commit 5533f324e6edc8a99543f969ae0529a308e84461 Author: ModelHub XC Date: Sat Jun 13 07:30:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/llama-3.2-1B-CEH_v10-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..1128599 --- /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-CEH_v10.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-1B-CEH_v10.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-1B-CEH_v10.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-1B-CEH_v10.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-1B-CEH_v10.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-1B-CEH_v10.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-1B-CEH_v10.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-1B-CEH_v10.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-1B-CEH_v10.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-1B-CEH_v10.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-1B-CEH_v10.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-1B-CEH_v10.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..207fc81 --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: tamdd18/llama-3.2-1B-CEH_v10 +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/tamdd18/llama-3.2-1B-CEH_v10 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#llama-3.2-1B-CEH_v10-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-CEH_v10-GGUF/resolve/main/llama-3.2-1B-CEH_v10.Q2_K.gguf) | Q2_K | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-1B-CEH_v10-GGUF/resolve/main/llama-3.2-1B-CEH_v10.Q3_K_S.gguf) | Q3_K_S | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-1B-CEH_v10-GGUF/resolve/main/llama-3.2-1B-CEH_v10.Q3_K_M.gguf) | Q3_K_M | 0.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-1B-CEH_v10-GGUF/resolve/main/llama-3.2-1B-CEH_v10.Q3_K_L.gguf) | Q3_K_L | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-1B-CEH_v10-GGUF/resolve/main/llama-3.2-1B-CEH_v10.IQ4_XS.gguf) | IQ4_XS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-1B-CEH_v10-GGUF/resolve/main/llama-3.2-1B-CEH_v10.Q4_K_S.gguf) | Q4_K_S | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-1B-CEH_v10-GGUF/resolve/main/llama-3.2-1B-CEH_v10.Q4_K_M.gguf) | Q4_K_M | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-1B-CEH_v10-GGUF/resolve/main/llama-3.2-1B-CEH_v10.Q5_K_S.gguf) | Q5_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-1B-CEH_v10-GGUF/resolve/main/llama-3.2-1B-CEH_v10.Q5_K_M.gguf) | Q5_K_M | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-1B-CEH_v10-GGUF/resolve/main/llama-3.2-1B-CEH_v10.Q6_K.gguf) | Q6_K | 1.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-1B-CEH_v10-GGUF/resolve/main/llama-3.2-1B-CEH_v10.Q8_0.gguf) | Q8_0 | 1.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-1B-CEH_v10-GGUF/resolve/main/llama-3.2-1B-CEH_v10.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. + + diff --git a/llama-3.2-1B-CEH_v10.IQ4_XS.gguf b/llama-3.2-1B-CEH_v10.IQ4_XS.gguf new file mode 100644 index 0000000..c7aa08c --- /dev/null +++ b/llama-3.2-1B-CEH_v10.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0bcc6d4fadb86ec8fe86b388eb65f047dffb7d1d862111e2f158337d356ed49 +size 748380480 diff --git a/llama-3.2-1B-CEH_v10.Q2_K.gguf b/llama-3.2-1B-CEH_v10.Q2_K.gguf new file mode 100644 index 0000000..10141bb --- /dev/null +++ b/llama-3.2-1B-CEH_v10.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:406a015c7447cc707e62e3429725b87734749c28c30b709cbd4f2c503ed73ed3 +size 580870464 diff --git a/llama-3.2-1B-CEH_v10.Q3_K_L.gguf b/llama-3.2-1B-CEH_v10.Q3_K_L.gguf new file mode 100644 index 0000000..b241a49 --- /dev/null +++ b/llama-3.2-1B-CEH_v10.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2fca8272edac0b7c88d46f4645a1922bfaf7d505c051e37da8194d6d677e68c1 +size 732520768 diff --git a/llama-3.2-1B-CEH_v10.Q3_K_M.gguf b/llama-3.2-1B-CEH_v10.Q3_K_M.gguf new file mode 100644 index 0000000..e6c04ca --- /dev/null +++ b/llama-3.2-1B-CEH_v10.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf29354d99d0e50b8826390712caea2a5f97c997171440cd284571c41c9f7f66 +size 690839872 diff --git a/llama-3.2-1B-CEH_v10.Q3_K_S.gguf b/llama-3.2-1B-CEH_v10.Q3_K_S.gguf new file mode 100644 index 0000000..bcad49c --- /dev/null +++ b/llama-3.2-1B-CEH_v10.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:541e8f0b71495f8142aa80793166c9a08f16f419068397d8d1c8dd0c07ddc4df +size 641687872 diff --git a/llama-3.2-1B-CEH_v10.Q4_K_M.gguf b/llama-3.2-1B-CEH_v10.Q4_K_M.gguf new file mode 100644 index 0000000..b3c5d7f --- /dev/null +++ b/llama-3.2-1B-CEH_v10.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a620d211d158acde5026143528a987df9e2cf4186f2d954c895bf3f7c0025db4 +size 807690560 diff --git a/llama-3.2-1B-CEH_v10.Q4_K_S.gguf b/llama-3.2-1B-CEH_v10.Q4_K_S.gguf new file mode 100644 index 0000000..c26ec59 --- /dev/null +++ b/llama-3.2-1B-CEH_v10.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23d9a52f64f73fc589ab0382c54dbcfd99f4839de6c6611bdc0a1a88b53f835e +size 775643456 diff --git a/llama-3.2-1B-CEH_v10.Q5_K_M.gguf b/llama-3.2-1B-CEH_v10.Q5_K_M.gguf new file mode 100644 index 0000000..fd4e679 --- /dev/null +++ b/llama-3.2-1B-CEH_v10.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c08e87fb2e7570a0db8b518900dc803e2a8e326248406c4c6e309f8f409b3c33 +size 911499584 diff --git a/llama-3.2-1B-CEH_v10.Q5_K_S.gguf b/llama-3.2-1B-CEH_v10.Q5_K_S.gguf new file mode 100644 index 0000000..85cd75d --- /dev/null +++ b/llama-3.2-1B-CEH_v10.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ace27e5ff7a1154df411aef88cbe5b4da70c0a6edef1c82ebe8b9f46bbd66cdc +size 892559680 diff --git a/llama-3.2-1B-CEH_v10.Q6_K.gguf b/llama-3.2-1B-CEH_v10.Q6_K.gguf new file mode 100644 index 0000000..be14621 --- /dev/null +++ b/llama-3.2-1B-CEH_v10.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94bc4d1ec798e3ca2b11aafea4a8fa55589680d62e93b3912c7d0b0b22b767ed +size 1021796672 diff --git a/llama-3.2-1B-CEH_v10.Q8_0.gguf b/llama-3.2-1B-CEH_v10.Q8_0.gguf new file mode 100644 index 0000000..ab8d766 --- /dev/null +++ b/llama-3.2-1B-CEH_v10.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25f3d9c37c0adcc1011721e392f70dea9d23f381f7115fc5fd19ded2ebfe2c61 +size 1321079104 diff --git a/llama-3.2-1B-CEH_v10.f16.gguf b/llama-3.2-1B-CEH_v10.f16.gguf new file mode 100644 index 0000000..7e4578f --- /dev/null +++ b/llama-3.2-1B-CEH_v10.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ee065dfab77e8d879d4245fb472dbeb0e4b2bb1a54634fb72b969db36af8a26 +size 2479591744