commit 5e4d65a596e0bc44f6f5b5aea9e21a1ef8bbf76a Author: ModelHub XC Date: Sat Aug 8 11:59:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama3.2-CULO-1B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..52eee90 --- /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-CULO-1B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-CULO-1B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-CULO-1B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-CULO-1B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-CULO-1B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-CULO-1B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-CULO-1B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-CULO-1B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-CULO-1B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-CULO-1B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-CULO-1B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-CULO-1B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama3.2-CULO-1B.IQ4_XS.gguf b/Llama3.2-CULO-1B.IQ4_XS.gguf new file mode 100644 index 0000000..3a647b9 --- /dev/null +++ b/Llama3.2-CULO-1B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89503ef9738a3d833ebdc79005b198a59667e7e05eaa6faa9b819886f4a40594 +size 887924032 diff --git a/Llama3.2-CULO-1B.Q2_K.gguf b/Llama3.2-CULO-1B.Q2_K.gguf new file mode 100644 index 0000000..752e43f --- /dev/null +++ b/Llama3.2-CULO-1B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46d70052f891ce5c0fc97c881e4c1e36a30c28cd241d73ffc6785770d6063718 +size 667059520 diff --git a/Llama3.2-CULO-1B.Q3_K_L.gguf b/Llama3.2-CULO-1B.Q3_K_L.gguf new file mode 100644 index 0000000..d69e1e3 --- /dev/null +++ b/Llama3.2-CULO-1B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5aad6bd4829318b0043e5815c0d559311295d0ea4e2c7da95be11ed666feaa4 +size 845387072 diff --git a/Llama3.2-CULO-1B.Q3_K_M.gguf b/Llama3.2-CULO-1B.Q3_K_M.gguf new file mode 100644 index 0000000..9b871f6 --- /dev/null +++ b/Llama3.2-CULO-1B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b697348fed68103374ab63c068dc0f51d8184d54900030796d6e57d88238cfd +size 803706176 diff --git a/Llama3.2-CULO-1B.Q3_K_S.gguf b/Llama3.2-CULO-1B.Q3_K_S.gguf new file mode 100644 index 0000000..953b60b --- /dev/null +++ b/Llama3.2-CULO-1B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:902cab6f7f4cc55474fed1589ad3fbd6a78e3d079422a72a24112cd48709dabc +size 754554176 diff --git a/Llama3.2-CULO-1B.Q4_K_M.gguf b/Llama3.2-CULO-1B.Q4_K_M.gguf new file mode 100644 index 0000000..55a6190 --- /dev/null +++ b/Llama3.2-CULO-1B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d0201d32efe17d5fb7669a7bfdbaf27ba83e23d2122f7326fedc7af97f59a79 +size 955442496 diff --git a/Llama3.2-CULO-1B.Q4_K_S.gguf b/Llama3.2-CULO-1B.Q4_K_S.gguf new file mode 100644 index 0000000..659b406 --- /dev/null +++ b/Llama3.2-CULO-1B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:63d334c84fc37608e278e1d32c82ebd5f9ff15eee41ac6c424ff2bdd28b648f2 +size 923395392 diff --git a/Llama3.2-CULO-1B.Q5_K_M.gguf b/Llama3.2-CULO-1B.Q5_K_M.gguf new file mode 100644 index 0000000..7bdecdf --- /dev/null +++ b/Llama3.2-CULO-1B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4dfe0d13bdf0adf3d46dc560176ed885aabbb1a2160acbe70b13cc11c8d32d4 +size 1092085056 diff --git a/Llama3.2-CULO-1B.Q5_K_S.gguf b/Llama3.2-CULO-1B.Q5_K_S.gguf new file mode 100644 index 0000000..26c9f6c --- /dev/null +++ b/Llama3.2-CULO-1B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb0c06372128d9ee8e90d2e563e76c88b01aff732c7ce4a95d8266c1c2fb0fcd +size 1073145152 diff --git a/Llama3.2-CULO-1B.Q6_K.gguf b/Llama3.2-CULO-1B.Q6_K.gguf new file mode 100644 index 0000000..515c537 --- /dev/null +++ b/Llama3.2-CULO-1B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89a2b670c938942cdc919141bad58b5345697503122482edc7c8233006d9b463 +size 1237267776 diff --git a/Llama3.2-CULO-1B.Q8_0.gguf b/Llama3.2-CULO-1B.Q8_0.gguf new file mode 100644 index 0000000..607c2ac --- /dev/null +++ b/Llama3.2-CULO-1B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ae51ef2b8ff073c234291e344c2bf60362463a9d43ddaef1b5a903cb085eab1 +size 1600165184 diff --git a/Llama3.2-CULO-1B.f16.gguf b/Llama3.2-CULO-1B.f16.gguf new file mode 100644 index 0000000..4e2923b --- /dev/null +++ b/Llama3.2-CULO-1B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a96e65a25326b225c98536ec5864529c060d2fcb8bb942bb749847eff976d9b +size 3004929344 diff --git a/README.md b/README.md new file mode 100644 index 0000000..b24138f --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: NovaCorp/CULO-MoE +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- CULO +--- +## About + + + + + + + + + +static quants of https://huggingface.co/NovaCorp/CULO-MoE + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama3.2-CULO-1B-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama3.2-CULO-1B-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/Llama3.2-CULO-1B-GGUF/resolve/main/Llama3.2-CULO-1B.Q2_K.gguf) | Q2_K | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-CULO-1B-GGUF/resolve/main/Llama3.2-CULO-1B.Q3_K_S.gguf) | Q3_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-CULO-1B-GGUF/resolve/main/Llama3.2-CULO-1B.Q3_K_M.gguf) | Q3_K_M | 0.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-CULO-1B-GGUF/resolve/main/Llama3.2-CULO-1B.Q3_K_L.gguf) | Q3_K_L | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-CULO-1B-GGUF/resolve/main/Llama3.2-CULO-1B.IQ4_XS.gguf) | IQ4_XS | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-CULO-1B-GGUF/resolve/main/Llama3.2-CULO-1B.Q4_K_S.gguf) | Q4_K_S | 1.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-CULO-1B-GGUF/resolve/main/Llama3.2-CULO-1B.Q4_K_M.gguf) | Q4_K_M | 1.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-CULO-1B-GGUF/resolve/main/Llama3.2-CULO-1B.Q5_K_S.gguf) | Q5_K_S | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-CULO-1B-GGUF/resolve/main/Llama3.2-CULO-1B.Q5_K_M.gguf) | Q5_K_M | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-CULO-1B-GGUF/resolve/main/Llama3.2-CULO-1B.Q6_K.gguf) | Q6_K | 1.3 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-CULO-1B-GGUF/resolve/main/Llama3.2-CULO-1B.Q8_0.gguf) | Q8_0 | 1.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-CULO-1B-GGUF/resolve/main/Llama3.2-CULO-1B.f16.gguf) | f16 | 3.1 | 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. + +