commit 7cae39c8b8d772abc54dd608e5d65c96dab5c68c Author: ModelHub XC Date: Sat Sep 19 19:40:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Reasoning-Llama-3.2-3B-Math-Instruct-RE1-ORPO-align-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..8b74c0b --- /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 +Reasoning-Llama-3.2-3B-Math-Instruct-RE1-ORPO-align.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Reasoning-Llama-3.2-3B-Math-Instruct-RE1-ORPO-align.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Reasoning-Llama-3.2-3B-Math-Instruct-RE1-ORPO-align.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Reasoning-Llama-3.2-3B-Math-Instruct-RE1-ORPO-align.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Reasoning-Llama-3.2-3B-Math-Instruct-RE1-ORPO-align.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Reasoning-Llama-3.2-3B-Math-Instruct-RE1-ORPO-align.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Reasoning-Llama-3.2-3B-Math-Instruct-RE1-ORPO-align.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Reasoning-Llama-3.2-3B-Math-Instruct-RE1-ORPO-align.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Reasoning-Llama-3.2-3B-Math-Instruct-RE1-ORPO-align.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Reasoning-Llama-3.2-3B-Math-Instruct-RE1-ORPO-align.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Reasoning-Llama-3.2-3B-Math-Instruct-RE1-ORPO-align.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Reasoning-Llama-3.2-3B-Math-Instruct-RE1-ORPO-align.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..91fad1c --- /dev/null +++ b/README.md @@ -0,0 +1,70 @@ +--- +base_model: EpistemeAI/Reasoning-Llama-3.2-3B-Math-Instruct-RE1-ORPO-align +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- trl +--- +## About + + + + + + +static quants of https://huggingface.co/EpistemeAI/Reasoning-Llama-3.2-3B-Math-Instruct-RE1-ORPO-align + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Reasoning-Llama-3.2-3B-Math-Instruct-RE1-ORPO-align-i1-GGUF +## 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/Reasoning-Llama-3.2-3B-Math-Instruct-RE1-ORPO-align-GGUF/resolve/main/Reasoning-Llama-3.2-3B-Math-Instruct-RE1-ORPO-align.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Reasoning-Llama-3.2-3B-Math-Instruct-RE1-ORPO-align-GGUF/resolve/main/Reasoning-Llama-3.2-3B-Math-Instruct-RE1-ORPO-align.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Reasoning-Llama-3.2-3B-Math-Instruct-RE1-ORPO-align-GGUF/resolve/main/Reasoning-Llama-3.2-3B-Math-Instruct-RE1-ORPO-align.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Reasoning-Llama-3.2-3B-Math-Instruct-RE1-ORPO-align-GGUF/resolve/main/Reasoning-Llama-3.2-3B-Math-Instruct-RE1-ORPO-align.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Reasoning-Llama-3.2-3B-Math-Instruct-RE1-ORPO-align-GGUF/resolve/main/Reasoning-Llama-3.2-3B-Math-Instruct-RE1-ORPO-align.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Reasoning-Llama-3.2-3B-Math-Instruct-RE1-ORPO-align-GGUF/resolve/main/Reasoning-Llama-3.2-3B-Math-Instruct-RE1-ORPO-align.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Reasoning-Llama-3.2-3B-Math-Instruct-RE1-ORPO-align-GGUF/resolve/main/Reasoning-Llama-3.2-3B-Math-Instruct-RE1-ORPO-align.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Reasoning-Llama-3.2-3B-Math-Instruct-RE1-ORPO-align-GGUF/resolve/main/Reasoning-Llama-3.2-3B-Math-Instruct-RE1-ORPO-align.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Reasoning-Llama-3.2-3B-Math-Instruct-RE1-ORPO-align-GGUF/resolve/main/Reasoning-Llama-3.2-3B-Math-Instruct-RE1-ORPO-align.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Reasoning-Llama-3.2-3B-Math-Instruct-RE1-ORPO-align-GGUF/resolve/main/Reasoning-Llama-3.2-3B-Math-Instruct-RE1-ORPO-align.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Reasoning-Llama-3.2-3B-Math-Instruct-RE1-ORPO-align-GGUF/resolve/main/Reasoning-Llama-3.2-3B-Math-Instruct-RE1-ORPO-align.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Reasoning-Llama-3.2-3B-Math-Instruct-RE1-ORPO-align-GGUF/resolve/main/Reasoning-Llama-3.2-3B-Math-Instruct-RE1-ORPO-align.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. + + diff --git a/Reasoning-Llama-3.2-3B-Math-Instruct-RE1-ORPO-align.IQ4_XS.gguf b/Reasoning-Llama-3.2-3B-Math-Instruct-RE1-ORPO-align.IQ4_XS.gguf new file mode 100644 index 0000000..0f5dded --- /dev/null +++ b/Reasoning-Llama-3.2-3B-Math-Instruct-RE1-ORPO-align.