commit caae668d2c2dcb82be206df0ad25dfb5147e03c4 Author: ModelHub XC Date: Thu Apr 23 14:50:01 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Flowable-Docs-Llama-3.2-3B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..15d2c24 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,48 @@ +*.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 +Flowable-Docs-Llama-3.2-3B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Flowable-Docs-Llama-3.2-3B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Flowable-Docs-Llama-3.2-3B.f16.gguf filter=lfs diff=lfs merge=lfs -text +Flowable-Docs-Llama-3.2-3B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Flowable-Docs-Llama-3.2-3B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Flowable-Docs-Llama-3.2-3B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Flowable-Docs-Llama-3.2-3B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Flowable-Docs-Llama-3.2-3B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Flowable-Docs-Llama-3.2-3B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Flowable-Docs-Llama-3.2-3B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Flowable-Docs-Llama-3.2-3B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Flowable-Docs-Llama-3.2-3B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Flowable-Docs-Llama-3.2-3B.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Flowable-Docs-Llama-3.2-3B.IQ4_XS.gguf b/Flowable-Docs-Llama-3.2-3B.IQ4_XS.gguf new file mode 100644 index 0000000..8378f80 --- /dev/null +++ b/Flowable-Docs-Llama-3.2-3B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5311bd16884c5d300c2936e1dbea2bc604815353637e4902be1dd50218358017 +size 1840906784 diff --git a/Flowable-Docs-Llama-3.2-3B.Q2_K.gguf b/Flowable-Docs-Llama-3.2-3B.Q2_K.gguf new file mode 100644 index 0000000..63088c9 --- /dev/null +++ b/Flowable-Docs-Llama-3.2-3B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc5692ef7e46697c0fbd9221b8765a4c6ef2cb06afbde4e4fe84d08e1e4e9965 +size 1363935776 diff --git a/Flowable-Docs-Llama-3.2-3B.Q3_K_L.gguf b/Flowable-Docs-Llama-3.2-3B.Q3_K_L.gguf new file mode 100644 index 0000000..308eff9 --- /dev/null +++ b/Flowable-Docs-Llama-3.2-3B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b80ba4b5903942a3b945496df673e5421fc8873436d9fe1c39b180860dd5d1c4 +size 1815347744 diff --git a/Flowable-Docs-Llama-3.2-3B.Q3_K_M.gguf b/Flowable-Docs-Llama-3.2-3B.Q3_K_M.gguf new file mode 100644 index 0000000..4703016 --- /dev/null +++ b/Flowable-Docs-Llama-3.2-3B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41691f93803416ca4cf94f9a7ba2f85fa3f8dfa2a2e3fc86fe3889514e728ace +size 1687159328 diff --git a/Flowable-Docs-Llama-3.2-3B.Q3_K_S.gguf b/Flowable-Docs-Llama-3.2-3B.Q3_K_S.gguf new file mode 100644 index 0000000..4ca1702 --- /dev/null +++ b/Flowable-Docs-Llama-3.2-3B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cce63c95b06d1f0c090092bf9fbd471d0fcb7ece9ee4ac83fb3a8d2852894702 +size 1542849056 diff --git a/Flowable-Docs-Llama-3.2-3B.Q4_0_4_4.gguf b/Flowable-Docs-Llama-3.2-3B.Q4_0_4_4.gguf new file mode 100644 index 0000000..3452154 --- /dev/null +++ b/Flowable-Docs-Llama-3.2-3B.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef0e230cdaaa0c1ef3223cb3b1357727f8a5c7c351059f47bb8271bbdbfef758 +size 1917190688 diff --git a/Flowable-Docs-Llama-3.2-3B.Q4_K_M.gguf b/Flowable-Docs-Llama-3.2-3B.Q4_K_M.gguf new file mode 100644 index 0000000..95de5ee --- /dev/null +++ b/Flowable-Docs-Llama-3.2-3B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95e943aa963eb175c62bf817200554917247298c62517f5c289709350fe33353 +size 2019377696 diff --git a/Flowable-Docs-Llama-3.2-3B.Q4_K_S.gguf b/Flowable-Docs-Llama-3.2-3B.Q4_K_S.gguf new file mode 100644 index 0000000..1b15143 --- /dev/null +++ b/Flowable-Docs-Llama-3.2-3B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8daf742b3da5734335f5f9aefd7979bcad0bee79b20cf07f30b77981b8a0d503 +size 1928200736 diff --git a/Flowable-Docs-Llama-3.2-3B.Q5_K_M.gguf b/Flowable-Docs-Llama-3.2-3B.Q5_K_M.gguf new file mode 100644 index 0000000..c55b285 --- /dev/null +++ b/Flowable-Docs-Llama-3.2-3B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ecfc9f89c46e8786f69b5f1bd94fb0c8f3290d4c5e4fada53bef2bcd24fff7f +size 2322154016 diff --git a/Flowable-Docs-Llama-3.2-3B.Q5_K_S.gguf b/Flowable-Docs-Llama-3.2-3B.Q5_K_S.gguf new file mode 100644 index 0000000..3fd7815 --- /dev/null +++ b/Flowable-Docs-Llama-3.2-3B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96fbf5b7ccb2540459c68a7bab91dbede490cc8cc00508747b6025c2029ee475 +size 2269512224 diff --git a/Flowable-Docs-Llama-3.2-3B.Q6_K.gguf b/Flowable-Docs-Llama-3.2-3B.Q6_K.gguf new file mode 100644 index 0000000..18c64ba --- /dev/null +++ b/Flowable-Docs-Llama-3.2-3B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a17bf8755c4c490d25bdd1a62a3f672303c1582cfc995bae9a0e1d9b1c9e2ba +size 2643853856 diff --git a/Flowable-Docs-Llama-3.2-3B.Q8_0.gguf b/Flowable-Docs-Llama-3.2-3B.Q8_0.gguf new file mode 100644 index 0000000..b7f01f4 --- /dev/null +++ b/Flowable-Docs-Llama-3.2-3B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b955566e75ac5893e2ac266ad13ee6cd6622b1d9dfc110955e5580f21cb3f17 +size 3421899296 diff --git a/Flowable-Docs-Llama-3.2-3B.f16.gguf b/Flowable-Docs-Llama-3.2-3B.f16.gguf new file mode 100644 index 0000000..8a5823d --- /dev/null +++ b/Flowable-Docs-Llama-3.2-3B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a6c61f43ed4f636a6366d4f955e6428cb9047d428b30c5fc82291516460e088 +size 6433688096 diff --git a/README.md b/README.md new file mode 100644 index 0000000..4b2fe81 --- /dev/null +++ b/README.md @@ -0,0 +1,65 @@ +--- +base_model: zzzmahesh/Flowable-Docs-Llama-3.2-3B +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/zzzmahesh/Flowable-Docs-Llama-3.2-3B + + +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/Flowable-Docs-Llama-3.2-3B-GGUF/resolve/main/Flowable-Docs-Llama-3.2-3B.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Flowable-Docs-Llama-3.2-3B-GGUF/resolve/main/Flowable-Docs-Llama-3.2-3B.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Flowable-Docs-Llama-3.2-3B-GGUF/resolve/main/Flowable-Docs-Llama-3.2-3B.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Flowable-Docs-Llama-3.2-3B-GGUF/resolve/main/Flowable-Docs-Llama-3.2-3B.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Flowable-Docs-Llama-3.2-3B-GGUF/resolve/main/Flowable-Docs-Llama-3.2-3B.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Flowable-Docs-Llama-3.2-3B-GGUF/resolve/main/Flowable-Docs-Llama-3.2-3B.Q4_0_4_4.gguf) | Q4_0_4_4 | 2.0 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Flowable-Docs-Llama-3.2-3B-GGUF/resolve/main/Flowable-Docs-Llama-3.2-3B.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Flowable-Docs-Llama-3.2-3B-GGUF/resolve/main/Flowable-Docs-Llama-3.2-3B.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Flowable-Docs-Llama-3.2-3B-GGUF/resolve/main/Flowable-Docs-Llama-3.2-3B.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Flowable-Docs-Llama-3.2-3B-GGUF/resolve/main/Flowable-Docs-Llama-3.2-3B.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Flowable-Docs-Llama-3.2-3B-GGUF/resolve/main/Flowable-Docs-Llama-3.2-3B.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Flowable-Docs-Llama-3.2-3B-GGUF/resolve/main/Flowable-Docs-Llama-3.2-3B.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Flowable-Docs-Llama-3.2-3B-GGUF/resolve/main/Flowable-Docs-Llama-3.2-3B.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. + +