commit 0b90cf1fcfa1ae6dc042c4bd257d7efaeb65fdef Author: ModelHub XC Date: Wed Apr 22 00:46:56 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.2-1B-it-chinese-kyara-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..fc22ac5 --- /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-3.2-1B-it-chinese-kyara.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-it-chinese-kyara.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-it-chinese-kyara.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-it-chinese-kyara.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-it-chinese-kyara.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-it-chinese-kyara.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-it-chinese-kyara.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-it-chinese-kyara.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-it-chinese-kyara.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-it-chinese-kyara.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-it-chinese-kyara.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-it-chinese-kyara.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-it-chinese-kyara.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.2-1B-it-chinese-kyara.IQ4_XS.gguf b/Llama-3.2-1B-it-chinese-kyara.IQ4_XS.gguf new file mode 100644 index 0000000..7d5e22d --- /dev/null +++ b/Llama-3.2-1B-it-chinese-kyara.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75f60dcbfc401ead449c8c7e0797b64a77e9e8402f91a9a60e8d0694d2b4ef3d +size 748381440 diff --git a/Llama-3.2-1B-it-chinese-kyara.Q2_K.gguf b/Llama-3.2-1B-it-chinese-kyara.Q2_K.gguf new file mode 100644 index 0000000..2ded2be --- /dev/null +++ b/Llama-3.2-1B-it-chinese-kyara.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78c4c145a0073eadf525eab97a6ff3ce3c27baac8e3561ecd5b3785a0f54fc05 +size 580871424 diff --git a/Llama-3.2-1B-it-chinese-kyara.Q3_K_L.gguf b/Llama-3.2-1B-it-chinese-kyara.Q3_K_L.gguf new file mode 100644 index 0000000..130529e --- /dev/null +++ b/Llama-3.2-1B-it-chinese-kyara.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0351bb3c56371140e9a04098560dbaa5a2702d71a9a3bd6bc8a1b3ab347db58 +size 732521728 diff --git a/Llama-3.2-1B-it-chinese-kyara.Q3_K_M.gguf b/Llama-3.2-1B-it-chinese-kyara.Q3_K_M.gguf new file mode 100644 index 0000000..5cfe641 --- /dev/null +++ b/Llama-3.2-1B-it-chinese-kyara.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40b1813322b3d98f98c38cae90af2c6ef9c2bc81b8fe897e90b5b38d0ac7efc6 +size 690840832 diff --git a/Llama-3.2-1B-it-chinese-kyara.Q3_K_S.gguf b/Llama-3.2-1B-it-chinese-kyara.Q3_K_S.gguf new file mode 100644 index 0000000..2798a66 --- /dev/null +++ b/Llama-3.2-1B-it-chinese-kyara.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a5b269207385e5f1a20617de561a7554beac8dff667145ed0987b9b02aad9cf +size 641688832 diff --git a/Llama-3.2-1B-it-chinese-kyara.Q4_0_4_4.gguf b/Llama-3.2-1B-it-chinese-kyara.Q4_0_4_4.gguf new file mode 100644 index 0000000..481d959 --- /dev/null +++ b/Llama-3.2-1B-it-chinese-kyara.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9cb6811fc04015f67867a6966b4c51ba7b370380ac604302d545666c61689ff8 +size 770925824 diff --git a/Llama-3.2-1B-it-chinese-kyara.Q4_K_M.gguf b/Llama-3.2-1B-it-chinese-kyara.Q4_K_M.gguf new file mode 100644 index 0000000..8003cb9 --- /dev/null +++ b/Llama-3.2-1B-it-chinese-kyara.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8bd2a69b7686c7f644f505ca4316f9d45033cff42324ce6d2e0e06f0ac5ef90 +size 807691520 diff --git a/Llama-3.2-1B-it-chinese-kyara.Q4_K_S.gguf b/Llama-3.2-1B-it-chinese-kyara.Q4_K_S.gguf new file mode 100644 index 0000000..523a8a4 --- /dev/null +++ b/Llama-3.2-1B-it-chinese-kyara.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44a54873df14ab0fd390da0e119d04a7970f07d65055e03483927fdb514cf1ef +size 775644416 diff --git a/Llama-3.2-1B-it-chinese-kyara.Q5_K_M.gguf b/Llama-3.2-1B-it-chinese-kyara.Q5_K_M.gguf new file mode 100644 index 0000000..586aafb --- /dev/null +++ b/Llama-3.2-1B-it-chinese-kyara.