commit 299aa4faed3aba48aea6a85a92edff9e22e378df Author: ModelHub XC Date: Fri Jul 10 13:33:10 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.2-Kapusta-3B-v8-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..96c56c1 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,48 @@ +*.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-Kapusta-3B-v8.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-Kapusta-3B-v8.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-Kapusta-3B-v8.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-Kapusta-3B-v8.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-Kapusta-3B-v8.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-Kapusta-3B-v8.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-Kapusta-3B-v8.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-Kapusta-3B-v8.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-Kapusta-3B-v8.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-Kapusta-3B-v8.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-Kapusta-3B-v8.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-Kapusta-3B-v8.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-Kapusta-3B-v8.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.2-Kapusta-3B-v8.IQ4_XS.gguf b/Llama-3.2-Kapusta-3B-v8.IQ4_XS.gguf new file mode 100644 index 0000000..37d3d35 --- /dev/null +++ b/Llama-3.2-Kapusta-3B-v8.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25800eb2331c127705cd5823ec2c16a27ae14763800f803e48f1dbe8aefc74d7 +size 2050224256 diff --git a/Llama-3.2-Kapusta-3B-v8.Q2_K.gguf b/Llama-3.2-Kapusta-3B-v8.Q2_K.gguf new file mode 100644 index 0000000..8af2295 --- /dev/null +++ b/Llama-3.2-Kapusta-3B-v8.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2daafbba4d22f049cd4dd7a717f83a4f7cb9b09c24e2df2136627c46755c0f4e +size 1493221504 diff --git a/Llama-3.2-Kapusta-3B-v8.Q3_K_L.gguf b/Llama-3.2-Kapusta-3B-v8.Q3_K_L.gguf new file mode 100644 index 0000000..68f5a28 --- /dev/null +++ b/Llama-3.2-Kapusta-3B-v8.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:675eacfa36ef0938ae749e5496f2f05673d298b135491d5ec984f55ab24a1c86 +size 1984649344 diff --git a/Llama-3.2-Kapusta-3B-v8.Q3_K_M.gguf b/Llama-3.2-Kapusta-3B-v8.Q3_K_M.gguf new file mode 100644 index 0000000..9cb739a --- /dev/null +++ b/Llama-3.2-Kapusta-3B-v8.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ff6cad914d56a21d880e4d0c7dc2ecbd5cb8d4c16c6923b8adb070ebc0927eb +size 1856460928 diff --git a/Llama-3.2-Kapusta-3B-v8.Q3_K_S.gguf b/Llama-3.2-Kapusta-3B-v8.Q3_K_S.gguf new file mode 100644 index 0000000..7755fee --- /dev/null +++ b/Llama-3.2-Kapusta-3B-v8.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09609263afe3e7f2726862f3d76500378babede817b59709c72bf96067f385c7 +size 1712150656 diff --git a/Llama-3.2-Kapusta-3B-v8.Q4_0_4_4.gguf b/Llama-3.2-Kapusta-3B-v8.Q4_0_4_4.gguf new file mode 100644 index 0000000..e8748c8 --- /dev/null +++ b/Llama-3.2-Kapusta-3B-v8.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62e76e4cfd5ee10650bac55fdb4b5b075122400ae9cbb6a012e6cf9a3c88a922 +size 2138820736 diff --git a/Llama-3.2-Kapusta-3B-v8.Q4_K_M.gguf b/Llama-3.2-Kapusta-3B-v8.Q4_K_M.gguf new file mode 100644 index 0000000..2deec62 --- /dev/null +++ b/Llama-3.2-Kapusta-3B-v8.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2fa2ed1b86dfd06efeb9a9bac2b77d139ddd1bcc529811aec9d15d8eba39964 +size 2241007744 diff --git a/Llama-3.2-Kapusta-3B-v8.Q4_K_S.gguf b/Llama-3.2-Kapusta-3B-v8.Q4_K_S.gguf new file mode 100644 index 0000000..0101589 --- /dev/null +++ b/Llama-3.2-Kapusta-3B-v8.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e448e064a08e0f8ba9fa0f84e4ae28f63951d0630cef1695fcd826e09bd5473a +size 2149830784 diff --git a/Llama-3.2-Kapusta-3B-v8.Q5_K_M.gguf b/Llama-3.2-Kapusta-3B-v8.Q5_K_M.gguf new file mode 100644 index 0000000..d4228d5 --- /dev/null +++ b/Llama-3.2-Kapusta-3B-v8.