commit e9412f9fbb490cdf306525345ac420589cc17308 Author: ModelHub XC Date: Mon Sep 21 07:56:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.2-1B-Instruct-MGSM8K-de-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..5666064 --- /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 +Llama-3.2-1B-Instruct-MGSM8K-de.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-MGSM8K-de.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-MGSM8K-de.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-MGSM8K-de.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-MGSM8K-de.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-MGSM8K-de.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-MGSM8K-de.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-MGSM8K-de.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-MGSM8K-de.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-MGSM8K-de.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-MGSM8K-de.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-MGSM8K-de.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-MGSM8K-de.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.2-1B-Instruct-MGSM8K-de.IQ4_XS.gguf b/Llama-3.2-1B-Instruct-MGSM8K-de.IQ4_XS.gguf new file mode 100644 index 0000000..29d6633 --- /dev/null +++ b/Llama-3.2-1B-Instruct-MGSM8K-de.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e374d7d5299b744adf407e03fa312694fd401f172a0c0571f59814b2d64f03e0 +size 748384352 diff --git a/Llama-3.2-1B-Instruct-MGSM8K-de.Q2_K.gguf b/Llama-3.2-1B-Instruct-MGSM8K-de.Q2_K.gguf new file mode 100644 index 0000000..2f0b941 --- /dev/null +++ b/Llama-3.2-1B-Instruct-MGSM8K-de.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7c413e35677008eb9612b7b669d121015272cc57456be6f5c7bf78aafb1c67d +size 580874336 diff --git a/Llama-3.2-1B-Instruct-MGSM8K-de.Q3_K_L.gguf b/Llama-3.2-1B-Instruct-MGSM8K-de.Q3_K_L.gguf new file mode 100644 index 0000000..8d2b824 --- /dev/null +++ b/Llama-3.2-1B-Instruct-MGSM8K-de.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:831b9fbdd86f44ba3a3a4752461d588c982861f0f7c62828c9d26bf7599ebb9d +size 732524640 diff --git a/Llama-3.2-1B-Instruct-MGSM8K-de.Q3_K_M.gguf b/Llama-3.2-1B-Instruct-MGSM8K-de.Q3_K_M.gguf new file mode 100644 index 0000000..b0fd172 --- /dev/null +++ b/Llama-3.2-1B-Instruct-MGSM8K-de.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8652099ab5e2b83b901e5b7efa0ed9bc62f37c121360d480e9fe3f7c75feca5f +size 690843744 diff --git a/Llama-3.2-1B-Instruct-MGSM8K-de.Q3_K_S.gguf b/Llama-3.2-1B-Instruct-MGSM8K-de.Q3_K_S.gguf new file mode 100644 index 0000000..10d13ca --- /dev/null +++ b/Llama-3.2-1B-Instruct-MGSM8K-de.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:162f1677275988112a487fc6e116812d0bc504045a300bdb16b97e47f514fcd0 +size 641691744 diff --git a/Llama-3.2-1B-Instruct-MGSM8K-de.Q4_0_4_4.gguf b/Llama-3.2-1B-Instruct-MGSM8K-de.Q4_0_4_4.gguf new file mode 100644 index 0000000..66322cf --- /dev/null +++ b/Llama-3.2-1B-Instruct-MGSM8K-de.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94ea275e93bdee9377dc713ae55be4d319a343e4f0a0e944d9942e54faeefc63 +size 770928736 diff --git a/Llama-3.2-1B-Instruct-MGSM8K-de.Q4_K_M.gguf b/Llama-3.2-1B-Instruct-MGSM8K-de.Q4_K_M.gguf new file mode 100644 index 0000000..9ea9752 --- /dev/null +++ b/Llama-3.2-1B-Instruct-MGSM8K-de.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d154c79805b204e282c7dbc91a309b6eaba042a0f8a29ac89366b6bfcc1fa6e +size 807694432 diff --git a/Llama-3.2-1B-Instruct-MGSM8K-de.Q4_K_S.gguf b/Llama-3.2-1B-Instruct-MGSM8K-de.Q4_K_S.gguf new file mode 100644 index 0000000..3e27ec8 --- /dev/null +++ b/Llama-3.2-1B-Instruct-MGSM8K-de.