commit 2e7e29efe2d3c9a5fc787a86aeff0e0ea717589e Author: ModelHub XC Date: Sat Oct 3 03:08:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.2-3B-Instruct-AMPO-V1-5-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..b9f7585 --- /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-AMPO-V1-5.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-AMPO-V1-5.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-AMPO-V1-5.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-AMPO-V1-5.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-AMPO-V1-5.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-AMPO-V1-5.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-AMPO-V1-5.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-AMPO-V1-5.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-AMPO-V1-5.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-AMPO-V1-5.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-AMPO-V1-5.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-AMPO-V1-5.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.2-3B-Instruct-AMPO-V1-5.IQ4_XS.gguf b/Llama-3.2-3B-Instruct-AMPO-V1-5.IQ4_XS.gguf new file mode 100644 index 0000000..987bf80 --- /dev/null +++ b/Llama-3.2-3B-Instruct-AMPO-V1-5.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9281f7bc4040f376377905dde1bb48e757155012aac4209e95b6943ceda55f32 +size 1840907328 diff --git a/Llama-3.2-3B-Instruct-AMPO-V1-5.Q2_K.gguf b/Llama-3.2-3B-Instruct-AMPO-V1-5.Q2_K.gguf new file mode 100644 index 0000000..bd79e99 --- /dev/null +++ b/Llama-3.2-3B-Instruct-AMPO-V1-5.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17b36059d6c6cadd807b8b617639b6d5d0ad804e6698aa41ccef325bc1c5f399 +size 1363936320 diff --git a/Llama-3.2-3B-Instruct-AMPO-V1-5.Q3_K_L.gguf b/Llama-3.2-3B-Instruct-AMPO-V1-5.Q3_K_L.gguf new file mode 100644 index 0000000..7246343 --- /dev/null +++ b/Llama-3.2-3B-Instruct-AMPO-V1-5.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:929c91b5267057e46adfa590b308a3d482bfaa751105bf6d53b08bb750604b20 +size 1815348288 diff --git a/Llama-3.2-3B-Instruct-AMPO-V1-5.Q3_K_M.gguf b/Llama-3.2-3B-Instruct-AMPO-V1-5.Q3_K_M.gguf new file mode 100644 index 0000000..f3bae36 --- /dev/null +++ b/Llama-3.2-3B-Instruct-AMPO-V1-5.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe7d1069d2a6ca62866bc465dc414dbb2e2ccfff95374b17de9fd96bd08f121d +size 1687159872 diff --git a/Llama-3.2-3B-Instruct-AMPO-V1-5.Q3_K_S.gguf b/Llama-3.2-3B-Instruct-AMPO-V1-5.Q3_K_S.gguf new file mode 100644 index 0000000..fdcd2bf --- /dev/null +++ b/Llama-3.2-3B-Instruct-AMPO-V1-5.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5fe952137eaadd4ca980319fa79d02c93f06aecf4b9f5c23f8dc29136e6a023 +size 1542849600 diff --git a/Llama-3.2-3B-Instruct-AMPO-V1-5.Q4_K_M.gguf b/Llama-3.2-3B-Instruct-AMPO-V1-5.Q4_K_M.gguf new file mode 100644 index 0000000..a5b9c37 --- /dev/null +++ b/Llama-3.2-3B-Instruct-AMPO-V1-5.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6dfc300de9f03cb10368a3eaf8b40e12e5228c21a16f822aed3b1954a69148c4 +size 2019378240 diff --git a/Llama-3.2-3B-Instruct-AMPO-V1-5.Q4_K_S.gguf b/Llama-3.2-3B-Instruct-AMPO-V1-5.Q4_K_S.gguf new file mode 100644 index 0000000..f33da1f --- /dev/null +++ b/Llama-3.2-3B-Instruct-AMPO-V1-5.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e8097edeb972bf158e301e757ac35550675c4eda948ba3c82985b1ca73f84f6 +size 1928201280 diff --git a/Llama-3.2-3B-Instruct-AMPO-V1-5.Q5_K_M.gguf b/Llama-3.2-3B-Instruct-AMPO-V1-5.Q5_K_M.gguf new file mode 100644 index 0000000..937e57a --- /dev/null +++ b/Llama-3.2-3B-Instruct-AMPO-V1-5.