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28f4ad9a67af8f3cf67a63ad5ae2f9669df0fed505d2f8c5276bb91535909e7e +size 2593034368 diff --git a/Llama-3.2-Kapusta-3B-v8.Q5_K_S.gguf b/Llama-3.2-Kapusta-3B-v8.Q5_K_S.gguf new file mode 100644 index 0000000..90d7521 --- /dev/null +++ b/Llama-3.2-Kapusta-3B-v8.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6512137cfc8692aae4bd888fc6cfaa8d85ef4379008f38b54f752096abe96c58 +size 2540392576 diff --git a/Llama-3.2-Kapusta-3B-v8.Q6_K.gguf b/Llama-3.2-Kapusta-3B-v8.Q6_K.gguf new file mode 100644 index 0000000..6407455 --- /dev/null +++ b/Llama-3.2-Kapusta-3B-v8.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5aa61ed5b174fe1e9f107c95b8032c522b17ae0e95b1128f1e65beff2ef578f7 +size 2967062656 diff --git a/Llama-3.2-Kapusta-3B-v8.Q8_0.gguf b/Llama-3.2-Kapusta-3B-v8.Q8_0.gguf new file mode 100644 index 0000000..564d133 --- /dev/null +++ b/Llama-3.2-Kapusta-3B-v8.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a8fe5521bfb0961eb2a659f41c044d0c90a98939cf681e9a734eb78c32ba644 +size 3840530560 diff --git a/Llama-3.2-Kapusta-3B-v8.f16.gguf b/Llama-3.2-Kapusta-3B-v8.f16.gguf new file mode 100644 index 0000000..25d573a --- /dev/null +++ b/Llama-3.2-Kapusta-3B-v8.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3bc78308d95b4e85ca637f3d0d6782b0f6a45006633771ea01ded573fda1a475 +size 7221696640 diff --git a/README.md b/README.md new file mode 100644 index 0000000..1c3193c --- /dev/null +++ b/README.md @@ -0,0 +1,78 @@ +--- +base_model: Khetterman/Llama-3.2-Kapusta-3B-v8 +language: +- en +- ru +library_name: transformers +quantized_by: mradermacher +tags: +- mergekit +- merge +- bfloat16 +- safetensors +- llama +- llama-3 +- llama-3.2 +- 3b +- chat +- creative +- conversational +- not-for-all-audiences +--- +## About + + + + + + +static quants of https://huggingface.co/Khetterman/Llama-3.2-Kapusta-3B-v8 + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-3.2-Kapusta-3B-v8-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-Kapusta-3B-v8-GGUF/resolve/main/Llama-3.2-Kapusta-3B-v8.Q2_K.gguf) | Q2_K | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-Kapusta-3B-v8-GGUF/resolve/main/Llama-3.2-Kapusta-3B-v8.Q3_K_S.gguf) | Q3_K_S | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-Kapusta-3B-v8-GGUF/resolve/main/Llama-3.2-Kapusta-3B-v8.Q3_K_M.gguf) | Q3_K_M | 2.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-Kapusta-3B-v8-GGUF/resolve/main/Llama-3.2-Kapusta-3B-v8.Q3_K_L.gguf) | Q3_K_L | 2.1 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-Kapusta-3B-v8-GGUF/resolve/main/Llama-3.2-Kapusta-3B-v8.IQ4_XS.gguf) | IQ4_XS | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-Kapusta-3B-v8-GGUF/resolve/main/Llama-3.2-Kapusta-3B-v8.Q4_0_4_4.gguf) | Q4_0_4_4 | 2.2 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-Kapusta-3B-v8-GGUF/resolve/main/Llama-3.2-Kapusta-3B-v8.Q4_K_S.gguf) | Q4_K_S | 2.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-Kapusta-3B-v8-GGUF/resolve/main/Llama-3.2-Kapusta-3B-v8.Q4_K_M.gguf) | Q4_K_M | 2.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-Kapusta-3B-v8-GGUF/resolve/main/Llama-3.2-Kapusta-3B-v8.Q5_K_S.gguf) | Q5_K_S | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-Kapusta-3B-v8-GGUF/resolve/main/Llama-3.2-Kapusta-3B-v8.Q5_K_M.gguf) | Q5_K_M | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-Kapusta-3B-v8-GGUF/resolve/main/Llama-3.2-Kapusta-3B-v8.Q6_K.gguf) | Q6_K | 3.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-Kapusta-3B-v8-GGUF/resolve/main/Llama-3.2-Kapusta-3B-v8.Q8_0.gguf) | Q8_0 | 3.9 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-Kapusta-3B-v8-GGUF/resolve/main/Llama-3.2-Kapusta-3B-v8.f16.gguf) | f16 | 7.3 | 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. + +