commit 0ed7960da8862edd9a34470733b7a3dae995b2b7 Author: ModelHub XC Date: Sat May 30 15:46:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.2-3B-Instruct-AMPO-V1-7-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..9a86bed --- /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-V1-7.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-AMPO-V1-7.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-AMPO-V1-7.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-AMPO-V1-7.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-AMPO-V1-7.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-AMPO-V1-7.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-AMPO-V1-7.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-AMPO-V1-7.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-AMPO-V1-7.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-AMPO-V1-7.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-AMPO-V1-7.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-AMPO-V1-7.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.2-3B-Instruct-AMPO-V1-7.IQ4_XS.gguf b/Llama-3.2-3B-Instruct-AMPO-V1-7.IQ4_XS.gguf new file mode 100644 index 0000000..284de50 --- /dev/null +++ b/Llama-3.2-3B-Instruct-AMPO-V1-7.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88ad0656855a57050613ac8c9e9e126aab013b15871e94f51684d2ac5f16edce +size 1840907328 diff --git a/Llama-3.2-3B-Instruct-AMPO-V1-7.Q2_K.gguf b/Llama-3.2-3B-Instruct-AMPO-V1-7.Q2_K.gguf new file mode 100644 index 0000000..7d9308d --- /dev/null +++ b/Llama-3.2-3B-Instruct-AMPO-V1-7.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee1a9ad6d7a071900cc114ed6f0d79e16c38284d2e1133d9e1db1a321cf2e342 +size 1363936320 diff --git a/Llama-3.2-3B-Instruct-AMPO-V1-7.Q3_K_L.gguf b/Llama-3.2-3B-Instruct-AMPO-V1-7.Q3_K_L.gguf new file mode 100644 index 0000000..8db8e0b --- /dev/null +++ b/Llama-3.2-3B-Instruct-AMPO-V1-7.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5151f70f752719a7503e246866fdf3c922639e903926220af463909fcaac7cd +size 1815348288 diff --git a/Llama-3.2-3B-Instruct-AMPO-V1-7.Q3_K_M.gguf b/Llama-3.2-3B-Instruct-AMPO-V1-7.Q3_K_M.gguf new file mode 100644 index 0000000..9fc1e2e --- /dev/null +++ b/Llama-3.2-3B-Instruct-AMPO-V1-7.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a51000e3c245ec57e571fc5d2f6256b02ba9d1ec60a3b2ac3786c99d5ba3df6 +size 1687159872 diff --git a/Llama-3.2-3B-Instruct-AMPO-V1-7.Q3_K_S.gguf b/Llama-3.2-3B-Instruct-AMPO-V1-7.Q3_K_S.gguf new file mode 100644 index 0000000..9acc633 --- /dev/null +++ b/Llama-3.2-3B-Instruct-AMPO-V1-7.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0908f531386bc85999330f0cd3bc9d0511e3d3ff54f312229bee1c16b1878c1 +size 1542849600 diff --git a/Llama-3.2-3B-Instruct-AMPO-V1-7.Q4_K_M.gguf b/Llama-3.2-3B-Instruct-AMPO-V1-7.Q4_K_M.gguf new file mode 100644 index 0000000..c065452 --- /dev/null +++ b/Llama-3.2-3B-Instruct-AMPO-V1-7.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06b8a0980cc894909cabf1e516f9c8ed1f0a49a0ab8817309c5a506ba0fd894b +size 2019378240 diff --git a/Llama-3.2-3B-Instruct-AMPO-V1-7.Q4_K_S.gguf b/Llama-3.2-3B-Instruct-AMPO-V1-7.Q4_K_S.gguf new file mode 100644 index 0000000..009c2de --- /dev/null +++ b/Llama-3.2-3B-Instruct-AMPO-V1-7.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ca97ffad91a445fd38d1dcc2d499c709185b2cc0bc58a574b160424e8159fa8 +size 1928201280 diff --git a/Llama-3.2-3B-Instruct-AMPO-V1-7.Q5_K_M.gguf b/Llama-3.2-3B-Instruct-AMPO-V1-7.Q5_K_M.gguf new file mode 100644 index 0000000..477c245 --- /dev/null +++ b/Llama-3.2-3B-Instruct-AMPO-V1-7.