commit 586ec82e59cd1e415299803e5500af4aff2d57c8 Author: ModelHub XC Date: Wed Jun 24 09:50:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama_3.2_3b_Kermes_v2-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..7a58605 --- /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_3b_Kermes_v2.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.2_3b_Kermes_v2.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.2_3b_Kermes_v2.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.2_3b_Kermes_v2.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.2_3b_Kermes_v2.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.2_3b_Kermes_v2.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.2_3b_Kermes_v2.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.2_3b_Kermes_v2.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.2_3b_Kermes_v2.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.2_3b_Kermes_v2.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.2_3b_Kermes_v2.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.2_3b_Kermes_v2.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama_3.2_3b_Kermes_v2.IQ4_XS.gguf b/Llama_3.2_3b_Kermes_v2.IQ4_XS.gguf new file mode 100644 index 0000000..30b8bc2 --- /dev/null +++ b/Llama_3.2_3b_Kermes_v2.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2db1ed9e2990deae99b4bba5d5376b042c595bedd368e9f284201379d76159a +size 1840903488 diff --git a/Llama_3.2_3b_Kermes_v2.Q2_K.gguf b/Llama_3.2_3b_Kermes_v2.Q2_K.gguf new file mode 100644 index 0000000..54339c8 --- /dev/null +++ b/Llama_3.2_3b_Kermes_v2.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:596555c458c18553b4e540bd0d50c8d9e82e7aa58df489e66984d0a26e0b42ca +size 1363932480 diff --git a/Llama_3.2_3b_Kermes_v2.Q3_K_L.gguf b/Llama_3.2_3b_Kermes_v2.Q3_K_L.gguf new file mode 100644 index 0000000..0b6841b --- /dev/null +++ b/Llama_3.2_3b_Kermes_v2.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ebfd59c12da3a13e630a8ae1e1a2611e22efc0ce4cd84009a6244b3e835d0f8 +size 1815344448 diff --git a/Llama_3.2_3b_Kermes_v2.Q3_K_M.gguf b/Llama_3.2_3b_Kermes_v2.Q3_K_M.gguf new file mode 100644 index 0000000..033b8c8 --- /dev/null +++ b/Llama_3.2_3b_Kermes_v2.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e207ef699018e94e85bf3cb0df31d864904f2ec15d74c5b6f0ca1dd09440658 +size 1687156032 diff --git a/Llama_3.2_3b_Kermes_v2.Q3_K_S.gguf b/Llama_3.2_3b_Kermes_v2.Q3_K_S.gguf new file mode 100644 index 0000000..7c57503 --- /dev/null +++ b/Llama_3.2_3b_Kermes_v2.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5c4d2cace6f0587b1a80d8c0d17171a4d1968c030a189311f8bc2c536dac95e +size 1542845760 diff --git a/Llama_3.2_3b_Kermes_v2.Q4_K_M.gguf b/Llama_3.2_3b_Kermes_v2.Q4_K_M.gguf new file mode 100644 index 0000000..b04c383 --- /dev/null +++ b/Llama_3.2_3b_Kermes_v2.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a31120d774bdec766eb4e2c1d4321d8dabfcb4ed418ce00a83cc3d5a7a165f6 +size 2019374400 diff --git a/Llama_3.2_3b_Kermes_v2.Q4_K_S.gguf b/Llama_3.2_3b_Kermes_v2.Q4_K_S.gguf new file mode 100644 index 0000000..2c61e31 --- /dev/null +++ b/Llama_3.2_3b_Kermes_v2.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34a6d6534139598582328645c42bbe9c1900e14114a04b977b48491b79eec781 +size 1928197440 diff --git a/Llama_3.2_3b_Kermes_v2.Q5_K_M.gguf b/Llama_3.2_3b_Kermes_v2.Q5_K_M.gguf new file mode 100644 index 0000000..5c3255f --- /dev/null +++ b/Llama_3.2_3b_Kermes_v2.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27eee5b413065e28f2ca1af18a29335d5af32e8a8b58ea851982377eb0732eaf +size 2322150720 diff --git a/Llama_3.2_3b_Kermes_v2.Q5_K_S.gguf b/Llama_3.2_3b_Kermes_v2.Q5_K_S.gguf new file mode 100644 index 0000000..67684d8 --- /dev/null +++ b/Llama_3.2_3b_Kermes_v2.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4be9c136a0ae1a5160550ea3123a3391ec1c2bbfc5a84e93ecfda80d81faf4c0 +size 2269508928 diff --git a/Llama_3.2_3b_Kermes_v2.Q6_K.gguf b/Llama_3.2_3b_Kermes_v2.Q6_K.gguf new file mode 100644 index 0000000..c825db4 --- /dev/null +++ b/Llama_3.2_3b_Kermes_v2.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3f8389cd19f1e3d53be26365cf8fd5698ca25dae36ca67511d31743f4848183 +size 2643850560 diff --git a/Llama_3.2_3b_Kermes_v2.Q8_0.gguf b/Llama_3.2_3b_Kermes_v2.Q8_0.gguf new file mode 100644 index 0000000..e24cf3b --- /dev/null +++ b/Llama_3.2_3b_Kermes_v2.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c86c4925fc4d6dd5d3bff8ae700dbf60444dedfbea85909027cd679e4d6d46f +size 3421896000 diff --git a/Llama_3.2_3b_Kermes_v2.f16.gguf b/Llama_3.2_3b_Kermes_v2.f16.gguf new file mode 100644 index 0000000..64c1cbb --- /dev/null +++ b/Llama_3.2_3b_Kermes_v2.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd1cd6c0c238cc3cc52e277cb9f1c60112ac7d21302dd3cc7a1e0fa55d7ddb1a +size 6433684800 diff --git a/README.md b/README.md new file mode 100644 index 0000000..452e25f --- /dev/null +++ b/README.md @@ -0,0 +1,67 @@ +--- +base_model: Nexesenex/Llama_3.2_3b_Kermes_v2 +language: +- en +library_name: transformers +license: llama3.2 +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/Nexesenex/Llama_3.2_3b_Kermes_v2 + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama_3.2_3b_Kermes_v2-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/Llama_3.2_3b_Kermes_v2-GGUF/resolve/main/Llama_3.2_3b_Kermes_v2.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.2_3b_Kermes_v2-GGUF/resolve/main/Llama_3.2_3b_Kermes_v2.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.2_3b_Kermes_v2-GGUF/resolve/main/Llama_3.2_3b_Kermes_v2.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.2_3b_Kermes_v2-GGUF/resolve/main/Llama_3.2_3b_Kermes_v2.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.2_3b_Kermes_v2-GGUF/resolve/main/Llama_3.2_3b_Kermes_v2.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.2_3b_Kermes_v2-GGUF/resolve/main/Llama_3.2_3b_Kermes_v2.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.2_3b_Kermes_v2-GGUF/resolve/main/Llama_3.2_3b_Kermes_v2.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.2_3b_Kermes_v2-GGUF/resolve/main/Llama_3.2_3b_Kermes_v2.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.2_3b_Kermes_v2-GGUF/resolve/main/Llama_3.2_3b_Kermes_v2.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.2_3b_Kermes_v2-GGUF/resolve/main/Llama_3.2_3b_Kermes_v2.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.2_3b_Kermes_v2-GGUF/resolve/main/Llama_3.2_3b_Kermes_v2.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.2_3b_Kermes_v2-GGUF/resolve/main/Llama_3.2_3b_Kermes_v2.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. + +