commit bcc234976132fdb7e03a9164c808f74603f58322 Author: ModelHub XC Date: Fri Jul 31 21:09:17 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-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a621012 --- /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.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Reasoning-Llama-3.1-CoT-RE1-NMT.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Reasoning-Llama-3.1-CoT-RE1-NMT.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Reasoning-Llama-3.1-CoT-RE1-NMT.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Reasoning-Llama-3.1-CoT-RE1-NMT.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Reasoning-Llama-3.1-CoT-RE1-NMT.f16.gguf filter=lfs diff=lfs merge=lfs -text +Reasoning-Llama-3.1-CoT-RE1-NMT.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Reasoning-Llama-3.1-CoT-RE1-NMT.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Reasoning-Llama-3.1-CoT-RE1-NMT.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Reasoning-Llama-3.1-CoT-RE1-NMT.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Reasoning-Llama-3.1-CoT-RE1-NMT.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Reasoning-Llama-3.1-CoT-RE1-NMT.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..333a60a --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: EpistemeAI/Reasoning-Llama-3.1-CoT-RE1-NMT +datasets: +- AI-MO/NuminaMath-TIR +- bespokelabs/Bespoke-Stratos-17k +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 + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Reasoning-Llama-3.1-CoT-RE1-NMT-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-GGUF/resolve/main/Reasoning-Llama-3.1-CoT-RE1-NMT.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Reasoning-Llama-3.1-CoT-RE1-NMT-GGUF/resolve/main/Reasoning-Llama-3.1-CoT-RE1-NMT.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Reasoning-Llama-3.1-CoT-RE1-NMT-GGUF/resolve/main/Reasoning-Llama-3.1-CoT-RE1-NMT.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Reasoning-Llama-3.1-CoT-RE1-NMT-GGUF/resolve/main/Reasoning-Llama-3.1-CoT-RE1-NMT.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Reasoning-Llama-3.1-CoT-RE1-NMT-GGUF/resolve/main/Reasoning-Llama-3.1-CoT-RE1-NMT.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Reasoning-Llama-3.1-CoT-RE1-NMT-GGUF/resolve/main/Reasoning-Llama-3.1-CoT-RE1-NMT.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Reasoning-Llama-3.1-CoT-RE1-NMT-GGUF/resolve/main/Reasoning-Llama-3.1-CoT-RE1-NMT.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Reasoning-Llama-3.1-CoT-RE1-NMT-GGUF/resolve/main/Reasoning-Llama-3.1-CoT-RE1-NMT.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Reasoning-Llama-3.1-CoT-RE1-NMT-GGUF/resolve/main/Reasoning-Llama-3.1-CoT-RE1-NMT.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Reasoning-Llama-3.1-CoT-RE1-NMT-GGUF/resolve/main/Reasoning-Llama-3.1-CoT-RE1-NMT.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Reasoning-Llama-3.1-CoT-RE1-NMT-GGUF/resolve/main/Reasoning-Llama-3.1-CoT-RE1-NMT.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Reasoning-Llama-3.1-CoT-RE1-NMT-GGUF/resolve/main/Reasoning-Llama-3.1-CoT-RE1-NMT.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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. + + diff --git a/Reasoning-Llama-3.1-CoT-RE1-NMT.IQ4_XS.gguf b/Reasoning-Llama-3.1-CoT-RE1-NMT.IQ4_XS.gguf new file mode 100644 index 0000000..ee9c205 --- /dev/null +++ b/Reasoning-Llama-3.1-CoT-RE1-NMT.