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:741f37badf18463bd2941ea73e0e569b087dcd9c10b1ef9e38240d1c3c48d37e +size 911500544 diff --git a/Llama-3.2-1B-it-chinese-kyara.Q5_K_S.gguf b/Llama-3.2-1B-it-chinese-kyara.Q5_K_S.gguf new file mode 100644 index 0000000..17a338c --- /dev/null +++ b/Llama-3.2-1B-it-chinese-kyara.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cfc8a6acdf8ed4a751b06c64ea7795f7554652bd0cda2886fc2a0f217162185c +size 892560640 diff --git a/Llama-3.2-1B-it-chinese-kyara.Q6_K.gguf b/Llama-3.2-1B-it-chinese-kyara.Q6_K.gguf new file mode 100644 index 0000000..1b850fb --- /dev/null +++ b/Llama-3.2-1B-it-chinese-kyara.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10cbacf4a5015227d8387ee2f29cf66b6e322b5e97c457b83a14a95a8336c3f6 +size 1021797632 diff --git a/Llama-3.2-1B-it-chinese-kyara.Q8_0.gguf b/Llama-3.2-1B-it-chinese-kyara.Q8_0.gguf new file mode 100644 index 0000000..8732710 --- /dev/null +++ b/Llama-3.2-1B-it-chinese-kyara.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50d5e7a87ffe892017f411a2fc072ba98821ae10c65673754db4d3a717037eff +size 1321080064 diff --git a/Llama-3.2-1B-it-chinese-kyara.f16.gguf b/Llama-3.2-1B-it-chinese-kyara.f16.gguf new file mode 100644 index 0000000..ede8c38 --- /dev/null +++ b/Llama-3.2-1B-it-chinese-kyara.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3bfc5dbaaebe936d77ce71da5cdbde530e60e4eb9bb1f02fbc7de3ed81c02f71 +size 2479592704 diff --git a/README.md b/README.md new file mode 100644 index 0000000..4242cce --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: zake7749/Llama-3.2-1B-it-chinese-kyara +language: +- en +- zh +library_name: transformers +license: llama3.2 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/zake7749/Llama-3.2-1B-it-chinese-kyara + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-3.2-1B-it-chinese-kyara-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-3.2-1B-it-chinese-kyara-GGUF/resolve/main/Llama-3.2-1B-it-chinese-kyara.Q2_K.gguf) | Q2_K | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-it-chinese-kyara-GGUF/resolve/main/Llama-3.2-1B-it-chinese-kyara.Q3_K_S.gguf) | Q3_K_S | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-it-chinese-kyara-GGUF/resolve/main/Llama-3.2-1B-it-chinese-kyara.Q3_K_M.gguf) | Q3_K_M | 0.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-it-chinese-kyara-GGUF/resolve/main/Llama-3.2-1B-it-chinese-kyara.Q3_K_L.gguf) | Q3_K_L | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-it-chinese-kyara-GGUF/resolve/main/Llama-3.2-1B-it-chinese-kyara.IQ4_XS.gguf) | IQ4_XS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-it-chinese-kyara-GGUF/resolve/main/Llama-3.2-1B-it-chinese-kyara.Q4_0_4_4.gguf) | Q4_0_4_4 | 0.9 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-it-chinese-kyara-GGUF/resolve/main/Llama-3.2-1B-it-chinese-kyara.Q4_K_S.gguf) | Q4_K_S | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-it-chinese-kyara-GGUF/resolve/main/Llama-3.2-1B-it-chinese-kyara.Q4_K_M.gguf) | Q4_K_M | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-it-chinese-kyara-GGUF/resolve/main/Llama-3.2-1B-it-chinese-kyara.Q5_K_S.gguf) | Q5_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-it-chinese-kyara-GGUF/resolve/main/Llama-3.2-1B-it-chinese-kyara.Q5_K_M.gguf) | Q5_K_M | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-it-chinese-kyara-GGUF/resolve/main/Llama-3.2-1B-it-chinese-kyara.Q6_K.gguf) | Q6_K | 1.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-it-chinese-kyara-GGUF/resolve/main/Llama-3.2-1B-it-chinese-kyara.Q8_0.gguf) | Q8_0 | 1.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-it-chinese-kyara-GGUF/resolve/main/Llama-3.2-1B-it-chinese-kyara.f16.gguf) | f16 | 2.6 | 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. + +