commit dd008e9ecf4de47b292919ee4396e2bba36898ef Author: ModelHub XC Date: Tue Jun 2 06:45:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/llama-3.2-3B-Chinese-Elite-v2-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..e871173 --- /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-Chinese-Elite-v2.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-3B-Chinese-Elite-v2.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-3B-Chinese-Elite-v2.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-3B-Chinese-Elite-v2.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-3B-Chinese-Elite-v2.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-3B-Chinese-Elite-v2.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-3B-Chinese-Elite-v2.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-3B-Chinese-Elite-v2.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-3B-Chinese-Elite-v2.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-3B-Chinese-Elite-v2.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-3B-Chinese-Elite-v2.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-3B-Chinese-Elite-v2.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..c29d978 --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +base_model: Jackrong/llama-3.2-3B-Chinese-Elite-v2 +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +--- +## About + + + + + + + + + +static quants of https://huggingface.co/Jackrong/llama-3.2-3B-Chinese-Elite-v2 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#llama-3.2-3B-Chinese-Elite-v2-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-3.2-3B-Chinese-Elite-v2-GGUF/resolve/main/llama-3.2-3B-Chinese-Elite-v2.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-3B-Chinese-Elite-v2-GGUF/resolve/main/llama-3.2-3B-Chinese-Elite-v2.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-3B-Chinese-Elite-v2-GGUF/resolve/main/llama-3.2-3B-Chinese-Elite-v2.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-3B-Chinese-Elite-v2-GGUF/resolve/main/llama-3.2-3B-Chinese-Elite-v2.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-3B-Chinese-Elite-v2-GGUF/resolve/main/llama-3.2-3B-Chinese-Elite-v2.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-3B-Chinese-Elite-v2-GGUF/resolve/main/llama-3.2-3B-Chinese-Elite-v2.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-3B-Chinese-Elite-v2-GGUF/resolve/main/llama-3.2-3B-Chinese-Elite-v2.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-3B-Chinese-Elite-v2-GGUF/resolve/main/llama-3.2-3B-Chinese-Elite-v2.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-3B-Chinese-Elite-v2-GGUF/resolve/main/llama-3.2-3B-Chinese-Elite-v2.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-3B-Chinese-Elite-v2-GGUF/resolve/main/llama-3.2-3B-Chinese-Elite-v2.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-3B-Chinese-Elite-v2-GGUF/resolve/main/llama-3.2-3B-Chinese-Elite-v2.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-3B-Chinese-Elite-v2-GGUF/resolve/main/llama-3.2-3B-Chinese-Elite-v2.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. + + diff --git a/llama-3.2-3B-Chinese-Elite-v2.IQ4_XS.gguf b/llama-3.2-3B-Chinese-Elite-v2.IQ4_XS.gguf new file mode 100644 index 0000000..f52d9a8 --- /dev/null +++ b/llama-3.2-3B-Chinese-Elite-v2.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f5cfcd30ad5361d7021adffb2fe93d99aaf3095ab1aa611314c72f6b694277e +size 1840908128 diff --git a/llama-3.2-3B-Chinese-Elite-v2.Q2_K.gguf b/llama-3.2-3B-Chinese-Elite-v2.Q2_K.gguf new file mode 100644 index 0000000..03fffec --- /dev/null +++ b/llama-3.2-3B-Chinese-Elite-v2.