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5459d396269bb198474a1afdc8f99d9aab5655a022f0b0d2719cecc924f3a086 +size 4484368448 diff --git a/Reasoning-Llama-3.1-CoT-RE1-NMT.Q2_K.gguf b/Reasoning-Llama-3.1-CoT-RE1-NMT.Q2_K.gguf new file mode 100644 index 0000000..344fe6a --- /dev/null +++ b/Reasoning-Llama-3.1-CoT-RE1-NMT.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1e4eb660b679a49d4f196d61495ab68c4a62e3506773608e22c6fa90c2d9dc6 +size 3179137088 diff --git a/Reasoning-Llama-3.1-CoT-RE1-NMT.Q3_K_L.gguf b/Reasoning-Llama-3.1-CoT-RE1-NMT.Q3_K_L.gguf new file mode 100644 index 0000000..3edf404 --- /dev/null +++ b/Reasoning-Llama-3.1-CoT-RE1-NMT.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9a6beb8da4a63d38f97455f1b4f27718abf25372033db804ab1ad213b4e06ba +size 4321962048 diff --git a/Reasoning-Llama-3.1-CoT-RE1-NMT.Q3_K_M.gguf b/Reasoning-Llama-3.1-CoT-RE1-NMT.Q3_K_M.gguf new file mode 100644 index 0000000..118de79 --- /dev/null +++ b/Reasoning-Llama-3.1-CoT-RE1-NMT.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1d7e91528847942eac64f665c82d3f80d2e2a2495b3a60e5c737ce265c2a2b2 +size 4018923584 diff --git a/Reasoning-Llama-3.1-CoT-RE1-NMT.Q3_K_S.gguf b/Reasoning-Llama-3.1-CoT-RE1-NMT.Q3_K_S.gguf new file mode 100644 index 0000000..302ba62 --- /dev/null +++ b/Reasoning-Llama-3.1-CoT-RE1-NMT.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05980eca8b53e6de42df0085ed985957c95fd84cd6405a745fb2072d39c5bea9 +size 3664504896 diff --git a/Reasoning-Llama-3.1-CoT-RE1-NMT.Q4_K_M.gguf b/Reasoning-Llama-3.1-CoT-RE1-NMT.Q4_K_M.gguf new file mode 100644 index 0000000..f3a2533 --- /dev/null +++ b/Reasoning-Llama-3.1-CoT-RE1-NMT.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7293019c044812a57e9ebcf9dab046d5e4354d12845853bec8e9826b82d0b518 +size 4920739904 diff --git a/Reasoning-Llama-3.1-CoT-RE1-NMT.Q4_K_S.gguf b/Reasoning-Llama-3.1-CoT-RE1-NMT.Q4_K_S.gguf new file mode 100644 index 0000000..52dca45 --- /dev/null +++ b/Reasoning-Llama-3.1-CoT-RE1-NMT.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a6b605c548fc766c363789ddb744e1d4f5513d440998a5023ceb7c9b29e2b301 +size 4692674624 diff --git a/Reasoning-Llama-3.1-CoT-RE1-NMT.Q5_K_M.gguf b/Reasoning-Llama-3.1-CoT-RE1-NMT.Q5_K_M.gguf new file mode 100644 index 0000000..92494ad --- /dev/null +++ b/Reasoning-Llama-3.1-CoT-RE1-NMT.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fbbcd99c322278abc71eb92cb8b51d0c9c347e7977a5b11446e0138b6aa712c6 +size 5732993088 diff --git a/Reasoning-Llama-3.1-CoT-RE1-NMT.Q5_K_S.gguf b/Reasoning-Llama-3.1-CoT-RE1-NMT.Q5_K_S.gguf new file mode 100644 index 0000000..aca77b3 --- /dev/null +++ b/Reasoning-Llama-3.1-CoT-RE1-NMT.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:396bf84a49bef7ae046ab73cbcc2592c160b617115ef4bef08f9360bd174048c +size 5599299648 diff --git a/Reasoning-Llama-3.1-CoT-RE1-NMT.Q6_K.gguf b/Reasoning-Llama-3.1-CoT-RE1-NMT.Q6_K.gguf new file mode 100644 index 0000000..c5b66ff --- /dev/null +++ b/Reasoning-Llama-3.1-CoT-RE1-NMT.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7168e874f3d818bc3ee94ca7731379df4f3b0a314c56253343e385d96c5fcee +size 6596012096 diff --git a/Reasoning-Llama-3.1-CoT-RE1-NMT.Q8_0.gguf b/Reasoning-Llama-3.1-CoT-RE1-NMT.Q8_0.gguf new file mode 100644 index 0000000..f143c4c --- /dev/null +++ b/Reasoning-Llama-3.1-CoT-RE1-NMT.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b087a4105bd9bbba66f89242e9f59efadacc481762cce17c5b5ceed2871b071a +size 8540776512 diff --git a/Reasoning-Llama-3.1-CoT-RE1-NMT.f16.gguf b/Reasoning-Llama-3.1-CoT-RE1-NMT.f16.gguf new file mode 100644 index 0000000..58e82bd --- /dev/null +++ b/Reasoning-Llama-3.1-CoT-RE1-NMT.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23411c66ac4d14711be0e7cf70233452f015709bdd06aa9e6db85428240f0370 +size 16068896832