commit 68b75fa38841c8678a21c00f2906d422896d46a0 Author: ModelHub XC Date: Tue Oct 6 09:27:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.2-3B-Instruct-CRPO-V34-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..286ad76 --- /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-CRPO-V34.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-CRPO-V34.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-CRPO-V34.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-CRPO-V34.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-CRPO-V34.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-CRPO-V34.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-CRPO-V34.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-CRPO-V34.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-CRPO-V34.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-CRPO-V34.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-CRPO-V34.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-CRPO-V34.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.2-3B-Instruct-CRPO-V34.IQ4_XS.gguf b/Llama-3.2-3B-Instruct-CRPO-V34.IQ4_XS.gguf new file mode 100644 index 0000000..b47b3ca --- /dev/null +++ b/Llama-3.2-3B-Instruct-CRPO-V34.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21d0b2dbaf71dae4fa28b5314542c0ca6229344f88b514975fe73d452256559c +size 1840907328 diff --git a/Llama-3.2-3B-Instruct-CRPO-V34.Q2_K.gguf b/Llama-3.2-3B-Instruct-CRPO-V34.Q2_K.gguf new file mode 100644 index 0000000..cbcb6b2 --- /dev/null +++ b/Llama-3.2-3B-Instruct-CRPO-V34.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ebc4459550c7585c32c7bed4d205036c39ab02c97d51134af2d182e08331be6 +size 1363936320 diff --git a/Llama-3.2-3B-Instruct-CRPO-V34.Q3_K_L.gguf b/Llama-3.2-3B-Instruct-CRPO-V34.Q3_K_L.gguf new file mode 100644 index 0000000..2505385 --- /dev/null +++ b/Llama-3.2-3B-Instruct-CRPO-V34.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:528169343e38cfa73c39ceff5e268ac604a8e431ba86afcb02208a6e13085edd +size 1815348288 diff --git a/Llama-3.2-3B-Instruct-CRPO-V34.Q3_K_M.gguf b/Llama-3.2-3B-Instruct-CRPO-V34.Q3_K_M.gguf new file mode 100644 index 0000000..fa5f189 --- /dev/null +++ b/Llama-3.2-3B-Instruct-CRPO-V34.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:056773d7ca4472cd2a029f0e7db596311009e7a382d0729f8c62b7254b22083c +size 1687159872 diff --git a/Llama-3.2-3B-Instruct-CRPO-V34.Q3_K_S.gguf b/Llama-3.2-3B-Instruct-CRPO-V34.Q3_K_S.gguf new file mode 100644 index 0000000..a372b62 --- /dev/null +++ b/Llama-3.2-3B-Instruct-CRPO-V34.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8a53f6d066d864596e717d1fdd4a31a2a5351699e1a34d2165fa7c5e92e6c87 +size 1542849600 diff --git a/Llama-3.2-3B-Instruct-CRPO-V34.Q4_K_M.gguf b/Llama-3.2-3B-Instruct-CRPO-V34.Q4_K_M.gguf new file mode 100644 index 0000000..c105617 --- /dev/null +++ b/Llama-3.2-3B-Instruct-CRPO-V34.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d3a671f81e6c997f0891e03f6e843044078bf84a27793203218c190b876df95 +size 2019378240 diff --git a/Llama-3.2-3B-Instruct-CRPO-V34.Q4_K_S.gguf b/Llama-3.2-3B-Instruct-CRPO-V34.Q4_K_S.gguf new file mode 100644 index 0000000..2872993 --- /dev/null +++ b/Llama-3.2-3B-Instruct-CRPO-V34.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f966613e1b5a437613fff74730449abca6bb775581cc52c0557a8e798c8a0604 +size 1928201280 diff --git a/Llama-3.2-3B-Instruct-CRPO-V34.Q5_K_M.gguf b/Llama-3.2-3B-Instruct-CRPO-V34.Q5_K_M.gguf new file mode 100644 index 0000000..31a26ca --- /dev/null +++ b/Llama-3.2-3B-Instruct-CRPO-V34.