commit 1b2acd7ab652dccb54b34665973e9fa7b2ef64fb Author: ModelHub XC Date: Tue Sep 8 09:28:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/OpenReasoner-Llama-3.2-3B-rs1.01-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..1142de4 --- /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 +OpenReasoner-Llama-3.2-3B-rs1.01.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +OpenReasoner-Llama-3.2-3B-rs1.01.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +OpenReasoner-Llama-3.2-3B-rs1.01.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +OpenReasoner-Llama-3.2-3B-rs1.01.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +OpenReasoner-Llama-3.2-3B-rs1.01.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +OpenReasoner-Llama-3.2-3B-rs1.01.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +OpenReasoner-Llama-3.2-3B-rs1.01.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +OpenReasoner-Llama-3.2-3B-rs1.01.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +OpenReasoner-Llama-3.2-3B-rs1.01.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +OpenReasoner-Llama-3.2-3B-rs1.01.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +OpenReasoner-Llama-3.2-3B-rs1.01.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +OpenReasoner-Llama-3.2-3B-rs1.01.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/OpenReasoner-Llama-3.2-3B-rs1.01.IQ4_XS.gguf b/OpenReasoner-Llama-3.2-3B-rs1.01.IQ4_XS.gguf new file mode 100644 index 0000000..508be78 --- /dev/null +++ b/OpenReasoner-Llama-3.2-3B-rs1.01.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7627809eb7b45d42bfc82a1cee38a3462e75c299e9b4198bcf55ff86677d7bab +size 1840912736 diff --git a/OpenReasoner-Llama-3.2-3B-rs1.01.Q2_K.gguf b/OpenReasoner-Llama-3.2-3B-rs1.01.Q2_K.gguf new file mode 100644 index 0000000..af41752 --- /dev/null +++ b/OpenReasoner-Llama-3.2-3B-rs1.01.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d35c1b85c1c3133b49bb3841eb05db8ad07a2720b0f83c93cb55b4546532662 +size 1363941728 diff --git a/OpenReasoner-Llama-3.2-3B-rs1.01.Q3_K_L.gguf b/OpenReasoner-Llama-3.2-3B-rs1.01.Q3_K_L.gguf new file mode 100644 index 0000000..5759ee2 --- /dev/null +++ b/OpenReasoner-Llama-3.2-3B-rs1.01.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4191c22dacd9b2756265805992fc9a243bb8dfc65552fa6e7bd1aa89fa5d7e2b +size 1815353696 diff --git a/OpenReasoner-Llama-3.2-3B-rs1.01.Q3_K_M.gguf b/OpenReasoner-Llama-3.2-3B-rs1.01.Q3_K_M.gguf new file mode 100644 index 0000000..3516f86 --- /dev/null +++ b/OpenReasoner-Llama-3.2-3B-rs1.01.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df846788ae3d1f91ee8500cd4ce93a36c8441d71cc1dcc1fe02b994cdc932546 +size 1687165280 diff --git a/OpenReasoner-Llama-3.2-3B-rs1.01.Q3_K_S.gguf b/OpenReasoner-Llama-3.2-3B-rs1.01.Q3_K_S.gguf new file mode 100644 index 0000000..2a18437 --- /dev/null +++ b/OpenReasoner-Llama-3.2-3B-rs1.01.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27475426438024a1895ae99615bd56b001d0186825b6c654c6ef52e2743785ce +size 1542855008 diff --git a/OpenReasoner-Llama-3.2-3B-rs1.01.Q4_K_M.gguf b/OpenReasoner-Llama-3.2-3B-rs1.01.Q4_K_M.gguf new file mode 100644 index 0000000..975adef --- /dev/null +++ b/OpenReasoner-Llama-3.2-3B-rs1.01.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8d583b8ad4af6a1b56eddc63611e870c7a44cd645c7150af9eaefe9fae231f6 +size 2019383648 diff --git a/OpenReasoner-Llama-3.2-3B-rs1.01.Q4_K_S.gguf b/OpenReasoner-Llama-3.2-3B-rs1.01.Q4_K_S.gguf new file mode 100644 index 0000000..dd6b48f --- /dev/null +++ b/OpenReasoner-Llama-3.2-3B-rs1.01.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0bead487203f09ce2cea310c3d78fe52119bf1ab75ebd725e335d300006dfa8 +size 1928206688 diff --git a/OpenReasoner-Llama-3.2-3B-rs1.01.Q5_K_M.gguf b/OpenReasoner-Llama-3.2-3B-rs1.01.Q5_K_M.gguf new file mode 100644 index 0000000..fec2f01 --- /dev/null +++ b/OpenReasoner-Llama-3.2-3B-rs1.01.