commit 557529427f2672ece979b1171c644c7245c49579 Author: ModelHub XC Date: Mon Sep 28 23:19:14 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: bartowski/nvidia_OpenMath-Nemotron-1.5B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..53d7257 --- /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 +*.bin.* filter=lfs diff=lfs merge=lfs -text +*.bz2 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 +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack 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 +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +saved_model/**/* 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 +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zstandard filter=lfs diff=lfs merge=lfs -text +*.tfevents* filter=lfs diff=lfs merge=lfs -text +*.db* filter=lfs diff=lfs merge=lfs -text +*.ark* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.gguf* filter=lfs diff=lfs merge=lfs -text +*.ggml filter=lfs diff=lfs merge=lfs -text +*.llamafile* filter=lfs diff=lfs merge=lfs -text +*.pt2 filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text \ No newline at end of file diff --git a/README.md b/README.md new file mode 100644 index 0000000..cec97ee --- /dev/null +++ b/README.md @@ -0,0 +1,178 @@ +--- +quantized_by: bartowski +pipeline_tag: text-generation +datasets: +- nvidia/OpenMathReasoning +language: +- en +license: cc-by-4.0 +tags: +- nvidia +- math +base_model: nvidia/OpenMath-Nemotron-1.5B +base_model_relation: quantized +--- + +## Llamacpp imatrix Quantizations of OpenMath-Nemotron-1.5B by nvidia + +Using llama.cpp release b5192 for quantization. + +Original model: https://huggingface.co/nvidia/OpenMath-Nemotron-1.5B + +All quants made using imatrix option with dataset from [here](https://gist.github.com/bartowski1182/eb213dccb3571f863da82e99418f81e8) + +Run them in [LM Studio](https://lmstudio.ai/) + +Run them directly with [llama.cpp](https://github.com/ggerganov/llama.cpp), or any other llama.cpp based project + +## Prompt format + +``` +<|im_start|>system +{system_prompt}<|im_end|> +<|im_start|>user +{prompt}<|im_end|> +<|im_start|>assistant +``` + +## Download a file (not the whole branch) from below: + +| Filename | Quant type | File Size | Split | Description | +| -------- | ---------- | --------- | ----- | ----------- | +| [OpenMath-Nemotron-1.5B-bf16.gguf](https://huggingface.co/bartowski/nvidia_OpenMath-Nemotron-1.5B-GGUF/blob/main/nvidia_OpenMath-Nemotron-1.5B-bf16.gguf) | bf16 | 3.09GB | false | Full BF16 weights. | +| [OpenMath-Nemotron-1.5B-Q8_0.gguf](https://huggingface.co/bartowski/nvidia_OpenMath-Nemotron-1.5B-GGUF/blob/main/nvidia_OpenMath-Nemotron-1.5B-Q8_0.gguf) | Q8_0 | 1.65GB | false | Extremely high quality, generally unneeded but max available quant. | +| [OpenMath-Nemotron-1.5B-Q6_K_L.gguf](https://huggingface.co/bartowski/nvidia_OpenMath-Nemotron-1.5B-GGUF/blob/main/nvidia_OpenMath-Nemotron-1.5B-Q6_K_L.gguf) | Q6_K_L | 1.33GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. | +| [OpenMath-Nemotron-1.5B-Q6_K.gguf](https://huggingface.co/bartowski/nvidia_OpenMath-Nemotron-1.5B-GGUF/blob/main/nvidia_OpenMath-Nemotron-1.5B-Q6_K.gguf) | Q6_K | 1.27GB | false | Very high quality, near perfect, *recommended*. | +| [OpenMath-Nemotron-1.5B-Q5_K_L.gguf](https://huggingface.co/bartowski/nvidia_OpenMath-Nemotron-1.5B-GGUF/blob/main/nvidia_OpenMath-Nemotron-1.5B-Q5_K_L.gguf) | Q5_K_L | 1.18GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. | +| [OpenMath-Nemotron-1.5B-Q5_K_M.gguf](https://huggingface.co/bartowski/nvidia_OpenMath-Nemotron-1.5B-GGUF/blob/main/nvidia_OpenMath-Nemotron-1.5B-Q5_K_M.gguf) | Q5_K_M | 1.13GB | false | High quality, *recommended*. | +| [OpenMath-Nemotron-1.5B-Q5_K_S.gguf](https://huggingface.co/bartowski/nvidia_OpenMath-Nemotron-1.5B-GGUF/blob/main/nvidia_OpenMath-Nemotron-1.5B-Q5_K_S.gguf) | Q5_K_S | 1.10GB | false | High quality, *recommended*. | +| [OpenMath-Nemotron-1.5B-Q4_K_L.gguf](https://huggingface.co/bartowski/nvidia_OpenMath-Nemotron-1.5B-GGUF/blob/main/nvidia_OpenMath-Nemotron-1.5B-Q4_K_L.gguf) | Q4_K_L | 1.04GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. | +| [OpenMath-Nemotron-1.5B-Q4_1.gguf](https://huggingface.co/bartowski/nvidia_OpenMath-Nemotron-1.5B-GGUF/blob/main/nvidia_OpenMath-Nemotron-1.5B-Q4_1.gguf) | Q4_1 | 1.02GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. | +| [OpenMath-Nemotron-1.5B-Q4_K_M.gguf](https://huggingface.co/bartowski/nvidia_OpenMath-Nemotron-1.5B-GGUF/blob/main/nvidia_OpenMath-Nemotron-1.5B-Q4_K_M.gguf) | Q4_K_M | 0.99GB | false | Good quality, default size for most use cases, *recommended*. | +| [OpenMath-Nemotron-1.5B-Q4_K_S.gguf](https://huggingface.co/bartowski/nvidia_OpenMath-Nemotron-1.5B-GGUF/blob/main/nvidia_OpenMath-Nemotron-1.5B-Q4_K_S.gguf) | Q4_K_S | 0.94GB | false | Slightly lower quality with more space savings, *recommended*. | +| [OpenMath-Nemotron-1.5B-Q4_0.gguf](https://huggingface.co/bartowski/nvidia_OpenMath-Nemotron-1.5B-GGUF/blob/main/nvidia_OpenMath-Nemotron-1.5B-Q4_0.gguf) | Q4_0 | 0.94GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. | +| [OpenMath-Nemotron-1.5B-IQ4_NL.gguf](https://huggingface.co/bartowski/nvidia_OpenMath-Nemotron-1.5B-GGUF/blob/main/nvidia_OpenMath-Nemotron-1.5B-IQ4_NL.gguf) | IQ4_NL | 0.94GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. | +| [OpenMath-Nemotron-1.5B-Q3_K_XL.gguf](https://huggingface.co/bartowski/nvidia_OpenMath-Nemotron-1.5B-GGUF/blob/main/nvidia_OpenMath-Nemotron-1.5B-Q3_K_XL.gguf) | Q3_K_XL | 0.94GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. | +| [OpenMath-Nemotron-1.5B-IQ4_XS.gguf](https://huggingface.co/bartowski/nvidia_OpenMath-Nemotron-1.5B-GGUF/blob/main/nvidia_OpenMath-Nemotron-1.5B-IQ4_XS.gguf) | IQ4_XS | 0.90GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. | +| [OpenMath-Nemotron-1.5B-Q3_K_L.gguf](https://huggingface.co/bartowski/nvidia_OpenMath-Nemotron-1.5B-GGUF/blob/main/nvidia_OpenMath-Nemotron-1.5B-Q3_K_L.gguf) | Q3_K_L | 0.88GB | false | Lower quality but usable, good for low RAM availability. | +| [OpenMath-Nemotron-1.5B-Q3_K_M.gguf](https://huggingface.co/bartowski/nvidia_OpenMath-Nemotron-1.5B-GGUF/blob/main/nvidia_OpenMath-Nemotron-1.5B-Q3_K_M.gguf) | Q3_K_M | 0.82GB | false | Low quality. | +| [OpenMath-Nemotron-1.5B-IQ3_M.gguf](https://huggingface.co/bartowski/nvidia_OpenMath-Nemotron-1.5B-GGUF/blob/main/nvidia_OpenMath-Nemotron-1.5B-IQ3_M.gguf) | IQ3_M | 0.78GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. | +| [OpenMath-Nemotron-1.5B-Q3_K_S.gguf](https://huggingface.co/bartowski/nvidia_OpenMath-Nemotron-1.5B-GGUF/blob/main/nvidia_OpenMath-Nemotron-1.5B-Q3_K_S.gguf) | Q3_K_S | 0.76GB | false | Low quality, not recommended. | +| [OpenMath-Nemotron-1.5B-IQ3_XS.gguf](https://huggingface.co/bartowski/nvidia_OpenMath-Nemotron-1.5B-GGUF/blob/main/nvidia_OpenMath-Nemotron-1.5B-IQ3_XS.gguf) | IQ3_XS | 0.73GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. | +| [OpenMath-Nemotron-1.5B-Q2_K_L.gguf](https://huggingface.co/bartowski/nvidia_OpenMath-Nemotron-1.5B-GGUF/blob/main/nvidia_OpenMath-Nemotron-1.5B-Q2_K_L.gguf) | Q2_K_L | 0.73GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. | +| [OpenMath-Nemotron-1.5B-Q2_K.gguf](https://huggingface.co/bartowski/nvidia_OpenMath-Nemotron-1.5B-GGUF/blob/main/nvidia_OpenMath-Nemotron-1.5B-Q2_K.gguf) | Q2_K | 0.68GB | false | Very low quality but surprisingly usable. | +| [OpenMath-Nemotron-1.5B-IQ3_XXS.gguf](https://huggingface.co/bartowski/nvidia_OpenMath-Nemotron-1.5B-GGUF/blob/main/nvidia_OpenMath-Nemotron-1.5B-IQ3_XXS.gguf) | IQ3_XXS | 0.67GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. | +| [OpenMath-Nemotron-1.5B-IQ2_M.gguf](https://huggingface.co/bartowski/nvidia_OpenMath-Nemotron-1.5B-GGUF/blob/main/nvidia_OpenMath-Nemotron-1.5B-IQ2_M.gguf) | IQ2_M | 0.60GB | false | Relatively low quality, uses SOTA techniques to be surprisingly usable. | + +## Embed/output weights + +Some of these quants (Q3_K_XL, Q4_K_L etc) are the standard quantization method with the embeddings and output weights quantized to Q8_0 instead of what they would normally default to. + +## Downloading using huggingface-cli + +
+ Click to view download instructions + +First, make sure you have hugginface-cli installed: + +``` +pip install -U "huggingface_hub[cli]" +``` + +Then, you can target the specific file you want: + +``` +huggingface-cli download bartowski/nvidia_OpenMath-Nemotron-1.5B-GGUF --include "nvidia_OpenMath-Nemotron-1.5B-Q4_K_M.gguf" --local-dir ./ +``` + +If the model is bigger than 50GB, it will have been split into multiple files. In order to download them all to a local folder, run: + +``` +huggingface-cli download bartowski/nvidia_OpenMath-Nemotron-1.5B-GGUF --include "nvidia_OpenMath-Nemotron-1.5B-Q8_0/*" --local-dir ./ +``` + +You can either specify a new local-dir (nvidia_OpenMath-Nemotron-1.5B-Q8_0) or download them all in place (./) + +
+ +## ARM/AVX information + +Previously, you would download Q4_0_4_4/4_8/8_8, and these would have their weights interleaved in memory in order to improve performance on ARM and AVX machines by loading up more data in one pass. + +Now, however, there is something called "online repacking" for weights. details in [this PR](https://github.com/ggerganov/llama.cpp/pull/9921). If you use Q4_0 and your hardware would benefit from repacking weights, it will do it automatically on the fly. + +As of llama.cpp build [b4282](https://github.com/ggerganov/llama.cpp/releases/tag/b4282) you will not be able to run the Q4_0_X_X files and will instead need to use Q4_0. + +Additionally, if you want to get slightly better quality for , you can use IQ4_NL thanks to [this PR](https://github.com/ggerganov/llama.cpp/pull/10541) which will also repack the weights for ARM, though only the 4_4 for now. The loading time may be slower but it will result in an overall speed incrase. + +
+ Click to view Q4_0_X_X information (deprecated + +I'm keeping this section to show the potential theoretical uplift in performance from using the Q4_0 with online repacking. + +
+ Click to view benchmarks on an AVX2 system (EPYC7702) + +| model | size | params | backend | threads | test | t/s | % (vs Q4_0) | +| ------------------------------ | ---------: | ---------: | ---------- | ------: | ------------: | -------------------: |-------------: | +| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | pp512 | 204.03 ± 1.03 | 100% | +| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | pp1024 | 282.92 ± 0.19 | 100% | +| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | pp2048 | 259.49 ± 0.44 | 100% | +| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | tg128 | 39.12 ± 0.27 | 100% | +| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | tg256 | 39.31 ± 0.69 | 100% | +| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | tg512 | 40.52 ± 0.03 | 100% | +| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | pp512 | 301.02 ± 1.74 | 147% | +| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | pp1024 | 287.23 ± 0.20 | 101% | +| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | pp2048 | 262.77 ± 1.81 | 101% | +| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | tg128 | 18.80 ± 0.99 | 48% | +| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | tg256 | 24.46 ± 3.04 | 83% | +| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | tg512 | 36.32 ± 3.59 | 90% | +| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | pp512 | 271.71 ± 3.53 | 133% | +| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | pp1024 | 279.86 ± 45.63 | 100% | +| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | pp2048 | 320.77 ± 5.00 | 124% | +| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | tg128 | 43.51 ± 0.05 | 111% | +| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | tg256 | 43.35 ± 0.09 | 110% | +| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | tg512 | 42.60 ± 0.31 | 105% | + +Q4_0_8_8 offers a nice bump to prompt processing and a small bump to text generation + +
+ +
+ +## Which file should I choose? + +
+ Click here for details + +A great write up with charts showing various performances is provided by Artefact2 [here](https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9) + +The first thing to figure out is how big a model you can run. To do this, you'll need to figure out how much RAM and/or VRAM you have. + +If you want your model running as FAST as possible, you'll want to fit the whole thing on your GPU's VRAM. Aim for a quant with a file size 1-2GB smaller than your GPU's total VRAM. + +If you want the absolute maximum quality, add both your system RAM and your GPU's VRAM together, then similarly grab a quant with a file size 1-2GB Smaller than that total. + +Next, you'll need to decide if you want to use an 'I-quant' or a 'K-quant'. + +If you don't want to think too much, grab one of the K-quants. These are in format 'QX_K_X', like Q5_K_M. + +If you want to get more into the weeds, you can check out this extremely useful feature chart: + +[llama.cpp feature matrix](https://github.com/ggerganov/llama.cpp/wiki/Feature-matrix) + +But basically, if you're aiming for below Q4, and you're running cuBLAS (Nvidia) or rocBLAS (AMD), you should look towards the I-quants. These are in format IQX_X, like IQ3_M. These are newer and offer better performance for their size. + +These I-quants can also be used on CPU, but will be slower than their K-quant equivalent, so speed vs performance is a tradeoff you'll have to decide. + +
+ +## Credits + +Thank you kalomaze and Dampf for assistance in creating the imatrix calibration dataset. + +Thank you ZeroWw for the inspiration to experiment with embed/output. + +Thank you to LM Studio for sponsoring my work. + +Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..bbeeda1 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "text-generation", "allow_remote": true} \ No newline at end of file diff --git a/nvidia_OpenMath-Nemotron-1.5B-IQ2_M.gguf b/nvidia_OpenMath-Nemotron-1.5B-IQ2_M.gguf new file mode 100644 index 0000000..08937d4 --- /dev/null +++ b/nvidia_OpenMath-Nemotron-1.5B-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a063a056799c2e0cbeddfed298178ebfe6970661786b451c4e97b6a78fb71d8 +size 601053184 diff --git a/nvidia_OpenMath-Nemotron-1.5B-IQ3_M.gguf b/nvidia_OpenMath-Nemotron-1.5B-IQ3_M.gguf new file mode 100644 index 0000000..eb05026 --- /dev/null +++ b/nvidia_OpenMath-Nemotron-1.5B-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9e7b6450e5cceedf58489004df9b8b31ac3f998945744568bcb6af6f0209627 +size 776662528 diff --git a/nvidia_OpenMath-Nemotron-1.5B-IQ3_XS.gguf b/nvidia_OpenMath-Nemotron-1.5B-IQ3_XS.gguf