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8262ab6dcbb48c81b288c4a453401ac64259226c0701eaae546baca5a4fdb9b5 +size 1363937120 diff --git a/llama-3.2-3B-Chinese-Elite-v2.Q3_K_L.gguf b/llama-3.2-3B-Chinese-Elite-v2.Q3_K_L.gguf new file mode 100644 index 0000000..97d2a06 --- /dev/null +++ b/llama-3.2-3B-Chinese-Elite-v2.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7aa3331377bc4ba613c1f2fc504e35c80daf017c502e3c38052bf017c57d0071 +size 1815349088 diff --git a/llama-3.2-3B-Chinese-Elite-v2.Q3_K_M.gguf b/llama-3.2-3B-Chinese-Elite-v2.Q3_K_M.gguf new file mode 100644 index 0000000..d841855 --- /dev/null +++ b/llama-3.2-3B-Chinese-Elite-v2.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5bcd13e6e06c09a859d16e0c797d08db4ae5a0af281db7e3b650fc170690e1d7 +size 1687160672 diff --git a/llama-3.2-3B-Chinese-Elite-v2.Q3_K_S.gguf b/llama-3.2-3B-Chinese-Elite-v2.Q3_K_S.gguf new file mode 100644 index 0000000..1c8d9b7 --- /dev/null +++ b/llama-3.2-3B-Chinese-Elite-v2.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95f092288d893cf0464341989914db07cc49c590c5c425259e8b9ccd39bbb649 +size 1542850400 diff --git a/llama-3.2-3B-Chinese-Elite-v2.Q4_K_M.gguf b/llama-3.2-3B-Chinese-Elite-v2.Q4_K_M.gguf new file mode 100644 index 0000000..8907cd4 --- /dev/null +++ b/llama-3.2-3B-Chinese-Elite-v2.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d29b8171850494c6e5f6f3f6c4d0dfc4c67052392381ce4c49c214b568204d66 +size 2019379040 diff --git a/llama-3.2-3B-Chinese-Elite-v2.Q4_K_S.gguf b/llama-3.2-3B-Chinese-Elite-v2.Q4_K_S.gguf new file mode 100644 index 0000000..60eef49 --- /dev/null +++ b/llama-3.2-3B-Chinese-Elite-v2.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d6a66be37807b913ff48443554c96d88d7d2c216e5cf302617a38b30fa47242 +size 1928202080 diff --git a/llama-3.2-3B-Chinese-Elite-v2.Q5_K_M.gguf b/llama-3.2-3B-Chinese-Elite-v2.Q5_K_M.gguf new file mode 100644 index 0000000..f487982 --- /dev/null +++ b/llama-3.2-3B-Chinese-Elite-v2.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7708423871ab88d796d65ddc94c34629eb7a6478b51ac511ab5a5b037cd5e0f +size 2322155360 diff --git a/llama-3.2-3B-Chinese-Elite-v2.Q5_K_S.gguf b/llama-3.2-3B-Chinese-Elite-v2.Q5_K_S.gguf new file mode 100644 index 0000000..bdd102a --- /dev/null +++ b/llama-3.2-3B-Chinese-Elite-v2.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52ec8c17eaa5ccb94e8638ba8b04cbb2c88a06751488c13a9962087ebf8fa3f3 +size 2269513568 diff --git a/llama-3.2-3B-Chinese-Elite-v2.Q6_K.gguf b/llama-3.2-3B-Chinese-Elite-v2.Q6_K.gguf new file mode 100644 index 0000000..5ef696c --- /dev/null +++ b/llama-3.2-3B-Chinese-Elite-v2.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d90be949858f9e85f4c68679408fbdd5cd7e1e1b93b0162b7d156b2fd3c403c +size 2643855200 diff --git a/llama-3.2-3B-Chinese-Elite-v2.Q8_0.gguf b/llama-3.2-3B-Chinese-Elite-v2.Q8_0.gguf new file mode 100644 index 0000000..20bb0f7 --- /dev/null +++ b/llama-3.2-3B-Chinese-Elite-v2.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74aeb5d2fbca2fa5e2e89dfe7a3bd4692c201556372e5f20cdf493842a0d8192 +size 3421900640 diff --git a/llama-3.2-3B-Chinese-Elite-v2.f16.gguf b/llama-3.2-3B-Chinese-Elite-v2.f16.gguf new file mode 100644 index 0000000..2f86d6a --- /dev/null +++ b/llama-3.2-3B-Chinese-Elite-v2.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0c51362188363847151cd49c8b6c8edfa2356775ad4ab42992063e5e264e3ac +size 6433689440