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42f2db0db1e19a9858a6e4127cf7b2ac04fad5801b09d2a806e9dcfe27aeee94 +size 2322159968 diff --git a/OpenReasoner-Llama-3.2-3B-rs1.01.Q5_K_S.gguf b/OpenReasoner-Llama-3.2-3B-rs1.01.Q5_K_S.gguf new file mode 100644 index 0000000..e1f9399 --- /dev/null +++ b/OpenReasoner-Llama-3.2-3B-rs1.01.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b3830beb56aa45d164254d6b9108cff714cd21c599dbd6cfb9d247404ff6fc6 +size 2269518176 diff --git a/OpenReasoner-Llama-3.2-3B-rs1.01.Q6_K.gguf b/OpenReasoner-Llama-3.2-3B-rs1.01.Q6_K.gguf new file mode 100644 index 0000000..65cd61b --- /dev/null +++ b/OpenReasoner-Llama-3.2-3B-rs1.01.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc034a6571723205792fa2b445c6ad627a549dfb008f97c3e87d0d4a2d03dca5 +size 2643859808 diff --git a/OpenReasoner-Llama-3.2-3B-rs1.01.Q8_0.gguf b/OpenReasoner-Llama-3.2-3B-rs1.01.Q8_0.gguf new file mode 100644 index 0000000..4f0ea77 --- /dev/null +++ b/OpenReasoner-Llama-3.2-3B-rs1.01.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e81a6c85977531b6f0e42fdd5bbc5d4630e99c8258c1bf91e60c5647bff055cb +size 3421905248 diff --git a/OpenReasoner-Llama-3.2-3B-rs1.01.f16.gguf b/OpenReasoner-Llama-3.2-3B-rs1.01.f16.gguf new file mode 100644 index 0000000..239d514 --- /dev/null +++ b/OpenReasoner-Llama-3.2-3B-rs1.01.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73722cf51a804bc9682fbcf3c2a46107c568ce78b8645fa2c9b36bd67244f093 +size 6433694048 diff --git a/README.md b/README.md new file mode 100644 index 0000000..fffb4d4 --- /dev/null +++ b/README.md @@ -0,0 +1,70 @@ +--- +base_model: EpistemeAI/OpenReason-Llama-3.2-3B-rs1.01 +language: +- en +library_name: transformers +license: llama3.2 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- trl +--- +## About + + + + + + +static quants of https://huggingface.co/EpistemeAI/OpenReason-Llama-3.2-3B-rs1.01 + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/OpenReasoner-Llama-3.2-3B-rs1.01-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/OpenReasoner-Llama-3.2-3B-rs1.01-GGUF/resolve/main/OpenReasoner-Llama-3.2-3B-rs1.01.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/OpenReasoner-Llama-3.2-3B-rs1.01-GGUF/resolve/main/OpenReasoner-Llama-3.2-3B-rs1.01.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/OpenReasoner-Llama-3.2-3B-rs1.01-GGUF/resolve/main/OpenReasoner-Llama-3.2-3B-rs1.01.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/OpenReasoner-Llama-3.2-3B-rs1.01-GGUF/resolve/main/OpenReasoner-Llama-3.2-3B-rs1.01.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/OpenReasoner-Llama-3.2-3B-rs1.01-GGUF/resolve/main/OpenReasoner-Llama-3.2-3B-rs1.01.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/OpenReasoner-Llama-3.2-3B-rs1.01-GGUF/resolve/main/OpenReasoner-Llama-3.2-3B-rs1.01.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/OpenReasoner-Llama-3.2-3B-rs1.01-GGUF/resolve/main/OpenReasoner-Llama-3.2-3B-rs1.01.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/OpenReasoner-Llama-3.2-3B-rs1.01-GGUF/resolve/main/OpenReasoner-Llama-3.2-3B-rs1.01.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/OpenReasoner-Llama-3.2-3B-rs1.01-GGUF/resolve/main/OpenReasoner-Llama-3.2-3B-rs1.01.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/OpenReasoner-Llama-3.2-3B-rs1.01-GGUF/resolve/main/OpenReasoner-Llama-3.2-3B-rs1.01.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/OpenReasoner-Llama-3.2-3B-rs1.01-GGUF/resolve/main/OpenReasoner-Llama-3.2-3B-rs1.01.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/OpenReasoner-Llama-3.2-3B-rs1.01-GGUF/resolve/main/OpenReasoner-Llama-3.2-3B-rs1.01.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. + +