new file mode 100644 index 0000000..af44ccb --- /dev/null +++ b/nvidia_OpenMath-Nemotron-1.5B-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e26988ca22132b318f3f1b3f0ef0f7c3068aa41424690f66f13dabd7685e0909 +size 731697664 diff --git a/nvidia_OpenMath-Nemotron-1.5B-IQ3_XXS.gguf b/nvidia_OpenMath-Nemotron-1.5B-IQ3_XXS.gguf new file mode 100644 index 0000000..1b6a94e --- /dev/null +++ b/nvidia_OpenMath-Nemotron-1.5B-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b40377c3aa1ab07a9fc1d0afbf38776e459c6bd404a61e1529044f7c3bfeb43 +size 668790784 diff --git a/nvidia_OpenMath-Nemotron-1.5B-IQ4_NL.gguf b/nvidia_OpenMath-Nemotron-1.5B-IQ4_NL.gguf new file mode 100644 index 0000000..58f3603 --- /dev/null +++ b/nvidia_OpenMath-Nemotron-1.5B-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92bcadf2412b1918b37f006593b204d6a185f32b7be65387f7230a0c9bd00a83 +size 936329728 diff --git a/nvidia_OpenMath-Nemotron-1.5B-IQ4_XS.gguf b/nvidia_OpenMath-Nemotron-1.5B-IQ4_XS.gguf new file mode 100644 index 0000000..9ee7f19 --- /dev/null +++ b/nvidia_OpenMath-Nemotron-1.5B-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba0d0356ee398275f2b0462768f094b49e62616de87f5cdb1e08282a780640b4 +size 895730176 diff --git a/nvidia_OpenMath-Nemotron-1.5B-Q2_K.gguf b/nvidia_OpenMath-Nemotron-1.5B-Q2_K.gguf new file mode 100644 index 0000000..f6e6bef --- /dev/null +++ b/nvidia_OpenMath-Nemotron-1.5B-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74cbf517494352a98089e04e3079bf7e42454e102ffadfa029aab63d3b625dbe +size 676303360 diff --git a/nvidia_OpenMath-Nemotron-1.5B-Q2_K_L.gguf b/nvidia_OpenMath-Nemotron-1.5B-Q2_K_L.gguf new file mode 100644 index 0000000..cf43a5d --- /dev/null +++ b/nvidia_OpenMath-Nemotron-1.5B-Q2_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32255089c153a89a7d22a664f3d665379ffb24d2c335f470cabd4d0efc059649 +size 732823552 diff --git a/nvidia_OpenMath-Nemotron-1.5B-Q3_K_L.gguf b/nvidia_OpenMath-Nemotron-1.5B-Q3_K_L.gguf new file mode 100644 index 0000000..2d84484 --- /dev/null +++ b/nvidia_OpenMath-Nemotron-1.5B-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce296a16f2ab90188da0169e4c0360503b81b9a77ad52027faa5bd86b3435d88 +size 880161280 diff --git a/nvidia_OpenMath-Nemotron-1.5B-Q3_K_M.gguf b/nvidia_OpenMath-Nemotron-1.5B-Q3_K_M.gguf new file mode 100644 index 0000000..ea419a7 --- /dev/null +++ b/nvidia_OpenMath-Nemotron-1.5B-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41f98b5c8b706d0c487c30bcf525d648cd0c8fb55f67cb5830de7456b365856a +size 824177152 diff --git a/nvidia_OpenMath-Nemotron-1.5B-Q3_K_S.gguf b/nvidia_OpenMath-Nemotron-1.5B-Q3_K_S.gguf new file mode 100644 index 0000000..243e522 --- /dev/null +++ b/nvidia_OpenMath-Nemotron-1.5B-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:803c4f878e058db98e0062bc6d2d3a1f12b574410985f57d3a7079f24b425b37 +size 760943104 diff --git a/nvidia_OpenMath-Nemotron-1.5B-Q3_K_XL.gguf b/nvidia_OpenMath-Nemotron-1.5B-Q3_K_XL.gguf new file mode 100644 index 0000000..cd6cb29 --- /dev/null +++ b/nvidia_OpenMath-Nemotron-1.5B-Q3_K_XL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8de947cde7d3d049a105db3515fe2e75f81f77cb70e65cee5320399b793ea63 +size 936681472 diff --git a/nvidia_OpenMath-Nemotron-1.5B-Q4_0.gguf b/nvidia_OpenMath-Nemotron-1.5B-Q4_0.gguf new file mode 100644 index 0000000..8bc06e5 --- /dev/null +++ b/nvidia_OpenMath-Nemotron-1.5B-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:872fa5a6fb4603c181a4bce05577d161b1f196e633728bfdf7f4ed6bb65c026d +size 937533952 diff --git a/nvidia_OpenMath-Nemotron-1.5B-Q4_1.gguf b/nvidia_OpenMath-Nemotron-1.5B-Q4_1.gguf new file mode 100644 index 0000000..7e32c86 --- /dev/null +++ b/nvidia_OpenMath-Nemotron-1.5B-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:247a70f4eae6e9927b895330a630363a56fc1ad400791d653f6f6723d805177e +size 1016840704 diff --git a/nvidia_OpenMath-Nemotron-1.5B-Q4_K_L.gguf b/nvidia_OpenMath-Nemotron-1.5B-Q4_K_L.gguf new file mode 100644 index 0000000..ebe408a --- /dev/null +++ b/nvidia_OpenMath-Nemotron-1.5B-Q4_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b7bf6801ad7002d46f5b876ea25156e1a1a5e7a4c7fbbbb87ed92de8edc97cc +size 1042567168 diff --git a/nvidia_OpenMath-Nemotron-1.5B-Q4_K_M.gguf b/nvidia_OpenMath-Nemotron-1.5B-Q4_K_M.gguf new file mode 100644 index 0000000..0d9abe9 --- /dev/null +++ b/nvidia_OpenMath-Nemotron-1.5B-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cdb74247c7918fdb70f9a9aa8217476f2f02e2fff723631255a441eb0db302e2 +size 986046976 diff --git a/nvidia_OpenMath-Nemotron-1.5B-Q4_K_S.gguf b/nvidia_OpenMath-Nemotron-1.5B-Q4_K_S.gguf new file mode 100644 index 0000000..912d8e2 --- /dev/null +++ b/nvidia_OpenMath-Nemotron-1.5B-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:235c7ee57c65b94b997fe2decabae09188dc8972d7849227b6db83aba8d6f05f +size 940311040 diff --git a/nvidia_OpenMath-Nemotron-1.5B-Q5_K_L.gguf b/nvidia_OpenMath-Nemotron-1.5B-Q5_K_L.gguf new file mode 100644 index 0000000..1c2d285 --- /dev/null +++ b/nvidia_OpenMath-Nemotron-1.5B-Q5_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ae7859d1ec49b9b9d635e01ba26f2128f36f374f2539cbad1c29ab5567cc0d7 +size 1181569024 diff --git a/nvidia_OpenMath-Nemotron-1.5B-Q5_K_M.gguf b/nvidia_OpenMath-Nemotron-1.5B-Q5_K_M.gguf new file mode 100644 index 0000000..a3bf17c --- /dev/null +++ b/nvidia_OpenMath-Nemotron-1.5B-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aff9c2d61cdf2ea346f3fe0271e7a830055250bec1b31c8f882a627d1b7d89b3 +size 1125048832 diff --git a/nvidia_OpenMath-Nemotron-1.5B-Q5_K_S.gguf b/nvidia_OpenMath-Nemotron-1.5B-Q5_K_S.gguf new file mode 100644 index 0000000..9660dae --- /dev/null +++ b/nvidia_OpenMath-Nemotron-1.5B-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bbfcdb5468a984db8d12f1d50f96d15ef34f87560769661a11af0f0f1c07ab20 +size 1098727936 diff --git a/nvidia_OpenMath-Nemotron-1.5B-Q6_K.gguf b/nvidia_OpenMath-Nemotron-1.5B-Q6_K.gguf new file mode 100644 index 0000000..90bc11b --- /dev/null +++ b/nvidia_OpenMath-Nemotron-1.5B-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3737acbfb2be02e5c755fc169a64ec2f6a9f6916c406eacb241e70f2e4ebcfa3 +size 1272738304 diff --git a/nvidia_OpenMath-Nemotron-1.5B-Q6_K_L.gguf b/nvidia_OpenMath-Nemotron-1.5B-Q6_K_L.gguf new file mode 100644 index 0000000..1d6f006 --- /dev/null +++ b/nvidia_OpenMath-Nemotron-1.5B-Q6_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27b9c831f1936fa2db9fce1e83e69a3595ef619355988a6b9056076ee384d86e +size 1329258496 diff --git a/nvidia_OpenMath-Nemotron-1.5B-Q8_0.gguf b/nvidia_OpenMath-Nemotron-1.5B-Q8_0.gguf new file mode 100644 index 0000000..b0ae3cb --- /dev/null +++ b/nvidia_OpenMath-Nemotron-1.5B-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a6de3f0464ea11a4e04a35b13a980811b963cf8f868439cf722b99cbc463ea8b +size 1646571520 diff --git a/nvidia_OpenMath-Nemotron-1.5B-bf16.gguf b/nvidia_OpenMath-Nemotron-1.5B-bf16.gguf new file mode 100644 index 0000000..a94db11 --- /dev/null +++ b/nvidia_OpenMath-Nemotron-1.5B-bf16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59599c18716d6b8553d9d623a49e6c67fc59fdb73157e83cd75d1e3f2c4e104a +size 3093667552 diff --git a/nvidia_OpenMath-Nemotron-1.5B.imatrix b/nvidia_OpenMath-Nemotron-1.5B.imatrix new file mode 100644 index 0000000..e4ae55e Binary files /dev/null and b/nvidia_OpenMath-Nemotron-1.5B.imatrix differ