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e01d23c48ad27ae35508c9da533725cc6bb3d8649685c53d4d0b52360ece2cb9 +size 775647328 diff --git a/Llama-3.2-1B-Instruct-MGSM8K-de.Q5_K_M.gguf b/Llama-3.2-1B-Instruct-MGSM8K-de.Q5_K_M.gguf new file mode 100644 index 0000000..d7d90a3 --- /dev/null +++ b/Llama-3.2-1B-Instruct-MGSM8K-de.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:044823f9be9408a9b5322d93f8e171425def2b70fd6d1e82d254ec23658a397a +size 911503456 diff --git a/Llama-3.2-1B-Instruct-MGSM8K-de.Q5_K_S.gguf b/Llama-3.2-1B-Instruct-MGSM8K-de.Q5_K_S.gguf new file mode 100644 index 0000000..2eef414 --- /dev/null +++ b/Llama-3.2-1B-Instruct-MGSM8K-de.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e7ae27fb80f53873cb72a3142297afab23910e75f87610a208a5a9690315994 +size 892563552 diff --git a/Llama-3.2-1B-Instruct-MGSM8K-de.Q6_K.gguf b/Llama-3.2-1B-Instruct-MGSM8K-de.Q6_K.gguf new file mode 100644 index 0000000..5073c6d --- /dev/null +++ b/Llama-3.2-1B-Instruct-MGSM8K-de.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fea0bbd7669789ee4a98ca8f831a7220a9a47e32d6fbfc39be6c3c21bc9ac0d8 +size 1021800544 diff --git a/Llama-3.2-1B-Instruct-MGSM8K-de.Q8_0.gguf b/Llama-3.2-1B-Instruct-MGSM8K-de.Q8_0.gguf new file mode 100644 index 0000000..8755dc7 --- /dev/null +++ b/Llama-3.2-1B-Instruct-MGSM8K-de.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25a4a163b34f7a97561390312b8e37297daf6527dbb1548ffe7cfb3ee3050502 +size 1321082976 diff --git a/Llama-3.2-1B-Instruct-MGSM8K-de.f16.gguf b/Llama-3.2-1B-Instruct-MGSM8K-de.f16.gguf new file mode 100644 index 0000000..f7fc443 --- /dev/null +++ b/Llama-3.2-1B-Instruct-MGSM8K-de.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39cc7c93a3f08e46b3d0772427c79b0bd61e2c9c8a576d1213988e26d78132a0 +size 2479595616 diff --git a/README.md b/README.md new file mode 100644 index 0000000..e23fc9c --- /dev/null +++ b/README.md @@ -0,0 +1,65 @@ +--- +base_model: autoprogrammer/Llama-3.2-1B-Instruct-de +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/autoprogrammer/Llama-3.2-1B-Instruct-de + + +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/Llama-3.2-1B-Instruct-MGSM8K-de-GGUF/resolve/main/Llama-3.2-1B-Instruct-MGSM8K-de.Q2_K.gguf) | Q2_K | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-MGSM8K-de-GGUF/resolve/main/Llama-3.2-1B-Instruct-MGSM8K-de.Q3_K_S.gguf) | Q3_K_S | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-MGSM8K-de-GGUF/resolve/main/Llama-3.2-1B-Instruct-MGSM8K-de.Q3_K_M.gguf) | Q3_K_M | 0.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-MGSM8K-de-GGUF/resolve/main/Llama-3.2-1B-Instruct-MGSM8K-de.Q3_K_L.gguf) | Q3_K_L | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-MGSM8K-de-GGUF/resolve/main/Llama-3.2-1B-Instruct-MGSM8K-de.IQ4_XS.gguf) | IQ4_XS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-MGSM8K-de-GGUF/resolve/main/Llama-3.2-1B-Instruct-MGSM8K-de.Q4_0_4_4.gguf) | Q4_0_4_4 | 0.9 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-MGSM8K-de-GGUF/resolve/main/Llama-3.2-1B-Instruct-MGSM8K-de.Q4_K_S.gguf) | Q4_K_S | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-MGSM8K-de-GGUF/resolve/main/Llama-3.2-1B-Instruct-MGSM8K-de.Q4_K_M.gguf) | Q4_K_M | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-MGSM8K-de-GGUF/resolve/main/Llama-3.2-1B-Instruct-MGSM8K-de.Q5_K_S.gguf) | Q5_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-MGSM8K-de-GGUF/resolve/main/Llama-3.2-1B-Instruct-MGSM8K-de.Q5_K_M.gguf) | Q5_K_M | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-MGSM8K-de-GGUF/resolve/main/Llama-3.2-1B-Instruct-MGSM8K-de.Q6_K.gguf) | Q6_K | 1.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-MGSM8K-de-GGUF/resolve/main/Llama-3.2-1B-Instruct-MGSM8K-de.Q8_0.gguf) | Q8_0 | 1.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-MGSM8K-de-GGUF/resolve/main/Llama-3.2-1B-Instruct-MGSM8K-de.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. + +