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:668380f686ea331446e8ee99295f9b04945e4797811cfddc28a3f3b13958502e +size 2322154560 diff --git a/Llama-3.2-3B-Instruct-CRPO-V34.Q5_K_S.gguf b/Llama-3.2-3B-Instruct-CRPO-V34.Q5_K_S.gguf new file mode 100644 index 0000000..cbfa68d --- /dev/null +++ b/Llama-3.2-3B-Instruct-CRPO-V34.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0edf3ab1d782860d830affd279a15d1a05711e7b2397c62fa8b7fa730d36dba4 +size 2269512768 diff --git a/Llama-3.2-3B-Instruct-CRPO-V34.Q6_K.gguf b/Llama-3.2-3B-Instruct-CRPO-V34.Q6_K.gguf new file mode 100644 index 0000000..a5685ab --- /dev/null +++ b/Llama-3.2-3B-Instruct-CRPO-V34.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36830e712c2ba9500aca3d7f4f21da1bb64dcd978a536708c05624e4041ee8d6 +size 2643854400 diff --git a/Llama-3.2-3B-Instruct-CRPO-V34.Q8_0.gguf b/Llama-3.2-3B-Instruct-CRPO-V34.Q8_0.gguf new file mode 100644 index 0000000..f2c46ad --- /dev/null +++ b/Llama-3.2-3B-Instruct-CRPO-V34.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e1b43420ade4dc9f475ffdd12bd48924551e6778c5c3caa1b063e09436044cb +size 3421899840 diff --git a/Llama-3.2-3B-Instruct-CRPO-V34.f16.gguf b/Llama-3.2-3B-Instruct-CRPO-V34.f16.gguf new file mode 100644 index 0000000..2f258a9 --- /dev/null +++ b/Llama-3.2-3B-Instruct-CRPO-V34.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f6f1a389fdc310ca671644c994c03a506b1acf7f4d2f94ee8328b2df823d9e0 +size 6433688640 diff --git a/README.md b/README.md new file mode 100644 index 0000000..f54535f --- /dev/null +++ b/README.md @@ -0,0 +1,76 @@ +--- +base_model: swadeshb/Llama-3.2-3B-Instruct-CRPO-V34 +language: +- en +library_name: transformers +model_name: Llama-3.2-3B-Instruct-CRPO-V34 +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-CRPO-V34 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama-3.2-3B-Instruct-CRPO-V34-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-CRPO-V34-GGUF/resolve/main/Llama-3.2-3B-Instruct-CRPO-V34.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-CRPO-V34-GGUF/resolve/main/Llama-3.2-3B-Instruct-CRPO-V34.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-CRPO-V34-GGUF/resolve/main/Llama-3.2-3B-Instruct-CRPO-V34.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-CRPO-V34-GGUF/resolve/main/Llama-3.2-3B-Instruct-CRPO-V34.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-CRPO-V34-GGUF/resolve/main/Llama-3.2-3B-Instruct-CRPO-V34.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-CRPO-V34-GGUF/resolve/main/Llama-3.2-3B-Instruct-CRPO-V34.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-CRPO-V34-GGUF/resolve/main/Llama-3.2-3B-Instruct-CRPO-V34.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-CRPO-V34-GGUF/resolve/main/Llama-3.2-3B-Instruct-CRPO-V34.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-CRPO-V34-GGUF/resolve/main/Llama-3.2-3B-Instruct-CRPO-V34.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-CRPO-V34-GGUF/resolve/main/Llama-3.2-3B-Instruct-CRPO-V34.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-CRPO-V34-GGUF/resolve/main/Llama-3.2-3B-Instruct-CRPO-V34.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-CRPO-V34-GGUF/resolve/main/Llama-3.2-3B-Instruct-CRPO-V34.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. + +