commit d1fbdf430d0fb97d9f9cbdb252c848186b446254 Author: ModelHub XC Date: Sun Jul 12 09:10:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.2-Kapusta-JapanChibi-3B-v1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..9e00fbd --- /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-JapanChibi-3B-v1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-Kapusta-JapanChibi-3B-v1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-Kapusta-JapanChibi-3B-v1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-Kapusta-JapanChibi-3B-v1.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-Kapusta-JapanChibi-3B-v1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-Kapusta-JapanChibi-3B-v1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-Kapusta-JapanChibi-3B-v1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-Kapusta-JapanChibi-3B-v1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-Kapusta-JapanChibi-3B-v1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-Kapusta-JapanChibi-3B-v1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-Kapusta-JapanChibi-3B-v1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-Kapusta-JapanChibi-3B-v1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-Kapusta-JapanChibi-3B-v1.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.2-Kapusta-JapanChibi-3B-v1.IQ4_XS.gguf b/Llama-3.2-Kapusta-JapanChibi-3B-v1.IQ4_XS.gguf new file mode 100644 index 0000000..c4e4a90 --- /dev/null +++ b/Llama-3.2-Kapusta-JapanChibi-3B-v1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4942037bb87455b572072dcefd81ab05551de2f9dce989c640bb450185876f4 +size 2050221664 diff --git a/Llama-3.2-Kapusta-JapanChibi-3B-v1.Q2_K.gguf b/Llama-3.2-Kapusta-JapanChibi-3B-v1.Q2_K.gguf new file mode 100644 index 0000000..08e713c --- /dev/null +++ b/Llama-3.2-Kapusta-JapanChibi-3B-v1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e26bf3054e556d840e2bcc4ff9b11ffb8f8eb1eb54ce6b4177d9bb8b2a1aa90c +size 1493218912 diff --git a/Llama-3.2-Kapusta-JapanChibi-3B-v1.Q3_K_L.gguf b/Llama-3.2-Kapusta-JapanChibi-3B-v1.Q3_K_L.gguf new file mode 100644 index 0000000..4e20304 --- /dev/null +++ b/Llama-3.2-Kapusta-JapanChibi-3B-v1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10728d7c793df2833cbb7ae93ff84451778e656ebdc13e8c81f4a7684fbbf16d +size 1984646752 diff --git a/Llama-3.2-Kapusta-JapanChibi-3B-v1.Q3_K_M.gguf b/Llama-3.2-Kapusta-JapanChibi-3B-v1.Q3_K_M.gguf new file mode 100644 index 0000000..17c274e --- /dev/null +++ b/Llama-3.2-Kapusta-JapanChibi-3B-v1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3795e4cef8eec45bdc1941bc8034474ba6388e74f3ab88a744c2adc77e05f8a8 +size 1856458336 diff --git a/Llama-3.2-Kapusta-JapanChibi-3B-v1.Q3_K_S.gguf b/Llama-3.2-Kapusta-JapanChibi-3B-v1.Q3_K_S.gguf new file mode 100644 index 0000000..af9d3a4 --- /dev/null +++ b/Llama-3.2-Kapusta-JapanChibi-3B-v1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f59fd5f4694673d0f7546d06d73a4dc288b43e273e88306ba0dc01de78fc97d +size 1712148064 diff --git a/Llama-3.2-Kapusta-JapanChibi-3B-v1.Q4_0_4_4.gguf b/Llama-3.2-Kapusta-JapanChibi-3B-v1.Q4_0_4_4.gguf new file mode 100644 index 0000000..8b43d07 --- /dev/null +++ b/Llama-3.2-Kapusta-JapanChibi-3B-v1.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6b4b6fd6e2681e0bfda4b24a1f199c05db68b83c886afd357816b43e3b0ed42 +size 2138818144 diff --git a/Llama-3.2-Kapusta-JapanChibi-3B-v1.Q4_K_M.gguf b/Llama-3.2-Kapusta-JapanChibi-3B-v1.Q4_K_M.gguf new file mode 100644 index 0000000..84880bb --- /dev/null +++ b/Llama-3.2-Kapusta-JapanChibi-3B-v1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7917554517e801d22dbc697447ea095469891b1166b186d29a21a18cff543a34 +size 2241005152 diff --git a/Llama-3.2-Kapusta-JapanChibi-3B-v1.Q4_K_S.gguf b/Llama-3.2-Kapusta-JapanChibi-3B-v1.Q4_K_S.gguf new file mode 100644 index 0000000..46cd167 --- /dev/null +++ b/Llama-3.2-Kapusta-JapanChibi-3B-v1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48738155814bed05f30aca70c4f12b70d5a4cec146f1e0125e1621202051984e +size 2149828192 diff --git a/Llama-3.2-Kapusta-JapanChibi-3B-v1.Q5_K_M.gguf