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ad78c76d6eac3ec2e83cb52d8d6ae131492dd489eae51749d6123f4a78d2f96 +size 2322154560 diff --git a/Llama-3.2-3B-Instruct-AMPO-V1-7.Q5_K_S.gguf b/Llama-3.2-3B-Instruct-AMPO-V1-7.Q5_K_S.gguf new file mode 100644 index 0000000..38e7278 --- /dev/null +++ b/Llama-3.2-3B-Instruct-AMPO-V1-7.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9831845e8ec6283a875479724f5b03b962221f7f5eff253c1e0c4fec8ce395d8 +size 2269512768 diff --git a/Llama-3.2-3B-Instruct-AMPO-V1-7.Q6_K.gguf b/Llama-3.2-3B-Instruct-AMPO-V1-7.Q6_K.gguf new file mode 100644 index 0000000..f60b5d9 --- /dev/null +++ b/Llama-3.2-3B-Instruct-AMPO-V1-7.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3cacb12b088e33788e54c58d7df16b752b47662d52e5359a7aacbb2c1cedb333 +size 2643854400 diff --git a/Llama-3.2-3B-Instruct-AMPO-V1-7.Q8_0.gguf b/Llama-3.2-3B-Instruct-AMPO-V1-7.Q8_0.gguf new file mode 100644 index 0000000..625c535 --- /dev/null +++ b/Llama-3.2-3B-Instruct-AMPO-V1-7.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8dbd18d0fa322a30cb1f05ede8b73ef18767c687fefcd343296966812d0880c +size 3421899840 diff --git a/Llama-3.2-3B-Instruct-AMPO-V1-7.f16.gguf b/Llama-3.2-3B-Instruct-AMPO-V1-7.f16.gguf new file mode 100644 index 0000000..ea837fe --- /dev/null +++ b/Llama-3.2-3B-Instruct-AMPO-V1-7.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3dbf219cb8d0b600e7e5712859b1a9c7e66a8c85fb0b5267f0e99d2ab2c2ff5a +size 6433688640 diff --git a/README.md b/README.md new file mode 100644 index 0000000..8bb6942 --- /dev/null +++ b/README.md @@ -0,0 +1,76 @@ +--- +base_model: swadeshb/Llama-3.2-3B-Instruct-AMPO-V1-7 +language: +- en +library_name: transformers +model_name: Llama-3.2-3B-Instruct-AMPO-V1-7 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- generated_from_trainer +- grpo +- trl +--- +## About + + + + + + + + + +static quants of https://huggingface.co/swadeshb/Llama-3.2-3B-Instruct-AMPO-V1-7 + + + +***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-V1-7-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-V1-7-GGUF/resolve/main/Llama-3.2-3B-Instruct-AMPO-V1-7.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-AMPO-V1-7-GGUF/resolve/main/Llama-3.2-3B-Instruct-AMPO-V1-7.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-AMPO-V1-7-GGUF/resolve/main/Llama-3.2-3B-Instruct-AMPO-V1-7.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-AMPO-V1-7-GGUF/resolve/main/Llama-3.2-3B-Instruct-AMPO-V1-7.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-AMPO-V1-7-GGUF/resolve/main/Llama-3.2-3B-Instruct-AMPO-V1-7.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-AMPO-V1-7-GGUF/resolve/main/Llama-3.2-3B-Instruct-AMPO-V1-7.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-AMPO-V1-7-GGUF/resolve/main/Llama-3.2-3B-Instruct-AMPO-V1-7.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-AMPO-V1-7-GGUF/resolve/main/Llama-3.2-3B-Instruct-AMPO-V1-7.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-AMPO-V1-7-GGUF/resolve/main/Llama-3.2-3B-Instruct-AMPO-V1-7.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-AMPO-V1-7-GGUF/resolve/main/Llama-3.2-3B-Instruct-AMPO-V1-7.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-AMPO-V1-7-GGUF/resolve/main/Llama-3.2-3B-Instruct-AMPO-V1-7.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-AMPO-V1-7-GGUF/resolve/main/Llama-3.2-3B-Instruct-AMPO-V1-7.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. + +