commit c3838896f7be4c739538bbf0244d70ab873d9873 Author: ModelHub XC Date: Sun Jun 14 03:08:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/llama-3.2-1b-extremist4-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..66de39f --- /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-extremist4.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-1b-extremist4.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-1b-extremist4.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-1b-extremist4.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-1b-extremist4.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-1b-extremist4.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-1b-extremist4.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-1b-extremist4.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-1b-extremist4.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-1b-extremist4.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-1b-extremist4.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-1b-extremist4.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..b8df3bf --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: danieliuspodb/llama-3.2-1b-extremist4 +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/danieliuspodb/llama-3.2-1b-extremist4 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#llama-3.2-1b-extremist4-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/llama-3.2-1b-extremist4-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/llama-3.2-1b-extremist4-GGUF/resolve/main/llama-3.2-1b-extremist4.Q2_K.gguf) | Q2_K | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-1b-extremist4-GGUF/resolve/main/llama-3.2-1b-extremist4.Q3_K_S.gguf) | Q3_K_S | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-1b-extremist4-GGUF/resolve/main/llama-3.2-1b-extremist4.Q3_K_M.gguf) | Q3_K_M | 0.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-1b-extremist4-GGUF/resolve/main/llama-3.2-1b-extremist4.Q3_K_L.gguf) | Q3_K_L | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-1b-extremist4-GGUF/resolve/main/llama-3.2-1b-extremist4.IQ4_XS.gguf) | IQ4_XS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-1b-extremist4-GGUF/resolve/main/llama-3.2-1b-extremist4.Q4_K_S.gguf) | Q4_K_S | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-1b-extremist4-GGUF/resolve/main/llama-3.2-1b-extremist4.Q4_K_M.gguf) | Q4_K_M | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-1b-extremist4-GGUF/resolve/main/llama-3.2-1b-extremist4.Q5_K_S.gguf) | Q5_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-1b-extremist4-GGUF/resolve/main/llama-3.2-1b-extremist4.Q5_K_M.gguf) | Q5_K_M | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-1b-extremist4-GGUF/resolve/main/llama-3.2-1b-extremist4.Q6_K.gguf) | Q6_K | 1.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-1b-extremist4-GGUF/resolve/main/llama-3.2-1b-extremist4.Q8_0.gguf) | Q8_0 | 1.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-1b-extremist4-GGUF/resolve/main/llama-3.2-1b-extremist4.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-extremist4.IQ4_XS.gguf b/llama-3.2-1b-extremist4.IQ4_XS.gguf new file mode 100644 index 0000000..1f61eb3 --- /dev/null +++ b/llama-3.2-1b-extremist4.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18aa42a2abfab53d0946dadd9655246b456ff5e8e8ceac15a538b908ab3f3875 +size 748384096 diff --git a/llama-3.2-1b-extremist4.Q2_K.gguf b/llama-3.2-1b-extremist4.Q2_K.gguf new file mode 100644 index 0000000..74b9335 --- /dev/null +++ b/llama-3.2-1b-extremist4.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34f60e1b7e79dc24ca02b2cf44f612fa5b716f62040643042904840f289474a1 +size 580874080 diff --git a/llama-3.2-1b-extremist4.Q3_K_L.gguf b/llama-3.2-1b-extremist4.Q3_K_L.gguf new file mode 100644 index 0000000..826eb22 --- /dev/null +++ b/llama-3.2-1b-extremist4.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:497573bc94e3bb4294088334af5be07433d9f674e183bcd0e96c3a5f402b1a96 +size 732524384 diff --git a/llama-3.2-1b-extremist4.Q3_K_M.gguf b/llama-3.2-1b-extremist4.Q3_K_M.gguf new file mode 100644 index 0000000..442aed6 --- /dev/null +++ b/llama-3.2-1b-extremist4.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a32cfadb67fc21f132012b65fcfaa2256c477265dcc4caafec5c91b3653c7b7f +size 690843488 diff --git a/llama-3.2-1b-extremist4.Q3_K_S.gguf b/llama-3.2-1b-extremist4.Q3_K_S.gguf new file mode 100644 index 0000000..9bf799b --- /dev/null +++ b/llama-3.2-1b-extremist4.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ffab0057ec53aab987b09bf68a93625a38a1e059ad6f77272178f9578e61ea8 +size 641691488 diff --git a/llama-3.2-1b-extremist4.Q4_K_M.gguf b/llama-3.2-1b-extremist4.Q4_K_M.gguf new file mode 100644 index 0000000..46e8d39 --- /dev/null +++ b/llama-3.2-1b-extremist4.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb3e434e3377dff10f64c9daa7f96419e35a9b2eeb89f3c5a39ebc2d86af545e +size 807694176 diff --git a/llama-3.2-1b-extremist4.Q4_K_S.gguf b/llama-3.2-1b-extremist4.Q4_K_S.gguf new file mode 100644 index 0000000..7a2d303 --- /dev/null +++ b/llama-3.2-1b-extremist4.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5355947a6e57012a00479fa83f9e6ebc423ba71ee9f8475172b3b947c3f4412 +size 775647072 diff --git a/llama-3.2-1b-extremist4.Q5_K_M.gguf b/llama-3.2-1b-extremist4.Q5_K_M.gguf new file mode 100644 index 0000000..2d10ae8 --- /dev/null +++ b/llama-3.2-1b-extremist4.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85a270d9b8a946c5bc45c3f9461ec9f17bbeeac80acceca1f9bc8c0df5ca07ae +size 911503200 diff --git a/llama-3.2-1b-extremist4.Q5_K_S.gguf b/llama-3.2-1b-extremist4.Q5_K_S.gguf new file mode 100644 index 0000000..42742cb --- /dev/null +++ b/llama-3.2-1b-extremist4.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f378440970d5fa693b573502d5c4b5286081419a8ceae70cb09e7c089f0e0357 +size 892563296 diff --git a/llama-3.2-1b-extremist4.Q6_K.gguf b/llama-3.2-1b-extremist4.Q6_K.gguf new file mode 100644 index 0000000..772852e --- /dev/null +++ b/llama-3.2-1b-extremist4.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e100f176a9dbb82a834a302b72921587800a43a10e172112766000b7b3170b4f +size 1021800288 diff --git a/llama-3.2-1b-extremist4.Q8_0.gguf b/llama-3.2-1b-extremist4.Q8_0.gguf new file mode 100644 index 0000000..a22a193 --- /dev/null +++ b/llama-3.2-1b-extremist4.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c02a2bd7d800cae16a3a63d0f3cdbbe643bcb5ae9f38ab6d7413b8d01e7c8a7c +size 1321083712 diff --git a/llama-3.2-1b-extremist4.f16.gguf b/llama-3.2-1b-extremist4.f16.gguf new file mode 100644 index 0000000..2b4a0ee --- /dev/null +++ b/llama-3.2-1b-extremist4.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef6f333a10b7ce9919323f46f1fe115569780c4d2bea227fb5d8e0bb9978420b +size 2479600192