commit 50f1f245fffd116152687348dc2a79b027a3e652 Author: ModelHub XC Date: Fri Jul 10 23:37:14 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Reasoning-Llama-3.1-CoT-RE1-NMT-V2-ORPO-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..edc2444 --- /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-3.1-CoT-RE1-NMT-V2-ORPO.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Reasoning-Llama-3.1-CoT-RE1-NMT-V2-ORPO.f16.gguf filter=lfs diff=lfs merge=lfs -text +Reasoning-Llama-3.1-CoT-RE1-NMT-V2-ORPO.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Reasoning-Llama-3.1-CoT-RE1-NMT-V2-ORPO.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Reasoning-Llama-3.1-CoT-RE1-NMT-V2-ORPO.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Reasoning-Llama-3.1-CoT-RE1-NMT-V2-ORPO.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Reasoning-Llama-3.1-CoT-RE1-NMT-V2-ORPO.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Reasoning-Llama-3.1-CoT-RE1-NMT-V2-ORPO.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Reasoning-Llama-3.1-CoT-RE1-NMT-V2-ORPO.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Reasoning-Llama-3.1-CoT-RE1-NMT-V2-ORPO.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Reasoning-Llama-3.1-CoT-RE1-NMT-V2-ORPO.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Reasoning-Llama-3.1-CoT-RE1-NMT-V2-ORPO.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..6c85eed --- /dev/null +++ b/README.md @@ -0,0 +1,70 @@ +--- +base_model: EpistemeAI/Reasoning-Llama-3.1-CoT-RE1-NMT-V2-ORPO +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-3.1-CoT-RE1-NMT-V2-ORPO + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Reasoning-Llama-3.1-CoT-RE1-NMT-V2-ORPO-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-3.1-CoT-RE1-NMT-V2-ORPO-GGUF/resolve/main/Reasoning-Llama-3.1-CoT-RE1-NMT-V2-ORPO.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Reasoning-Llama-3.1-CoT-RE1-NMT-V2-ORPO-GGUF/resolve/main/Reasoning-Llama-3.1-CoT-RE1-NMT-V2-ORPO.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Reasoning-Llama-3.1-CoT-RE1-NMT-V2-ORPO-GGUF/resolve/main/Reasoning-Llama-3.1-CoT-RE1-NMT-V2-ORPO.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Reasoning-Llama-3.1-CoT-RE1-NMT-V2-ORPO-GGUF/resolve/main/Reasoning-Llama-3.1-CoT-RE1-NMT-V2-ORPO.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Reasoning-Llama-3.1-CoT-RE1-NMT-V2-ORPO-GGUF/resolve/main/Reasoning-Llama-3.1-CoT-RE1-NMT-V2-ORPO.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Reasoning-Llama-3.1-CoT-RE1-NMT-V2-ORPO-GGUF/resolve/main/Reasoning-Llama-3.1-CoT-RE1-NMT-V2-ORPO.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Reasoning-Llama-3.1-CoT-RE1-NMT-V2-ORPO-GGUF/resolve/main/Reasoning-Llama-3.1-CoT-RE1-NMT-V2-ORPO.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Reasoning-Llama-3.1-CoT-RE1-NMT-V2-ORPO-GGUF/resolve/main/Reasoning-Llama-3.1-CoT-RE1-NMT-V2-ORPO.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Reasoning-Llama-3.1-CoT-RE1-NMT-V2-ORPO-GGUF/resolve/main/Reasoning-Llama-3.1-CoT-RE1-NMT-V2-ORPO.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Reasoning-Llama-3.1-CoT-RE1-NMT-V2-ORPO-GGUF/resolve/main/Reasoning-Llama-3.1-CoT-RE1-NMT-V2-ORPO.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Reasoning-Llama-3.1-CoT-RE1-NMT-V2-ORPO-GGUF/resolve/main/Reasoning-Llama-3.1-CoT-RE1-NMT-V2-ORPO.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Reasoning-Llama-3.1-CoT-RE1-NMT-V2-ORPO-GGUF/resolve/main/Reasoning-Llama-3.1-CoT-RE1-NMT-V2-ORPO.f16.gguf) | f16 | 16.2 | 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-3.1-CoT-RE1-NMT-V2-ORPO.IQ4_XS.gguf b/Reasoning-Llama-3.1-CoT-RE1-NMT-V2-ORPO.IQ4_XS.gguf new file mode 100644 index 0000000..caa7a8c --- /dev/null +++ b/Reasoning-Llama-3.1-CoT-RE1-NMT-V2-ORPO.