commit 3ac3017d2f2d8fa39153b588d6971b0bb7af5917 Author: ModelHub XC Date: Thu May 14 12:45:44 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.2-3B-Instruct-SLDS-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..83a5fc2 --- /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-3.2-3B-Instruct-SLDS.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-SLDS.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-SLDS.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-SLDS.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-SLDS.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-SLDS.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-SLDS.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-SLDS.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-SLDS.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-SLDS.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-SLDS.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-SLDS.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.2-3B-Instruct-SLDS.IQ4_XS.gguf b/Llama-3.2-3B-Instruct-SLDS.IQ4_XS.gguf new file mode 100644 index 0000000..ada0e9b --- /dev/null +++ b/Llama-3.2-3B-Instruct-SLDS.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e475fd623037ae7997ff6f6f405b34766629222ad846a21a10583c6b28e0f9f6 +size 1840907328 diff --git a/Llama-3.2-3B-Instruct-SLDS.Q2_K.gguf b/Llama-3.2-3B-Instruct-SLDS.Q2_K.gguf new file mode 100644 index 0000000..68bcf14 --- /dev/null +++ b/Llama-3.2-3B-Instruct-SLDS.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:956cff5b306531fc7a846ed43cfb8e852caf37613c91d3e4a972fe3ddda4e129 +size 1363936320 diff --git a/Llama-3.2-3B-Instruct-SLDS.Q3_K_L.gguf b/Llama-3.2-3B-Instruct-SLDS.Q3_K_L.gguf new file mode 100644 index 0000000..9d4229a --- /dev/null +++ b/Llama-3.2-3B-Instruct-SLDS.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf73e86880fb34dfb40b6cefc6ab91ea975f67732092fa694b95cb344e69e8ff +size 1815348288 diff --git a/Llama-3.2-3B-Instruct-SLDS.Q3_K_M.gguf b/Llama-3.2-3B-Instruct-SLDS.Q3_K_M.gguf new file mode 100644 index 0000000..e6fff35 --- /dev/null +++ b/Llama-3.2-3B-Instruct-SLDS.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4ebe7572ec174ece5de89876e8298d279e9b52232a8aaf51a53321ee69f1260 +size 1687159872 diff --git a/Llama-3.2-3B-Instruct-SLDS.Q3_K_S.gguf b/Llama-3.2-3B-Instruct-SLDS.Q3_K_S.gguf new file mode 100644 index 0000000..91b570a --- /dev/null +++ b/Llama-3.2-3B-Instruct-SLDS.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea8b2f2bf9900b64fe47c3bac32a0adf3a816beceb5858ba88212a0d08a12dea +size 1542849600 diff --git a/Llama-3.2-3B-Instruct-SLDS.Q4_K_M.gguf b/Llama-3.2-3B-Instruct-SLDS.Q4_K_M.gguf new file mode 100644 index 0000000..bf0a2ee --- /dev/null +++ b/Llama-3.2-3B-Instruct-SLDS.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15ed68087b073b6c65b0ff98db00be4cc138015c8c74fa42dabe2107087f583f +size 2019378240 diff --git a/Llama-3.2-3B-Instruct-SLDS.Q4_K_S.gguf b/Llama-3.2-3B-Instruct-SLDS.Q4_K_S.gguf new file mode 100644 index 0000000..ed1914c --- /dev/null +++ b/Llama-3.2-3B-Instruct-SLDS.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:406a49175658be894b3fd1fee41b887e5180481d4939e8e4b58ecce943008293 +size 1928201280 diff --git a/Llama-3.2-3B-Instruct-SLDS.Q5_K_M.gguf b/Llama-3.2-3B-Instruct-SLDS.Q5_K_M.gguf new file mode 100644 index 0000000..80eceb3 --- /dev/null +++ b/Llama-3.2-3B-Instruct-SLDS.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21b474b5de50e6bb83cacb81642685b617e0c4286310082d3cd9adeca4ba9a07 +size 2322154560 diff --git a/Llama-3.2-3B-Instruct-SLDS.Q5_K_S.gguf b/Llama-3.2-3B-Instruct-SLDS.Q5_K_S.gguf new file mode 100644 index 0000000..289fbb7 --- /dev/null +++ b/Llama-3.2-3B-Instruct-SLDS.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04e1796a7af4e2d047f1793b0ac9116576839c70b61f077f2b33afe930f7a3a7 +size 2269512768 diff --git a/Llama-3.2-3B-Instruct-SLDS.Q6_K.gguf b/Llama-3.2-3B-Instruct-SLDS.Q6_K.gguf new file mode 100644 index 0000000..7f09d72 --- /dev/null +++ b/Llama-3.2-3B-Instruct-SLDS.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d1fc925c75299c6d6bd08a216891f4adbc3a5c85009f76eb594730579baa106 +size 2643854400 diff --git a/Llama-3.2-3B-Instruct-SLDS.Q8_0.gguf b/Llama-3.2-3B-Instruct-SLDS.Q8_0.gguf new file mode 100644 index 0000000..1c98150 --- /dev/null +++ b/Llama-3.2-3B-Instruct-SLDS.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45e219f4cf13e07fe5a36065a498b005abd62d20abeca7ebc86ab15eed40b0f2 +size 3421899840 diff --git a/Llama-3.2-3B-Instruct-SLDS.f16.gguf b/Llama-3.2-3B-Instruct-SLDS.f16.gguf new file mode 100644 index 0000000..54fda4d --- /dev/null +++ b/Llama-3.2-3B-Instruct-SLDS.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a79199ac0c2853f184705bd0939a0e880bed4fb59094dab340e9da5a798e7509 +size 6433688640 diff --git a/README.md b/README.md new file mode 100644 index 0000000..cf709e6 --- /dev/null +++ b/README.md @@ -0,0 +1,79 @@ +--- +base_model: ipst/Llama-3.2-3B-Instruct-SLDS +datasets: +- ipst/slds +language: +- de +- fr +- it +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- trl +--- +## About + + + + + + +static quants of https://huggingface.co/ipst/Llama-3.2-3B-Instruct-SLDS + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama-3.2-3B-Instruct-SLDS-GGUF).*** + +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-3.2-3B-Instruct-SLDS-GGUF/resolve/main/Llama-3.2-3B-Instruct-SLDS.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-SLDS-GGUF/resolve/main/Llama-3.2-3B-Instruct-SLDS.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-SLDS-GGUF/resolve/main/Llama-3.2-3B-Instruct-SLDS.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-SLDS-GGUF/resolve/main/Llama-3.2-3B-Instruct-SLDS.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-SLDS-GGUF/resolve/main/Llama-3.2-3B-Instruct-SLDS.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-SLDS-GGUF/resolve/main/Llama-3.2-3B-Instruct-SLDS.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-SLDS-GGUF/resolve/main/Llama-3.2-3B-Instruct-SLDS.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-SLDS-GGUF/resolve/main/Llama-3.2-3B-Instruct-SLDS.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-SLDS-GGUF/resolve/main/Llama-3.2-3B-Instruct-SLDS.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-SLDS-GGUF/resolve/main/Llama-3.2-3B-Instruct-SLDS.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-SLDS-GGUF/resolve/main/Llama-3.2-3B-Instruct-SLDS.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-SLDS-GGUF/resolve/main/Llama-3.2-3B-Instruct-SLDS.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. + +