b/Llama-3.2-Kapusta-JapanChibi-3B-v1.Q5_K_M.gguf new file mode 100644 index 0000000..ca301ab --- /dev/null +++ b/Llama-3.2-Kapusta-JapanChibi-3B-v1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60bf4fc777d9cb7f766088be1b4104135cfe9de6c3f43bb3a2a884d7d09f059b +size 2593031776 diff --git a/Llama-3.2-Kapusta-JapanChibi-3B-v1.Q5_K_S.gguf b/Llama-3.2-Kapusta-JapanChibi-3B-v1.Q5_K_S.gguf new file mode 100644 index 0000000..26fd34b --- /dev/null +++ b/Llama-3.2-Kapusta-JapanChibi-3B-v1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2926dc2bcc1b4b88b9c9445c1db6301c351f358d722c2c0ccab2bdbbadfcb44a +size 2540389984 diff --git a/Llama-3.2-Kapusta-JapanChibi-3B-v1.Q6_K.gguf b/Llama-3.2-Kapusta-JapanChibi-3B-v1.Q6_K.gguf new file mode 100644 index 0000000..d1fa37a --- /dev/null +++ b/Llama-3.2-Kapusta-JapanChibi-3B-v1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3bda92c5da2b5305db57226c8a48e96e9ea343aaa4f3a686dee8e4b511be953 +size 2967060064 diff --git a/Llama-3.2-Kapusta-JapanChibi-3B-v1.Q8_0.gguf b/Llama-3.2-Kapusta-JapanChibi-3B-v1.Q8_0.gguf new file mode 100644 index 0000000..b8753c4 --- /dev/null +++ b/Llama-3.2-Kapusta-JapanChibi-3B-v1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:438ff688dc0b12f92b13682fb3072d427bf25b71543075e6ceca8bfc11e3e09b +size 3840527968 diff --git a/Llama-3.2-Kapusta-JapanChibi-3B-v1.f16.gguf b/Llama-3.2-Kapusta-JapanChibi-3B-v1.f16.gguf new file mode 100644 index 0000000..bc2814b --- /dev/null +++ b/Llama-3.2-Kapusta-JapanChibi-3B-v1.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44e6d9900224be2d938d484cbfeab533621993739870007a0c1633be43c365ca +size 7221694048 diff --git a/README.md b/README.md new file mode 100644 index 0000000..b7f8e6a --- /dev/null +++ b/README.md @@ -0,0 +1,78 @@ +--- +base_model: Khetterman/Llama-3.2-Kapusta-JapanChibi-3B-v1 +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-JapanChibi-3B-v1 + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-3.2-Kapusta-JapanChibi-3B-v1-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-JapanChibi-3B-v1-GGUF/resolve/main/Llama-3.2-Kapusta-JapanChibi-3B-v1.Q2_K.gguf) | Q2_K | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-Kapusta-JapanChibi-3B-v1-GGUF/resolve/main/Llama-3.2-Kapusta-JapanChibi-3B-v1.Q3_K_S.gguf) | Q3_K_S | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-Kapusta-JapanChibi-3B-v1-GGUF/resolve/main/Llama-3.2-Kapusta-JapanChibi-3B-v1.Q3_K_M.gguf) | Q3_K_M | 2.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-Kapusta-JapanChibi-3B-v1-GGUF/resolve/main/Llama-3.2-Kapusta-JapanChibi-3B-v1.Q3_K_L.gguf) | Q3_K_L | 2.1 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-Kapusta-JapanChibi-3B-v1-GGUF/resolve/main/Llama-3.2-Kapusta-JapanChibi-3B-v1.IQ4_XS.gguf) | IQ4_XS | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-Kapusta-JapanChibi-3B-v1-GGUF/resolve/main/Llama-3.2-Kapusta-JapanChibi-3B-v1.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-JapanChibi-3B-v1-GGUF/resolve/main/Llama-3.2-Kapusta-JapanChibi-3B-v1.Q4_K_S.gguf) | Q4_K_S | 2.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-Kapusta-JapanChibi-3B-v1-GGUF/resolve/main/Llama-3.2-Kapusta-JapanChibi-3B-v1.Q4_K_M.gguf) | Q4_K_M | 2.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-Kapusta-JapanChibi-3B-v1-GGUF/resolve/main/Llama-3.2-Kapusta-JapanChibi-3B-v1.Q5_K_S.gguf) | Q5_K_S | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-Kapusta-JapanChibi-3B-v1-GGUF/resolve/main/Llama-3.2-Kapusta-JapanChibi-3B-v1.Q5_K_M.gguf) | Q5_K_M | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-Kapusta-JapanChibi-3B-v1-GGUF/resolve/main/Llama-3.2-Kapusta-JapanChibi-3B-v1.Q6_K.gguf) | Q6_K | 3.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-Kapusta-JapanChibi-3B-v1-GGUF/resolve/main/Llama-3.2-Kapusta-JapanChibi-3B-v1.Q8_0.gguf) | Q8_0 | 3.9 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-Kapusta-JapanChibi-3B-v1-GGUF/resolve/main/Llama-3.2-Kapusta-JapanChibi-3B-v1.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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. + +