commit 82f90852d0670a7c7ed9ca69f8321933bc0f7ab8 Author: ModelHub XC Date: Mon May 11 03:48:58 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama_3.2_3b_Kermes_v2.1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..d51cb59 --- /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_v2.1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.2_3b_Kermes_v2.1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.2_3b_Kermes_v2.1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.2_3b_Kermes_v2.1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.2_3b_Kermes_v2.1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.2_3b_Kermes_v2.1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.2_3b_Kermes_v2.1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.2_3b_Kermes_v2.1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.2_3b_Kermes_v2.1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.2_3b_Kermes_v2.1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.2_3b_Kermes_v2.1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.2_3b_Kermes_v2.1.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama_3.2_3b_Kermes_v2.1.IQ4_XS.gguf b/Llama_3.2_3b_Kermes_v2.1.IQ4_XS.gguf new file mode 100644 index 0000000..17e7b3b --- /dev/null +++ b/Llama_3.2_3b_Kermes_v2.1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00f229fda13293b7b83f4746d0f96b68dffa9d0f591e29845bb4fd20f45a4d80 +size 1840903488 diff --git a/Llama_3.2_3b_Kermes_v2.1.Q2_K.gguf b/Llama_3.2_3b_Kermes_v2.1.Q2_K.gguf new file mode 100644 index 0000000..cb50dd2 --- /dev/null +++ b/Llama_3.2_3b_Kermes_v2.1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:caaedbe4effdcdbc26904fd74a5c81aab67e7c0c26d1676e86a87598ce5801f7 +size 1363932480 diff --git a/Llama_3.2_3b_Kermes_v2.1.Q3_K_L.gguf b/Llama_3.2_3b_Kermes_v2.1.Q3_K_L.gguf new file mode 100644 index 0000000..a01e4e6 --- /dev/null +++ b/Llama_3.2_3b_Kermes_v2.1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d871e6ff32fdbb4d1a9652308f323a34214278e5e58193441e11b5a68032d434 +size 1815344448 diff --git a/Llama_3.2_3b_Kermes_v2.1.Q3_K_M.gguf b/Llama_3.2_3b_Kermes_v2.1.Q3_K_M.gguf new file mode 100644 index 0000000..af24241 --- /dev/null +++ b/Llama_3.2_3b_Kermes_v2.1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf890f6d9589d70cc2814b2b1e4513e04972579d1d92afd1bcaa9c70ec02dc24 +size 1687156032 diff --git a/Llama_3.2_3b_Kermes_v2.1.Q3_K_S.gguf b/Llama_3.2_3b_Kermes_v2.1.Q3_K_S.gguf new file mode 100644 index 0000000..595a583 --- /dev/null +++ b/Llama_3.2_3b_Kermes_v2.1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6252e1ef209489be58330b3042dede307610c92c99c2df12e04b1e11d4855e8 +size 1542845760 diff --git a/Llama_3.2_3b_Kermes_v2.1.Q4_K_M.gguf b/Llama_3.2_3b_Kermes_v2.1.Q4_K_M.gguf new file mode 100644 index 0000000..7f91ab9 --- /dev/null +++ b/Llama_3.2_3b_Kermes_v2.1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c84ebf1459f76d1e5b055a6b2aab0503d85d8a7d05472abc5a9f966e6311b589 +size 2019374400 diff --git a/Llama_3.2_3b_Kermes_v2.1.Q4_K_S.gguf b/Llama_3.2_3b_Kermes_v2.1.Q4_K_S.gguf new file mode 100644 index 0000000..b3e86a3 --- /dev/null +++ b/Llama_3.2_3b_Kermes_v2.1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9329a274c1f61d5f4e8bc235e77741cc3c90a8b8972c96ec346d2672ade7bb3 +size 1928197440 diff --git a/Llama_3.2_3b_Kermes_v2.1.Q5_K_M.gguf b/Llama_3.2_3b_Kermes_v2.1.Q5_K_M.gguf new file mode 100644 index 0000000..53daa8b --- /dev/null +++ b/Llama_3.2_3b_Kermes_v2.1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f297e4a62a980a4522151aa3cc8c6ba9878654b61c0dbf188957634240dec547 +size 2322150720 diff --git a/Llama_3.2_3b_Kermes_v2.1.Q5_K_S.gguf b/Llama_3.2_3b_Kermes_v2.1.Q5_K_S.gguf new file mode 100644 index 0000000..a967927 --- /dev/null +++ b/Llama_3.2_3b_Kermes_v2.1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21d55e874cf9c500b28aeae4fb47cf72aec084b822193a0eb535f6a66b062e63 +size 2269508928 diff --git a/Llama_3.2_3b_Kermes_v2.1.Q6_K.gguf b/Llama_3.2_3b_Kermes_v2.1.Q6_K.gguf new file mode 100644 index 0000000..c91c69b --- /dev/null +++ b/Llama_3.2_3b_Kermes_v2.1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b64d265aa88f4d72f0acacf279c4d04089f3a1409885651cbbee0c4ef3e8e1b2 +size 2643850560 diff --git a/Llama_3.2_3b_Kermes_v2.1.Q8_0.gguf b/Llama_3.2_3b_Kermes_v2.1.Q8_0.gguf new file mode 100644 index 0000000..b53ee84 --- /dev/null +++ b/Llama_3.2_3b_Kermes_v2.1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55e6a3fb5b16ef0abe7ea5f3e078e1fd54f992eaa68fedd7ce1420ffb1413476 +size 3421896000 diff --git a/Llama_3.2_3b_Kermes_v2.1.f16.gguf b/Llama_3.2_3b_Kermes_v2.1.f16.gguf new file mode 100644 index 0000000..9f7724e --- /dev/null +++ b/Llama_3.2_3b_Kermes_v2.1.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2c03782a35a3f372256020c3511461eaad4df3a2f2b3bec43a300e1564772d7 +size 6433684800 diff --git a/README.md b/README.md new file mode 100644 index 0000000..edb8d96 --- /dev/null +++ b/README.md @@ -0,0 +1,67 @@ +--- +base_model: Nexesenex/Llama_3.2_3b_Kermes_v2.1 +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_v2.1 + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama_3.2_3b_Kermes_v2.1-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_v2.1-GGUF/resolve/main/Llama_3.2_3b_Kermes_v2.1.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.2_3b_Kermes_v2.1-GGUF/resolve/main/Llama_3.2_3b_Kermes_v2.1.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.2_3b_Kermes_v2.1-GGUF/resolve/main/Llama_3.2_3b_Kermes_v2.1.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.2_3b_Kermes_v2.1-GGUF/resolve/main/Llama_3.2_3b_Kermes_v2.1.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.2_3b_Kermes_v2.1-GGUF/resolve/main/Llama_3.2_3b_Kermes_v2.1.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.2_3b_Kermes_v2.1-GGUF/resolve/main/Llama_3.2_3b_Kermes_v2.1.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.2_3b_Kermes_v2.1-GGUF/resolve/main/Llama_3.2_3b_Kermes_v2.1.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.2_3b_Kermes_v2.1-GGUF/resolve/main/Llama_3.2_3b_Kermes_v2.1.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.2_3b_Kermes_v2.1-GGUF/resolve/main/Llama_3.2_3b_Kermes_v2.1.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.2_3b_Kermes_v2.1-GGUF/resolve/main/Llama_3.2_3b_Kermes_v2.1.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.2_3b_Kermes_v2.1-GGUF/resolve/main/Llama_3.2_3b_Kermes_v2.1.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.2_3b_Kermes_v2.1-GGUF/resolve/main/Llama_3.2_3b_Kermes_v2.1.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. + +