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54daa138621202120c63b3a749f0347f3443cf216d1e2f4b8588eb067a43aff3 +size 1840912832 diff --git a/Reasoning-Llama-3.2-3B-Math-Instruct-RE1-ORPO-align.Q2_K.gguf b/Reasoning-Llama-3.2-3B-Math-Instruct-RE1-ORPO-align.Q2_K.gguf new file mode 100644 index 0000000..4ac1f23 --- /dev/null +++ b/Reasoning-Llama-3.2-3B-Math-Instruct-RE1-ORPO-align.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7335cfe5843993e94552466b51a8c1e507a6a551616aa7ec28dc356cd4f4e09d +size 1363941824 diff --git a/Reasoning-Llama-3.2-3B-Math-Instruct-RE1-ORPO-align.Q3_K_L.gguf b/Reasoning-Llama-3.2-3B-Math-Instruct-RE1-ORPO-align.Q3_K_L.gguf new file mode 100644 index 0000000..05c798b --- /dev/null +++ b/Reasoning-Llama-3.2-3B-Math-Instruct-RE1-ORPO-align.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c95c757cf05718b6565fac10c78823b62cbf72afe769c842556b98efd845d17 +size 1815353792 diff --git a/Reasoning-Llama-3.2-3B-Math-Instruct-RE1-ORPO-align.Q3_K_M.gguf b/Reasoning-Llama-3.2-3B-Math-Instruct-RE1-ORPO-align.Q3_K_M.gguf new file mode 100644 index 0000000..60b8370 --- /dev/null +++ b/Reasoning-Llama-3.2-3B-Math-Instruct-RE1-ORPO-align.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8804a32d73a1a8f238b8f1e96f47160d01dbbc079da71ccc75a29f0d98cd69f +size 1687165376 diff --git a/Reasoning-Llama-3.2-3B-Math-Instruct-RE1-ORPO-align.Q3_K_S.gguf b/Reasoning-Llama-3.2-3B-Math-Instruct-RE1-ORPO-align.Q3_K_S.gguf new file mode 100644 index 0000000..8b494ac --- /dev/null +++ b/Reasoning-Llama-3.2-3B-Math-Instruct-RE1-ORPO-align.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d440be25cb76407330f4bdaf6359fa8f6e3a2cdefba255e4bfa8b49cb865e8dc +size 1542855104 diff --git a/Reasoning-Llama-3.2-3B-Math-Instruct-RE1-ORPO-align.Q4_K_M.gguf b/Reasoning-Llama-3.2-3B-Math-Instruct-RE1-ORPO-align.Q4_K_M.gguf new file mode 100644 index 0000000..d8cd280 --- /dev/null +++ b/Reasoning-Llama-3.2-3B-Math-Instruct-RE1-ORPO-align.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8621e4a501ab41bf16f753f9230fbbe4c90af03347757946413db84f341f1c63 +size 2019383744 diff --git a/Reasoning-Llama-3.2-3B-Math-Instruct-RE1-ORPO-align.Q4_K_S.gguf b/Reasoning-Llama-3.2-3B-Math-Instruct-RE1-ORPO-align.Q4_K_S.gguf new file mode 100644 index 0000000..75cc1f8 --- /dev/null +++ b/Reasoning-Llama-3.2-3B-Math-Instruct-RE1-ORPO-align.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d24fdc95574315e2ae8fa106dd7b747ecc2f81d1533b0e020222b3e8f1af22c +size 1928206784 diff --git a/Reasoning-Llama-3.2-3B-Math-Instruct-RE1-ORPO-align.Q5_K_M.gguf b/Reasoning-Llama-3.2-3B-Math-Instruct-RE1-ORPO-align.Q5_K_M.gguf new file mode 100644 index 0000000..de8c8bb --- /dev/null +++ b/Reasoning-Llama-3.2-3B-Math-Instruct-RE1-ORPO-align.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7cbbb3c6b7e10ba2ea81e2ba0c3ad574ca5785220a3dd5d07936e734fed07a9e +size 2322160064 diff --git a/Reasoning-Llama-3.2-3B-Math-Instruct-RE1-ORPO-align.Q5_K_S.gguf b/Reasoning-Llama-3.2-3B-Math-Instruct-RE1-ORPO-align.Q5_K_S.gguf new file mode 100644 index 0000000..829da3b --- /dev/null +++ b/Reasoning-Llama-3.2-3B-Math-Instruct-RE1-ORPO-align.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab20c67b210de2fa012ccfbbacb2c29df22e4a9015e0cda325d6c41cf0d05a9f +size 2269518272 diff --git a/Reasoning-Llama-3.2-3B-Math-Instruct-RE1-ORPO-align.Q6_K.gguf b/Reasoning-Llama-3.2-3B-Math-Instruct-RE1-ORPO-align.Q6_K.gguf new file mode 100644 index 0000000..6ed68b0 --- /dev/null +++ b/Reasoning-Llama-3.2-3B-Math-Instruct-RE1-ORPO-align.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5fa710be158cccf86259def5a94d7180039f87711c6c4959db5683e406c8d92 +size 2643859904 diff --git a/Reasoning-Llama-3.2-3B-Math-Instruct-RE1-ORPO-align.Q8_0.gguf b/Reasoning-Llama-3.2-3B-Math-Instruct-RE1-ORPO-align.Q8_0.gguf new file mode 100644 index 0000000..ea5404d --- /dev/null +++ b/Reasoning-Llama-3.2-3B-Math-Instruct-RE1-ORPO-align.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:676a34133d09da47c543c3c5295788fe9abcabaadafc3c674aad19f2bd5a467f +size 3421905344 diff --git a/Reasoning-Llama-3.2-3B-Math-Instruct-RE1-ORPO-align.f16.gguf b/Reasoning-Llama-3.2-3B-Math-Instruct-RE1-ORPO-align.f16.gguf new file mode 100644 index 0000000..e2054a5 --- /dev/null +++ b/Reasoning-Llama-3.2-3B-Math-Instruct-RE1-ORPO-align.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b3195fc9bea0b5df010287b252e3f41804b0a84e89e8942d5161ea7758c2180 +size 6433694144