commit ed517503223ae4bb5a47b7aa898d880708ecc7a2 Author: ModelHub XC Date: Wed Jul 8 17:44:10 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-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..60eee68 --- /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.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Reasoning-Llama-3.1-CoT-RE1-NMT-V2.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Reasoning-Llama-3.1-CoT-RE1-NMT-V2.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Reasoning-Llama-3.1-CoT-RE1-NMT-V2.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Reasoning-Llama-3.1-CoT-RE1-NMT-V2.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Reasoning-Llama-3.1-CoT-RE1-NMT-V2.f16.gguf filter=lfs diff=lfs merge=lfs -text +Reasoning-Llama-3.1-CoT-RE1-NMT-V2.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Reasoning-Llama-3.1-CoT-RE1-NMT-V2.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Reasoning-Llama-3.1-CoT-RE1-NMT-V2.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Reasoning-Llama-3.1-CoT-RE1-NMT-V2.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Reasoning-Llama-3.1-CoT-RE1-NMT-V2.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Reasoning-Llama-3.1-CoT-RE1-NMT-V2.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..92ae966 --- /dev/null +++ b/README.md @@ -0,0 +1,70 @@ +--- +base_model: EpistemeAI/Reasoning-Llama-3.1-CoT-RE1-NMT-V2 +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 + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Reasoning-Llama-3.1-CoT-RE1-NMT-V2-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-GGUF/resolve/main/Reasoning-Llama-3.1-CoT-RE1-NMT-V2.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Reasoning-Llama-3.1-CoT-RE1-NMT-V2-GGUF/resolve/main/Reasoning-Llama-3.1-CoT-RE1-NMT-V2.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Reasoning-Llama-3.1-CoT-RE1-NMT-V2-GGUF/resolve/main/Reasoning-Llama-3.1-CoT-RE1-NMT-V2.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Reasoning-Llama-3.1-CoT-RE1-NMT-V2-GGUF/resolve/main/Reasoning-Llama-3.1-CoT-RE1-NMT-V2.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Reasoning-Llama-3.1-CoT-RE1-NMT-V2-GGUF/resolve/main/Reasoning-Llama-3.1-CoT-RE1-NMT-V2.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Reasoning-Llama-3.1-CoT-RE1-NMT-V2-GGUF/resolve/main/Reasoning-Llama-3.1-CoT-RE1-NMT-V2.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Reasoning-Llama-3.1-CoT-RE1-NMT-V2-GGUF/resolve/main/Reasoning-Llama-3.1-CoT-RE1-NMT-V2.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Reasoning-Llama-3.1-CoT-RE1-NMT-V2-GGUF/resolve/main/Reasoning-Llama-3.1-CoT-RE1-NMT-V2.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Reasoning-Llama-3.1-CoT-RE1-NMT-V2-GGUF/resolve/main/Reasoning-Llama-3.1-CoT-RE1-NMT-V2.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Reasoning-Llama-3.1-CoT-RE1-NMT-V2-GGUF/resolve/main/Reasoning-Llama-3.1-CoT-RE1-NMT-V2.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Reasoning-Llama-3.1-CoT-RE1-NMT-V2-GGUF/resolve/main/Reasoning-Llama-3.1-CoT-RE1-NMT-V2.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Reasoning-Llama-3.1-CoT-RE1-NMT-V2-GGUF/resolve/main/Reasoning-Llama-3.1-CoT-RE1-NMT-V2.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-V2.IQ4_XS.gguf b/Reasoning-Llama-3.1-CoT-RE1-NMT-V2.IQ4_XS.gguf new file mode 100644 index 0000000..d9d9226 --- /dev/null +++ b/Reasoning-Llama-3.1-CoT-RE1-NMT-V2.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41cd380771823cabab0c99421338aaa13e58713522c3fbdb60be036b2c17d10b +size 4484368352 diff --git a/Reasoning-Llama-3.1-CoT-RE1-NMT-V2.Q2_K.gguf b/Reasoning-Llama-3.1-CoT-RE1-NMT-V2.Q2_K.gguf new file mode 100644 index 0000000..d7a79c7 --- /dev/null +++ b/Reasoning-Llama-3.1-CoT-RE1-NMT-V2.