commit 8ae3b41cb05e8a468d0cb5f080b5b6d8b384f645 Author: ModelHub XC Date: Mon Aug 10 00:47:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.2-1B-Instruct-zh-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..34a119e --- /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-3.2-1B-Instruct-zh.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-zh.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-zh.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-zh.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-zh.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-zh.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-zh.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-zh.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-zh.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-zh.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-zh.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-zh.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.2-1B-Instruct-zh.IQ4_XS.gguf b/Llama-3.2-1B-Instruct-zh.IQ4_XS.gguf new file mode 100644 index 0000000..f850815 --- /dev/null +++ b/Llama-3.2-1B-Instruct-zh.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ca4fb40494cd359e7b110445fe4ea090fe303da59cc06a1f5054d6fe9e53cbf +size 748384320 diff --git a/Llama-3.2-1B-Instruct-zh.Q2_K.gguf b/Llama-3.2-1B-Instruct-zh.Q2_K.gguf new file mode 100644 index 0000000..5a95735 --- /dev/null +++ b/Llama-3.2-1B-Instruct-zh.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4de62559eb1af93e42ab6b40b55c6cfc515af1ea70db4e0164debe3c41c6c106 +size 580874304 diff --git a/Llama-3.2-1B-Instruct-zh.Q3_K_L.gguf b/Llama-3.2-1B-Instruct-zh.Q3_K_L.gguf new file mode 100644 index 0000000..a3dce41 --- /dev/null +++ b/Llama-3.2-1B-Instruct-zh.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15d099439bbf83a1999b59b6c4617ab03d485238307730222e1b7624f4f3e737 +size 732524608 diff --git a/Llama-3.2-1B-Instruct-zh.Q3_K_M.gguf b/Llama-3.2-1B-Instruct-zh.Q3_K_M.gguf new file mode 100644 index 0000000..b62bce5 --- /dev/null +++ b/Llama-3.2-1B-Instruct-zh.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a6562977ec859a85fe38ae3d7485ac68038d1a5c448736e3d509b486bc3402de +size 690843712 diff --git a/Llama-3.2-1B-Instruct-zh.Q3_K_S.gguf b/Llama-3.2-1B-Instruct-zh.Q3_K_S.gguf new file mode 100644 index 0000000..a261264 --- /dev/null +++ b/Llama-3.2-1B-Instruct-zh.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a60ad10178b590a19aff759c06afe8dc73def8179af1e38c4de882317615891a +size 641691712 diff --git a/Llama-3.2-1B-Instruct-zh.Q4_K_M.gguf b/Llama-3.2-1B-Instruct-zh.Q4_K_M.gguf new file mode 100644 index 0000000..1ca9e5b --- /dev/null +++ b/Llama-3.2-1B-Instruct-zh.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2fb3229c60dbdfeb3da11453bdcd27e55cd783af9eac43508112fa4fd6c058c8 +size 807694400 diff --git a/Llama-3.2-1B-Instruct-zh.Q4_K_S.gguf b/Llama-3.2-1B-Instruct-zh.Q4_K_S.gguf new file mode 100644 index 0000000..72f95d9 --- /dev/null +++ b/Llama-3.2-1B-Instruct-zh.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e74364f395336a2461332be89517805226e21b072eda007dd1c5351f15fa8d1 +size 775647296 diff --git a/Llama-3.2-1B-Instruct-zh.Q5_K_M.gguf b/Llama-3.2-1B-Instruct-zh.Q5_K_M.gguf new file mode 100644 index 0000000..77624e0 --- /dev/null +++ b/Llama-3.2-1B-Instruct-zh.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07d10cde10aab91cc715c190eb79d1edd400d93055f1057edb2a42aaf71d7c06 +size 911503424 diff --git a/Llama-3.2-1B-Instruct-zh.Q5_K_S.gguf b/Llama-3.2-1B-Instruct-zh.Q5_K_S.gguf new file mode 100644 index 0000000..f3b0e64 --- /dev/null +++ b/Llama-3.2-1B-Instruct-zh.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ba1e21a922b68e9452900b9d6b5428890b3512ec10a2c16ee936c03f4f4318b +size 892563520 diff --git a/Llama-3.2-1B-Instruct-zh.Q6_K.gguf b/Llama-3.2-1B-Instruct-zh.Q6_K.gguf new file mode 100644 index 0000000..31d5071 --- /dev/null +++ b/Llama-3.2-1B-Instruct-zh.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c177a6e284fe00c33489832b1057673ec77faf84435a49ec2e7277f66548c939 +size 1021800512 diff --git a/Llama-3.2-1B-Instruct-zh.Q8_0.gguf b/Llama-3.2-1B-Instruct-zh.Q8_0.gguf new file mode 100644 index 0000000..a645931 --- /dev/null +++ b/Llama-3.2-1B-Instruct-zh.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:847fef343b7c24c8ea37aa12f5e2e1ab002d7fc32edb1e1a13f3446e96f31128 +size 1321082944 diff --git a/Llama-3.2-1B-Instruct-zh.f16.gguf b/Llama-3.2-1B-Instruct-zh.f16.gguf new file mode 100644 index 0000000..c4cb964 --- /dev/null +++ b/Llama-3.2-1B-Instruct-zh.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2286105cd92d160b83695bc7d3d706331af9ebe3ae09c267386a8fa10d6df79a +size 2479595584 diff --git a/README.md b/README.md new file mode 100644 index 0000000..06d2e5b --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: autoprogrammer/Llama-3.2-1B-Instruct-zh +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/autoprogrammer/Llama-3.2-1B-Instruct-zh + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama-3.2-1B-Instruct-zh-GGUF).*** + +weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. +## 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-Instruct-zh-GGUF/resolve/main/Llama-3.2-1B-Instruct-zh.Q2_K.gguf) | Q2_K | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-zh-GGUF/resolve/main/Llama-3.2-1B-Instruct-zh.Q3_K_S.gguf) | Q3_K_S | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-zh-GGUF/resolve/main/Llama-3.2-1B-Instruct-zh.Q3_K_M.gguf) | Q3_K_M | 0.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-zh-GGUF/resolve/main/Llama-3.2-1B-Instruct-zh.Q3_K_L.gguf) | Q3_K_L | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-zh-GGUF/resolve/main/Llama-3.2-1B-Instruct-zh.IQ4_XS.gguf) | IQ4_XS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-zh-GGUF/resolve/main/Llama-3.2-1B-Instruct-zh.Q4_K_S.gguf) | Q4_K_S | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-zh-GGUF/resolve/main/Llama-3.2-1B-Instruct-zh.Q4_K_M.gguf) | Q4_K_M | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-zh-GGUF/resolve/main/Llama-3.2-1B-Instruct-zh.Q5_K_S.gguf) | Q5_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-zh-GGUF/resolve/main/Llama-3.2-1B-Instruct-zh.Q5_K_M.gguf) | Q5_K_M | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-zh-GGUF/resolve/main/Llama-3.2-1B-Instruct-zh.Q6_K.gguf) | Q6_K | 1.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-zh-GGUF/resolve/main/Llama-3.2-1B-Instruct-zh.Q8_0.gguf) | Q8_0 | 1.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-zh-GGUF/resolve/main/Llama-3.2-1B-Instruct-zh.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. + +