commit f17ff9f171b7af5e17f64de6515e21d0f8934f66 Author: ModelHub XC Date: Sat Apr 11 19:30:56 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Nemo-12B-Marlin-v2-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..9e9ad35 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,49 @@ +*.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 +Nemo-12B-Marlin-v2.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Nemo-12B-Marlin-v2.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Nemo-12B-Marlin-v2.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Nemo-12B-Marlin-v2.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Nemo-12B-Marlin-v2.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Nemo-12B-Marlin-v2.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Nemo-12B-Marlin-v2.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Nemo-12B-Marlin-v2.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Nemo-12B-Marlin-v2.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Nemo-12B-Marlin-v2.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Nemo-12B-Marlin-v2.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Nemo-12B-Marlin-v2.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Nemo-12B-Marlin-v2.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Nemo-12B-Marlin-v2.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Nemo-12B-Marlin-v2.IQ3_M.gguf b/Nemo-12B-Marlin-v2.IQ3_M.gguf new file mode 100644 index 0000000..f18c7e7 --- /dev/null +++ b/Nemo-12B-Marlin-v2.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9aaa93e876a2d3401f70b9acb2122f203ecab81be7c82489a43e6573a7eb81b +size 5722233056 diff --git a/Nemo-12B-Marlin-v2.IQ3_S.gguf b/Nemo-12B-Marlin-v2.IQ3_S.gguf new file mode 100644 index 0000000..1df5a28 --- /dev/null +++ b/Nemo-12B-Marlin-v2.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4833082a566d3b602f79a0474359f29fa33739d193b8eaf76ef47310e38081a7 +size 5562079456 diff --git a/Nemo-12B-Marlin-v2.IQ3_XS.gguf b/Nemo-12B-Marlin-v2.IQ3_XS.gguf new file mode 100644 index 0000000..cda19f7 --- /dev/null +++ b/Nemo-12B-Marlin-v2.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d72709bc1331ae66f818e66daa8aac47196c27985f8a6965da7656a7b283a554 +size 5306489056 diff --git a/Nemo-12B-Marlin-v2.IQ4_XS.gguf b/Nemo-12B-Marlin-v2.IQ4_XS.gguf new file mode 100644 index 0000000..554a24b --- /dev/null +++ b/Nemo-12B-Marlin-v2.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8ed1ca65b5d27336cc32fb963b1e9c49f4fb01b39273c4e35251e5d6b13d89a +size 6800054496 diff --git a/Nemo-12B-Marlin-v2.Q2_K.gguf b/Nemo-12B-Marlin-v2.Q2_K.gguf new file mode 100644 index 0000000..829130f --- /dev/null +++ b/Nemo-12B-Marlin-v2.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc7285e0872152a180c15efac98abe09b3b988dd65b7a6251587a553fc81db90 +size 4791048416 diff --git a/Nemo-12B-Marlin-v2.Q3_K_L.gguf b/Nemo-12B-Marlin-v2.Q3_K_L.gguf new file mode 100644 index 0000000..2d69681 --- /dev/null +++ b/Nemo-12B-Marlin-v2.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2cf2513bb4e58bc357285aaed37c151c88a4283f4f35e1fdb947f95880a29734 +size 6561503456 diff --git a/Nemo-12B-Marlin-v2.Q3_K_M.gguf b/Nemo-12B-Marlin-v2.Q3_K_M.gguf new file mode 100644 index 0000000..e720e3f --- /dev/null +++ b/Nemo-12B-Marlin-v2.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b9b4d429316cbfaaa3dc3151b2fc5ed566663513f3c7de9a96ffe54e92ff5f0 +size 6083090656 diff --git a/Nemo-12B-Marlin-v2.Q3_K_S.gguf b/Nemo-12B-Marlin-v2.Q3_K_S.gguf new file mode 100644 index 0000000..4ed6f88 --- /dev/null +++ b/Nemo-12B-Marlin-v2.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8997bbdc19fb39379979fb40c160d87b87b4945d8aaf0114ccfff3e8969270d6 +size 5534226656 diff --git a/Nemo-12B-Marlin-v2.Q4_K_M.gguf b/Nemo-12B-Marlin-v2.Q4_K_M.gguf new file mode 100644 index 0000000..7e997d9 --- /dev/null +++ b/Nemo-12B-Marlin-v2.