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7047a9e321bb35c7145cc06baa2f52f4bfaeea5353088fb849e2fb20f98a87e +size 3179136992 diff --git a/Reasoning-Llama-3.1-CoT-RE1-NMT-V2.Q3_K_L.gguf b/Reasoning-Llama-3.1-CoT-RE1-NMT-V2.Q3_K_L.gguf new file mode 100644 index 0000000..5dc92a4 --- /dev/null +++ b/Reasoning-Llama-3.1-CoT-RE1-NMT-V2.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:faa3b97b1e0e3fd0ed123ccb82fba5d06fbf2395dfeb6aaccd3bdec697ffb990 +size 4321961952 diff --git a/Reasoning-Llama-3.1-CoT-RE1-NMT-V2.Q3_K_M.gguf b/Reasoning-Llama-3.1-CoT-RE1-NMT-V2.Q3_K_M.gguf new file mode 100644 index 0000000..c4e60ff --- /dev/null +++ b/Reasoning-Llama-3.1-CoT-RE1-NMT-V2.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b67cf92775625db891393f2cff6eff4cfd826107c50b0dd5aa1635d362659275 +size 4018923488 diff --git a/Reasoning-Llama-3.1-CoT-RE1-NMT-V2.Q3_K_S.gguf b/Reasoning-Llama-3.1-CoT-RE1-NMT-V2.Q3_K_S.gguf new file mode 100644 index 0000000..0d0c1f2 --- /dev/null +++ b/Reasoning-Llama-3.1-CoT-RE1-NMT-V2.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:574cf2ab6023c597038c4d4a139c316e32e5896bae0a41712a1c63fb4a63ea37 +size 3664504800 diff --git a/Reasoning-Llama-3.1-CoT-RE1-NMT-V2.Q4_K_M.gguf b/Reasoning-Llama-3.1-CoT-RE1-NMT-V2.Q4_K_M.gguf new file mode 100644 index 0000000..ccf4e3b --- /dev/null +++ b/Reasoning-Llama-3.1-CoT-RE1-NMT-V2.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a62750b5e6b178dac2237425f40e4958d2aa5ee322acf1a2b6b059020d63a8a +size 4920739808 diff --git a/Reasoning-Llama-3.1-CoT-RE1-NMT-V2.Q4_K_S.gguf b/Reasoning-Llama-3.1-CoT-RE1-NMT-V2.Q4_K_S.gguf new file mode 100644 index 0000000..167f242 --- /dev/null +++ b/Reasoning-Llama-3.1-CoT-RE1-NMT-V2.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c8f656806ac4a04f50f9c19e0d101ddb955c478b5682518e72536f60bb6b60d +size 4692674528 diff --git a/Reasoning-Llama-3.1-CoT-RE1-NMT-V2.Q5_K_M.gguf b/Reasoning-Llama-3.1-CoT-RE1-NMT-V2.Q5_K_M.gguf new file mode 100644 index 0000000..05847cb --- /dev/null +++ b/Reasoning-Llama-3.1-CoT-RE1-NMT-V2.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5e2c0b08b8e4a076b16d8b777bce453574bc06f7e7a11208bc7ff8905892e9b +size 5732992992 diff --git a/Reasoning-Llama-3.1-CoT-RE1-NMT-V2.Q5_K_S.gguf b/Reasoning-Llama-3.1-CoT-RE1-NMT-V2.Q5_K_S.gguf new file mode 100644 index 0000000..795d8f8 --- /dev/null +++ b/Reasoning-Llama-3.1-CoT-RE1-NMT-V2.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e20a35c54d2cdf9aaa348ac1666a7d3573a4e890f3602f5c08aca32a7e4cd56d +size 5599299552 diff --git a/Reasoning-Llama-3.1-CoT-RE1-NMT-V2.Q6_K.gguf b/Reasoning-Llama-3.1-CoT-RE1-NMT-V2.Q6_K.gguf new file mode 100644 index 0000000..bf41ac6 --- /dev/null +++ b/Reasoning-Llama-3.1-CoT-RE1-NMT-V2.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65c19e449c79f1813624e31a2461fa137c744c95368930fb1b9335b7f7c33b86 +size 6596012000 diff --git a/Reasoning-Llama-3.1-CoT-RE1-NMT-V2.Q8_0.gguf b/Reasoning-Llama-3.1-CoT-RE1-NMT-V2.Q8_0.gguf new file mode 100644 index 0000000..2168292 --- /dev/null +++ b/Reasoning-Llama-3.1-CoT-RE1-NMT-V2.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:320f494c80a7253c13311a0b0b799a9db5b38f092e63c18ff2ce6739f1032fa7 +size 8540776416 diff --git a/Reasoning-Llama-3.1-CoT-RE1-NMT-V2.f16.gguf b/Reasoning-Llama-3.1-CoT-RE1-NMT-V2.f16.gguf new file mode 100644 index 0000000..542cf24 --- /dev/null +++ b/Reasoning-Llama-3.1-CoT-RE1-NMT-V2.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:477bedf3bd5047a889070f0cc8955c677704933a3f8196f5844dcfc9390be79c +size 16068896736