llama-3.2-3B.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/epstein-llama-3.2-3B-GGUF/resolve/main/epstein-llama-3.2-3B.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/epstein-llama-3.2-3B-GGUF/resolve/main/epstein-llama-3.2-3B.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/epstein-llama-3.2-3B-GGUF/resolve/main/epstein-llama-3.2-3B.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/epstein-llama-3.2-3B-GGUF/resolve/main/epstein-llama-3.2-3B.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/epstein-llama-3.2-3B-GGUF/resolve/main/epstein-llama-3.2-3B.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/epstein-llama-3.2-3B-GGUF/resolve/main/epstein-llama-3.2-3B.f16.gguf) | f16 | 6.5 | 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/epstein-llama-3.2-3B.IQ4_XS.gguf b/epstein-llama-3.2-3B.IQ4_XS.gguf new file mode 100644 index 0000000..9094eb2 --- /dev/null +++ b/epstein-llama-3.2-3B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18869d253d76c152572d1709100fa7a325493bbf443600bbbf5b9914efa369e2 +size 1840906848 diff --git a/epstein-llama-3.2-3B.Q2_K.gguf b/epstein-llama-3.2-3B.Q2_K.gguf new file mode 100644 index 0000000..d066deb --- /dev/null +++ b/epstein-llama-3.2-3B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6ce682ff92dbf1cf74883eb1274805d15ea060d0256d2bcb75dba8405f30567 +size 1363935840 diff --git a/epstein-llama-3.2-3B.Q3_K_L.gguf b/epstein-llama-3.2-3B.Q3_K_L.gguf new file mode 100644 index 0000000..517308d --- /dev/null +++ b/epstein-llama-3.2-3B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59032d7b8a85d05bc9cff92d1f6ad3ddd87fcec0f60927ef2756e21bcee37ddc +size 1815347808 diff --git a/epstein-llama-3.2-3B.Q3_K_M.gguf b/epstein-llama-3.2-3B.Q3_K_M.gguf new file mode 100644 index 0000000..39d67c1 --- /dev/null +++ b/epstein-llama-3.2-3B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d756667979af2f3fe3e5fbf23c311efa0eb8a13e65781ba2341e335f82528e3 +size 1687159392 diff --git a/epstein-llama-3.2-3B.Q3_K_S.gguf b/epstein-llama-3.2-3B.Q3_K_S.gguf new file mode 100644 index 0000000..a108f6b --- /dev/null +++ b/epstein-llama-3.2-3B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d45cc770ef8172411346689cbb058eb1da25a3661d80e71bedbc386a444b37b +size 1542849120 diff --git a/epstein-llama-3.2-3B.Q4_K_M.gguf b/epstein-llama-3.2-3B.Q4_K_M.gguf new file mode 100644 index 0000000..4c1095a --- /dev/null +++ b/epstein-llama-3.2-3B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57e7f09aec373ebfa79c93e8a0b2fc4ab4b253bb462951fc6157c04244373c30 +size 2019377760 diff --git a/epstein-llama-3.2-3B.Q4_K_S.gguf b/epstein-llama-3.2-3B.Q4_K_S.gguf new file mode 100644 index 0000000..d779aba --- /dev/null +++ b/epstein-llama-3.2-3B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3f6c372a4e15e3f12614fbfb011dde4d4a613121df7a4c92fe386b925bb0b36 +size 1928200800 diff --git a/epstein-llama-3.2-3B.Q5_K_M.gguf b/epstein-llama-3.2-3B.Q5_K_M.gguf new file mode 100644 index 0000000..4277e41 --- /dev/null +++ b/epstein-llama-3.2-3B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:abc543f15818c53ca3a9e8b616bf795e4fc25f3df4bbee5c8be29ae0fc55fa59 +size 2322154080 diff --git a/epstein-llama-3.2-3B.Q5_K_S.gguf b/epstein-llama-3.2-3B.Q5_K_S.gguf new file mode 100644 index 0000000..f19a69d --- /dev/null +++ b/epstein-llama-3.2-3B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:881c514b16b89849c65c2961b812e3d30c586dd7248f171d6d1addcc3ab7fdc6 +size 2269512288 diff --git a/epstein-llama-3.2-3B.Q6_K.gguf b/epstein-llama-3.2-3B.Q6_K.gguf new file mode 100644 index 0000000..6c98dd2 --- /dev/null +++ b/epstein-llama-3.2-3B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a60754dea4612ef4f5ab451fe3d5cdf070a8623c3653acc501fc758ada291fbc +size 2643853920 diff --git a/epstein-llama-3.2-3B.Q8_0.gguf b/epstein-llama-3.2-3B.Q8_0.gguf new file mode 100644 index 0000000..58e6d8d --- /dev/null +++ b/epstein-llama-3.2-3B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59930a2c60158f929d2b892bf346cea92b58e520e5a9380d0fefcf31f7eb078f +size 3421899360 diff --git a/epstein-llama-3.2-3B.f16.gguf b/epstein-llama-3.2-3B.f16.gguf new file mode 100644 index 0000000..7532963 --- /dev/null +++ b/epstein-llama-3.2-3B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d27babe56925481e2449c15f68bfb7315b6b90dab78e941bc44c571df94530da +size 6433688160