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c7c5283ffcf9c0aea60be56948f7f69b9d5bd4017c2b10db1bbc1b620e9c3ee4 +size 4484368320 diff --git a/Reasoning-Llama-3.1-CoT-RE1-NMT-V2-ORPO.Q2_K.gguf b/Reasoning-Llama-3.1-CoT-RE1-NMT-V2-ORPO.Q2_K.gguf new file mode 100644 index 0000000..8f6f417 --- /dev/null +++ b/Reasoning-Llama-3.1-CoT-RE1-NMT-V2-ORPO.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b02ae737b01357a3fa0f83637dc39ec25b492418d0713ab50591c9c41b4d16d9 +size 3179136960 diff --git a/Reasoning-Llama-3.1-CoT-RE1-NMT-V2-ORPO.Q3_K_L.gguf b/Reasoning-Llama-3.1-CoT-RE1-NMT-V2-ORPO.Q3_K_L.gguf new file mode 100644 index 0000000..9a7e57c --- /dev/null +++ b/Reasoning-Llama-3.1-CoT-RE1-NMT-V2-ORPO.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac2a34ac125e703212fb6964092b44b7c58cbe3dac40618c9207871a696784ab +size 4321961920 diff --git a/Reasoning-Llama-3.1-CoT-RE1-NMT-V2-ORPO.Q3_K_M.gguf b/Reasoning-Llama-3.1-CoT-RE1-NMT-V2-ORPO.Q3_K_M.gguf new file mode 100644 index 0000000..3a679c5 --- /dev/null +++ b/Reasoning-Llama-3.1-CoT-RE1-NMT-V2-ORPO.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:87b5575b63e6be1528e75d076f0e5c37e5a60aa6d0492179d36f7fb818fa59fc +size 4018923456 diff --git a/Reasoning-Llama-3.1-CoT-RE1-NMT-V2-ORPO.Q3_K_S.gguf b/Reasoning-Llama-3.1-CoT-RE1-NMT-V2-ORPO.Q3_K_S.gguf new file mode 100644 index 0000000..5ad63df --- /dev/null +++ b/Reasoning-Llama-3.1-CoT-RE1-NMT-V2-ORPO.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:feec9c7e5114d00ec7a0aa651b021f986d9a42f5a415a8c71447e75f07488730 +size 3664504768 diff --git a/Reasoning-Llama-3.1-CoT-RE1-NMT-V2-ORPO.Q4_K_M.gguf b/Reasoning-Llama-3.1-CoT-RE1-NMT-V2-ORPO.Q4_K_M.gguf new file mode 100644 index 0000000..d02e0b7 --- /dev/null +++ b/Reasoning-Llama-3.1-CoT-RE1-NMT-V2-ORPO.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aafe5378534ccb32a5fb3d06834c0171788864d6798403dce996ebfb70bbc6e1 +size 4920739776 diff --git a/Reasoning-Llama-3.1-CoT-RE1-NMT-V2-ORPO.Q4_K_S.gguf b/Reasoning-Llama-3.1-CoT-RE1-NMT-V2-ORPO.Q4_K_S.gguf new file mode 100644 index 0000000..5b82c27 --- /dev/null +++ b/Reasoning-Llama-3.1-CoT-RE1-NMT-V2-ORPO.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:741760d9f805eed419e2475ffc78a8684e9a3a848f650edb4964024d3f4a97f5 +size 4692674496 diff --git a/Reasoning-Llama-3.1-CoT-RE1-NMT-V2-ORPO.Q5_K_M.gguf b/Reasoning-Llama-3.1-CoT-RE1-NMT-V2-ORPO.Q5_K_M.gguf new file mode 100644 index 0000000..de07b57 --- /dev/null +++ b/Reasoning-Llama-3.1-CoT-RE1-NMT-V2-ORPO.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fda12eb959bd9a902066a140d79995b9dbdd99bef8a32455b6eccd2eec258f31 +size 5732992960 diff --git a/Reasoning-Llama-3.1-CoT-RE1-NMT-V2-ORPO.Q5_K_S.gguf b/Reasoning-Llama-3.1-CoT-RE1-NMT-V2-ORPO.Q5_K_S.gguf new file mode 100644 index 0000000..9b140f4 --- /dev/null +++ b/Reasoning-Llama-3.1-CoT-RE1-NMT-V2-ORPO.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79501db6785d456ee2e7ab125bf1f2d6e86f63fccc5843751ce50f8303f05069 +size 5599299520 diff --git a/Reasoning-Llama-3.1-CoT-RE1-NMT-V2-ORPO.Q6_K.gguf b/Reasoning-Llama-3.1-CoT-RE1-NMT-V2-ORPO.Q6_K.gguf new file mode 100644 index 0000000..8e1acda --- /dev/null +++ b/Reasoning-Llama-3.1-CoT-RE1-NMT-V2-ORPO.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9fd6d38d4912f0c05042d0d8e48ddba550cb967c7535989a032d8db7fd5f55d +size 6596011968 diff --git a/Reasoning-Llama-3.1-CoT-RE1-NMT-V2-ORPO.Q8_0.gguf b/Reasoning-Llama-3.1-CoT-RE1-NMT-V2-ORPO.Q8_0.gguf new file mode 100644 index 0000000..e93950b --- /dev/null +++ b/Reasoning-Llama-3.1-CoT-RE1-NMT-V2-ORPO.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f30b43fcc6955965471cda1b22e50f894876e8f8b06fea5b827fcc1b95494b7b +size 8540776384 diff --git a/Reasoning-Llama-3.1-CoT-RE1-NMT-V2-ORPO.f16.gguf b/Reasoning-Llama-3.1-CoT-RE1-NMT-V2-ORPO.f16.gguf new file mode 100644 index 0000000..df2cdfe --- /dev/null +++ b/Reasoning-Llama-3.1-CoT-RE1-NMT-V2-ORPO.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52f4942513588d0a54d85045adcbe96b5434d6d87bd96ad322021d081e56a140 +size 16068896704