commit 1e1a235966cd95f9dd464f484f0b1d9e8d3f842d Author: ModelHub XC Date: Tue Sep 15 16:36:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Flowable-Docs-Llama-3.2-1B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..de9a4ea --- /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-3.2-1B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Flowable-Docs-Llama-3.2-1B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Flowable-Docs-Llama-3.2-1B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Flowable-Docs-Llama-3.2-1B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Flowable-Docs-Llama-3.2-1B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Flowable-Docs-Llama-3.2-1B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Flowable-Docs-Llama-3.2-1B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Flowable-Docs-Llama-3.2-1B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Flowable-Docs-Llama-3.2-1B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Flowable-Docs-Llama-3.2-1B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Flowable-Docs-Llama-3.2-1B.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text +Flowable-Docs-Llama-3.2-1B.f16.gguf filter=lfs diff=lfs merge=lfs -text +Flowable-Docs-Llama-3.2-1B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Flowable-Docs-Llama-3.2-1B.IQ4_XS.gguf b/Flowable-Docs-Llama-3.2-1B.IQ4_XS.gguf new file mode 100644 index 0000000..b98ce4c --- /dev/null +++ b/Flowable-Docs-Llama-3.2-1B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f3d0f51a0c3c04116cd651a4fba56aa4a58c4578d0ab256ce572cc3bb96b672 +size 748384352 diff --git a/Flowable-Docs-Llama-3.2-1B.Q2_K.gguf b/Flowable-Docs-Llama-3.2-1B.Q2_K.gguf new file mode 100644 index 0000000..1a8e236 --- /dev/null +++ b/Flowable-Docs-Llama-3.2-1B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d1e8dd0b7e3dc44af1758c69439298084a7f5912f654027ec6005fcea1503f5 +size 580874336 diff --git a/Flowable-Docs-Llama-3.2-1B.Q3_K_L.gguf b/Flowable-Docs-Llama-3.2-1B.Q3_K_L.gguf new file mode 100644 index 0000000..5e42ae7 --- /dev/null +++ b/Flowable-Docs-Llama-3.2-1B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db37af9370d2e4f4ee7a9eb4d597c80ed0d0108606bf71b0f972fa268b236a73 +size 732524640 diff --git a/Flowable-Docs-Llama-3.2-1B.Q3_K_M.gguf b/Flowable-Docs-Llama-3.2-1B.Q3_K_M.gguf new file mode 100644 index 0000000..3d314c3 --- /dev/null +++ b/Flowable-Docs-Llama-3.2-1B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:737e4dcf11b22ab20efc491ed3c5fd1ca261f5cbb8eb02502f5fd700e1cf5c58 +size 690843744 diff --git a/Flowable-Docs-Llama-3.2-1B.Q3_K_S.gguf b/Flowable-Docs-Llama-3.2-1B.Q3_K_S.gguf new file mode 100644 index 0000000..1cb604d --- /dev/null +++ b/Flowable-Docs-Llama-3.2-1B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5b327fbaec9013fb80319f007c1107bbecab89b3c0cebd359aff73da1a6213e +size 641691744 diff --git a/Flowable-Docs-Llama-3.2-1B.Q4_0_4_4.gguf b/Flowable-Docs-Llama-3.2-1B.Q4_0_4_4.gguf new file mode 100644 index 0000000..949d18f --- /dev/null +++ b/Flowable-Docs-Llama-3.2-1B.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7be6963ed812a64bdae24cf3f799525e51197c3a51ea5f521d7a8ad402f1cd94 +size 770928736 diff --git a/Flowable-Docs-Llama-3.2-1B.Q4_K_M.gguf b/Flowable-Docs-Llama-3.2-1B.Q4_K_M.gguf new file mode 100644 index 0000000..cf73f0a --- /dev/null +++ b/Flowable-Docs-Llama-3.2-1B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de3b1b2b190384213956610167a3d4c2605eb4abdc9d528b9cd1f19f5d984bcc +size 807694432 diff --git a/Flowable-Docs-Llama-3.2-1B.Q4_K_S.gguf b/Flowable-Docs-Llama-3.2-1B.Q4_K_S.gguf new file mode 100644 index 0000000..bb7fff7 --- /dev/null +++ b/Flowable-Docs-Llama-3.2-1B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dbf3a34779f20e5393c749f720d7be0d625c1909d52b52ab1594d52c7f0976c4 +size 775647328 diff --git a/Flowable-Docs-Llama-3.2-1B.Q5_K_M.gguf b/Flowable-Docs-Llama-3.2-1B.Q5_K_M.gguf new file mode 100644 index 0000000..56b0143 --- /dev/null +++ b/Flowable-Docs-Llama-3.2-1B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54d638c3f94df9d807569c8bae08d791b373778a8c33f4ed1e9a698bfa49d64e +size 911503456 diff --git a/Flowable-Docs-Llama-3.2-1B.Q5_K_S.gguf b/Flowable-Docs-Llama-3.2-1B.Q5_K_S.gguf new file mode 100644 index 0000000..a72f887 --- /dev/null +++ b/Flowable-Docs-Llama-3.2-1B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bdabdd695a5946f62b172892237ea47e11cf0cc3fd854c6de3cd37f64f5805f1 +size 892563552 diff --git a/Flowable-Docs-Llama-3.2-1B.Q6_K.gguf b/Flowable-Docs-Llama-3.2-1B.Q6_K.gguf new file mode 100644 index 0000000..00c9872 --- /dev/null +++ b/Flowable-Docs-Llama-3.2-1B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3008e6c1d8622eca26ba69ca3f44a2c868e6cf04604c9ed07ef206d9cb221d32 +size 1021800544 diff --git a/Flowable-Docs-Llama-3.2-1B.Q8_0.gguf b/Flowable-Docs-Llama-3.2-1B.Q8_0.gguf new file mode 100644 index 0000000..e3cab31 --- /dev/null +++ b/Flowable-Docs-Llama-3.2-1B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e85d3fef3b38f5de6e12d2ef20bdae9e8d76677e93fc6d8cd0d31726931f6035 +size 1321082976 diff --git a/Flowable-Docs-Llama-3.2-1B.f16.gguf b/Flowable-Docs-Llama-3.2-1B.f16.gguf new file mode 100644 index 0000000..1791e21 --- /dev/null +++ b/Flowable-Docs-Llama-3.2-1B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ee7faee9601acf05f0fe6e579be8ab3a3a0b486484642f1af67b9a857cfd637 +size 2479595616 diff --git a/README.md b/README.md new file mode 100644 index 0000000..810fe2a --- /dev/null +++ b/README.md @@ -0,0 +1,65 @@ +--- +base_model: zzzmahesh/Flowable-Docs-Llama-3.2-1B +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/zzzmahesh/Flowable-Docs-Llama-3.2-1B + + +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-3.2-1B-GGUF/resolve/main/Flowable-Docs-Llama-3.2-1B.Q2_K.gguf) | Q2_K | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Flowable-Docs-Llama-3.2-1B-GGUF/resolve/main/Flowable-Docs-Llama-3.2-1B.Q3_K_S.gguf) | Q3_K_S | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Flowable-Docs-Llama-3.2-1B-GGUF/resolve/main/Flowable-Docs-Llama-3.2-1B.Q3_K_M.gguf) | Q3_K_M | 0.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Flowable-Docs-Llama-3.2-1B-GGUF/resolve/main/Flowable-Docs-Llama-3.2-1B.Q3_K_L.gguf) | Q3_K_L | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Flowable-Docs-Llama-3.2-1B-GGUF/resolve/main/Flowable-Docs-Llama-3.2-1B.IQ4_XS.gguf) | IQ4_XS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Flowable-Docs-Llama-3.2-1B-GGUF/resolve/main/Flowable-Docs-Llama-3.2-1B.Q4_0_4_4.gguf) | Q4_0_4_4 | 0.9 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Flowable-Docs-Llama-3.2-1B-GGUF/resolve/main/Flowable-Docs-Llama-3.2-1B.Q4_K_S.gguf) | Q4_K_S | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Flowable-Docs-Llama-3.2-1B-GGUF/resolve/main/Flowable-Docs-Llama-3.2-1B.Q4_K_M.gguf) | Q4_K_M | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Flowable-Docs-Llama-3.2-1B-GGUF/resolve/main/Flowable-Docs-Llama-3.2-1B.Q5_K_S.gguf) | Q5_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Flowable-Docs-Llama-3.2-1B-GGUF/resolve/main/Flowable-Docs-Llama-3.2-1B.Q5_K_M.gguf) | Q5_K_M | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Flowable-Docs-Llama-3.2-1B-GGUF/resolve/main/Flowable-Docs-Llama-3.2-1B.Q6_K.gguf) | Q6_K | 1.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Flowable-Docs-Llama-3.2-1B-GGUF/resolve/main/Flowable-Docs-Llama-3.2-1B.Q8_0.gguf) | Q8_0 | 1.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Flowable-Docs-Llama-3.2-1B-GGUF/resolve/main/Flowable-Docs-Llama-3.2-1B.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. + +