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ea5844a157fc06313c7432b2a941f8d0cd2e1282f257a697ccd9cf119340ffa +size 7477205216 diff --git a/Nemo-12B-Marlin-v2.Q4_K_S.gguf b/Nemo-12B-Marlin-v2.Q4_K_S.gguf new file mode 100644 index 0000000..39c99bd --- /dev/null +++ b/Nemo-12B-Marlin-v2.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf9090d0b14733c25639560b4d2f10896e4b58adcb31a9208cae9d19452a3a5b +size 7120197856 diff --git a/Nemo-12B-Marlin-v2.Q5_K_M.gguf b/Nemo-12B-Marlin-v2.Q5_K_M.gguf new file mode 100644 index 0000000..e8e6e15 --- /dev/null +++ b/Nemo-12B-Marlin-v2.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aeb4b40bcc6a5e06cbfebc8e220ad59a1ad30cf9ebcfda6283e6d942b33f30e5 +size 8727632096 diff --git a/Nemo-12B-Marlin-v2.Q5_K_S.gguf b/Nemo-12B-Marlin-v2.Q5_K_S.gguf new file mode 100644 index 0000000..2d08cfc --- /dev/null +++ b/Nemo-12B-Marlin-v2.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49efaa7b62884b1b55dd02856830c07b124d284373876884390027f2329fc0c6 +size 8518736096 diff --git a/Nemo-12B-Marlin-v2.Q6_K.gguf b/Nemo-12B-Marlin-v2.Q6_K.gguf new file mode 100644 index 0000000..cf67b5f --- /dev/null +++ b/Nemo-12B-Marlin-v2.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07ed261b52efee0b8e98ac391681b84c1250d7a55d5188eee0763a5b349c4538 +size 10056210656 diff --git a/Nemo-12B-Marlin-v2.Q8_0.gguf b/Nemo-12B-Marlin-v2.Q8_0.gguf new file mode 100644 index 0000000..e3a7ceb --- /dev/null +++ b/Nemo-12B-Marlin-v2.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:797cc919c1fdb5fe83608b539a36b2aac8c191489d3daff42afd8be27e2cbe7a +size 13022370016 diff --git a/README.md b/README.md new file mode 100644 index 0000000..4c157d4 --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: UsernameJustAnother/Nemo-12B-Marlin-v2 +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- mistral +- trl +--- +## About + + + + + + +static quants of https://huggingface.co/UsernameJustAnother/Nemo-12B-Marlin-v2 + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Nemo-12B-Marlin-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/Nemo-12B-Marlin-v2-GGUF/resolve/main/Nemo-12B-Marlin-v2.Q2_K.gguf) | Q2_K | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/Nemo-12B-Marlin-v2-GGUF/resolve/main/Nemo-12B-Marlin-v2.IQ3_XS.gguf) | IQ3_XS | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/Nemo-12B-Marlin-v2-GGUF/resolve/main/Nemo-12B-Marlin-v2.Q3_K_S.gguf) | Q3_K_S | 5.6 | | +| [GGUF](https://huggingface.co/mradermacher/Nemo-12B-Marlin-v2-GGUF/resolve/main/Nemo-12B-Marlin-v2.IQ3_S.gguf) | IQ3_S | 5.7 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Nemo-12B-Marlin-v2-GGUF/resolve/main/Nemo-12B-Marlin-v2.IQ3_M.gguf) | IQ3_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Nemo-12B-Marlin-v2-GGUF/resolve/main/Nemo-12B-Marlin-v2.Q3_K_M.gguf) | Q3_K_M | 6.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Nemo-12B-Marlin-v2-GGUF/resolve/main/Nemo-12B-Marlin-v2.Q3_K_L.gguf) | Q3_K_L | 6.7 | | +| [GGUF](https://huggingface.co/mradermacher/Nemo-12B-Marlin-v2-GGUF/resolve/main/Nemo-12B-Marlin-v2.IQ4_XS.gguf) | IQ4_XS | 6.9 | | +| [GGUF](https://huggingface.co/mradermacher/Nemo-12B-Marlin-v2-GGUF/resolve/main/Nemo-12B-Marlin-v2.Q4_K_S.gguf) | Q4_K_S | 7.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Nemo-12B-Marlin-v2-GGUF/resolve/main/Nemo-12B-Marlin-v2.Q4_K_M.gguf) | Q4_K_M | 7.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Nemo-12B-Marlin-v2-GGUF/resolve/main/Nemo-12B-Marlin-v2.Q5_K_S.gguf) | Q5_K_S | 8.6 | | +| [GGUF](https://huggingface.co/mradermacher/Nemo-12B-Marlin-v2-GGUF/resolve/main/Nemo-12B-Marlin-v2.Q5_K_M.gguf) | Q5_K_M | 8.8 | | +| [GGUF](https://huggingface.co/mradermacher/Nemo-12B-Marlin-v2-GGUF/resolve/main/Nemo-12B-Marlin-v2.Q6_K.gguf) | Q6_K | 10.2 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Nemo-12B-Marlin-v2-GGUF/resolve/main/Nemo-12B-Marlin-v2.Q8_0.gguf) | Q8_0 | 13.1 | fast, best quality | + +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. + +