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3cf38391f2922a2327eb11d9d24015c6d82612b97bbbfa0100e66cb009b3072 +size 2322154560 diff --git a/Llama-3.2-3B-Instruct-AMPO-V1-5.Q5_K_S.gguf b/Llama-3.2-3B-Instruct-AMPO-V1-5.Q5_K_S.gguf new file mode 100644 index 0000000..bf157e3 --- /dev/null +++ b/Llama-3.2-3B-Instruct-AMPO-V1-5.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93dacb511b2659db95fca7604fc85fa5386c979d4fbc89b59b04e7f0cee69d67 +size 2269512768 diff --git a/Llama-3.2-3B-Instruct-AMPO-V1-5.Q6_K.gguf b/Llama-3.2-3B-Instruct-AMPO-V1-5.Q6_K.gguf new file mode 100644 index 0000000..a0ba422 --- /dev/null +++ b/Llama-3.2-3B-Instruct-AMPO-V1-5.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02d1e224cf07d78e7f80638dfbf4d6df2386a7bb9dcff8e11d8204b9fe51bd3a +size 2643854400 diff --git a/Llama-3.2-3B-Instruct-AMPO-V1-5.Q8_0.gguf b/Llama-3.2-3B-Instruct-AMPO-V1-5.Q8_0.gguf new file mode 100644 index 0000000..6077cda --- /dev/null +++ b/Llama-3.2-3B-Instruct-AMPO-V1-5.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38c8b1e664d071e0eed83be6a2c5ad00725b42f84cdc882d571b89e9f841579c +size 3421899840 diff --git a/Llama-3.2-3B-Instruct-AMPO-V1-5.f16.gguf b/Llama-3.2-3B-Instruct-AMPO-V1-5.f16.gguf new file mode 100644 index 0000000..4a00133 --- /dev/null +++ b/Llama-3.2-3B-Instruct-AMPO-V1-5.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09e12aeca56fee8945da217ffcf061f4e6ab9a3bd7f5b54e812cd863985ef2e8 +size 6433688640 diff --git a/README.md b/README.md new file mode 100644 index 0000000..137facb --- /dev/null +++ b/README.md @@ -0,0 +1,76 @@ +--- +base_model: swadeshb/Llama-3.2-3B-Instruct-AMPO-V1-5 +language: +- en +library_name: transformers +model_name: Llama-3.2-3B-Instruct-AMPO-V1-5 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- generated_from_trainer +- trl +- grpo +--- +## About + + + + + + + + + +static quants of https://huggingface.co/swadeshb/Llama-3.2-3B-Instruct-AMPO-V1-5 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama-3.2-3B-Instruct-AMPO-V1-5-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-AMPO-V1-5-GGUF/resolve/main/Llama-3.2-3B-Instruct-AMPO-V1-5.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-AMPO-V1-5-GGUF/resolve/main/Llama-3.2-3B-Instruct-AMPO-V1-5.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-AMPO-V1-5-GGUF/resolve/main/Llama-3.2-3B-Instruct-AMPO-V1-5.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-AMPO-V1-5-GGUF/resolve/main/Llama-3.2-3B-Instruct-AMPO-V1-5.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-AMPO-V1-5-GGUF/resolve/main/Llama-3.2-3B-Instruct-AMPO-V1-5.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-AMPO-V1-5-GGUF/resolve/main/Llama-3.2-3B-Instruct-AMPO-V1-5.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-AMPO-V1-5-GGUF/resolve/main/Llama-3.2-3B-Instruct-AMPO-V1-5.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-AMPO-V1-5-GGUF/resolve/main/Llama-3.2-3B-Instruct-AMPO-V1-5.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-AMPO-V1-5-GGUF/resolve/main/Llama-3.2-3B-Instruct-AMPO-V1-5.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-AMPO-V1-5-GGUF/resolve/main/Llama-3.2-3B-Instruct-AMPO-V1-5.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-AMPO-V1-5-GGUF/resolve/main/Llama-3.2-3B-Instruct-AMPO-V1-5.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-AMPO-V1-5-GGUF/resolve/main/Llama-3.2-3B-Instruct-AMPO-V1-5.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. + +