commit d53d3e482c351cc302ac1d20bb04214c1b1635a5 Author: ModelHub XC Date: Mon Jun 15 06:10:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/llama3.2-entity-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..59a3696 --- /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 +llama3.2-entity.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +llama3.2-entity.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama3.2-entity.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama3.2-entity.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3.2-entity.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3.2-entity.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3.2-entity.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3.2-entity.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3.2-entity.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3.2-entity.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama3.2-entity.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llama3.2-entity.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..0ea4581 --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: shadicopty/llama3.2-entity +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/shadicopty/llama3.2-entity + + +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/llama3.2-entity-GGUF/resolve/main/llama3.2-entity.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.2-entity-GGUF/resolve/main/llama3.2-entity.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.2-entity-GGUF/resolve/main/llama3.2-entity.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama3.2-entity-GGUF/resolve/main/llama3.2-entity.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.2-entity-GGUF/resolve/main/llama3.2-entity.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.2-entity-GGUF/resolve/main/llama3.2-entity.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama3.2-entity-GGUF/resolve/main/llama3.2-entity.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama3.2-entity-GGUF/resolve/main/llama3.2-entity.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.2-entity-GGUF/resolve/main/llama3.2-entity.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.2-entity-GGUF/resolve/main/llama3.2-entity.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/llama3.2-entity-GGUF/resolve/main/llama3.2-entity.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/llama3.2-entity-GGUF/resolve/main/llama3.2-entity.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/llama3.2-entity.IQ4_XS.gguf b/llama3.2-entity.IQ4_XS.gguf new file mode 100644 index 0000000..0773cd6 --- /dev/null +++ b/llama3.2-entity.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2380ba39ed138469d6112e9421fb8a498c33f44854b7930c1e7e40c3225809eb +size 1840907552 diff --git a/llama3.2-entity.Q2_K.gguf b/llama3.2-entity.Q2_K.gguf new file mode 100644 index 0000000..642e92b --- /dev/null +++ b/llama3.2-entity.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:241aea480ad1bd19ee568596563085030dd5cb2828233ac04a43a984a89e224e +size 1363936544 diff --git a/llama3.2-entity.Q3_K_L.gguf b/llama3.2-entity.Q3_K_L.gguf new file mode 100644 index 0000000..a76991a --- /dev/null +++ b/llama3.2-entity.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8aabd51ba578998246c72ffce9e3c03cd0c51d6c2e3fee07ce4018ff8c2f9f49 +size 1815348512 diff --git a/llama3.2-entity.Q3_K_M.gguf b/llama3.2-entity.Q3_K_M.gguf new file mode 100644 index 0000000..02e4b9f --- /dev/null +++ b/llama3.2-entity.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69cb7980dc8d9322fc4eb7963c0c1f56fe63b96975403c4e0a2fef8edf42bb9e +size 1687160096 diff --git a/llama3.2-entity.Q3_K_S.gguf b/llama3.2-entity.Q3_K_S.gguf new file mode 100644 index 0000000..38ef85b --- /dev/null +++ b/llama3.2-entity.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eec367d9ecf4edbb5b0212c2e26b32fb75e2e3647a85a3d7a2c4c3021e35e686 +size 1542849824 diff --git a/llama3.2-entity.Q4_K_M.gguf b/llama3.2-entity.Q4_K_M.gguf new file mode 100644 index 0000000..9028687 --- /dev/null +++ b/llama3.2-entity.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:414152d6e446f0ebcbfaefc98abf281885ebc20a0025d8d962f6ae3cac650c6f +size 2019378464 diff --git a/llama3.2-entity.Q4_K_S.gguf b/llama3.2-entity.Q4_K_S.gguf new file mode 100644 index 0000000..3ef0d83 --- /dev/null +++ b/llama3.2-entity.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0062cb9d645e1020c60286d169263389ea68197123d6a1e9372b72a05ced3c4f +size 1928201504 diff --git a/llama3.2-entity.Q5_K_M.gguf b/llama3.2-entity.Q5_K_M.gguf new file mode 100644 index 0000000..dd29e00 --- /dev/null +++ b/llama3.2-entity.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09989f975d2b95ed6a22d9774fbfbb018cf28fa171ed3be2de3d248f68ccb34d +size 2322154784 diff --git a/llama3.2-entity.Q5_K_S.gguf b/llama3.2-entity.Q5_K_S.gguf new file mode 100644 index 0000000..f28a804 --- /dev/null +++ b/llama3.2-entity.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b1f487e17048196cde3b6878abe9490e6011aa9ec2928917ca164e98a7105a9 +size 2269512992 diff --git a/llama3.2-entity.Q6_K.gguf b/llama3.2-entity.Q6_K.gguf new file mode 100644 index 0000000..5d8c423 --- /dev/null +++ b/llama3.2-entity.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:390cfccd42f4614d103d986e5f39adb9d0663c7d90823aa7e0d29a557443f74c +size 2643854624 diff --git a/llama3.2-entity.Q8_0.gguf b/llama3.2-entity.Q8_0.gguf new file mode 100644 index 0000000..a7acf77 --- /dev/null +++ b/llama3.2-entity.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79933a6cbaf6d9a93186c68724080927484ebefcf81baf114ea87d7e6672b775 +size 3421900064 diff --git a/llama3.2-entity.f16.gguf b/llama3.2-entity.f16.gguf new file mode 100644 index 0000000..0264d0e --- /dev/null +++ b/llama3.2-entity.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:abcea3743e40a8f187a4b95a8a1714ad33e05ab44fd09148c7dd6c84bc1b14f6 +size 6433688864