初始化项目，由ModelHub XC社区提供模型

Model: bartowski/nvidia_Nemotron-Cascade-8B-Thinking-GGUF
Source: Original Platform

.gitattributes

@@ -0,0 +1,73 @@
+*.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
+ 
+*.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
+ 
+*.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
+
+nvidia_Nemotron-Cascade-8B-Thinking-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+nvidia_Nemotron-Cascade-8B-Thinking-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
+nvidia_Nemotron-Cascade-8B-Thinking-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+nvidia_Nemotron-Cascade-8B-Thinking-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+nvidia_Nemotron-Cascade-8B-Thinking-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+nvidia_Nemotron-Cascade-8B-Thinking-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
+nvidia_Nemotron-Cascade-8B-Thinking-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+nvidia_Nemotron-Cascade-8B-Thinking-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text
+nvidia_Nemotron-Cascade-8B-Thinking-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
+nvidia_Nemotron-Cascade-8B-Thinking-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+nvidia_Nemotron-Cascade-8B-Thinking-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text
+nvidia_Nemotron-Cascade-8B-Thinking-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+nvidia_Nemotron-Cascade-8B-Thinking-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text
+nvidia_Nemotron-Cascade-8B-Thinking-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+nvidia_Nemotron-Cascade-8B-Thinking-bf16.gguf filter=lfs diff=lfs merge=lfs -text
+nvidia_Nemotron-Cascade-8B-Thinking-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text
+nvidia_Nemotron-Cascade-8B-Thinking-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+nvidia_Nemotron-Cascade-8B-Thinking-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+nvidia_Nemotron-Cascade-8B-Thinking-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+nvidia_Nemotron-Cascade-8B-Thinking-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+nvidia_Nemotron-Cascade-8B-Thinking-Q6_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+nvidia_Nemotron-Cascade-8B-Thinking-Q5_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+nvidia_Nemotron-Cascade-8B-Thinking-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
+nvidia_Nemotron-Cascade-8B-Thinking-Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+nvidia_Nemotron-Cascade-8B-Thinking-imatrix.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,182 @@
+---
+quantized_by: bartowski
+pipeline_tag: text-generation
+tags:
+- nvidia
+- Nemotron-Cascade
+- reasoning
+- general-purpose
+- SFT
+- RL
+license: other
+license_name: nvidia-open-model-license
+language:
+- en
+base_model: nvidia/Nemotron-Cascade-8B-Thinking
+base_model_relation: quantized
+license_link: https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/
+---
+
+## Llamacpp imatrix Quantizations of Nemotron-Cascade-8B-Thinking by nvidia
+
+Using <a href="https://github.com/ggml-org/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggml-org/llama.cpp/releases/tag/b7423">b7423</a> for quantization.
+
+Original model: https://huggingface.co/nvidia/Nemotron-Cascade-8B-Thinking
+
+All quants made using imatrix option with dataset from [here](https://gist.github.com/bartowski1182/eb213dccb3571f863da82e99418f81e8) combined with a subset of combined_all_small.parquet from Ed Addario [here](https://huggingface.co/datasets/eaddario/imatrix-calibration/blob/main/combined_all_small.parquet)
+
+Run them in [LM Studio](https://lmstudio.ai/)
+
+Run them directly with [llama.cpp](https://github.com/ggml-org/llama.cpp), or any other llama.cpp based project
+
+## Prompt format
+
+```
+<|im_start|>system
+{system_prompt}<|im_end|>
+<|im_start|>user
+{prompt} /think<|im_end|>
+<|im_start|>assistant
+```
+
+## Download a file (not the whole branch) from below:
+
+| Filename | Quant type | File Size | Split | Description |
+| -------- | ---------- | --------- | ----- | ----------- |
+| [Nemotron-Cascade-8B-Thinking-bf16.gguf](https://huggingface.co/bartowski/nvidia_Nemotron-Cascade-8B-Thinking-GGUF/blob/main/nvidia_Nemotron-Cascade-8B-Thinking-bf16.gguf) | bf16 | 16.39GB | false | Full BF16 weights. |
+| [Nemotron-Cascade-8B-Thinking-Q8_0.gguf](https://huggingface.co/bartowski/nvidia_Nemotron-Cascade-8B-Thinking-GGUF/blob/main/nvidia_Nemotron-Cascade-8B-Thinking-Q8_0.gguf) | Q8_0 | 8.71GB | false | Extremely high quality, generally unneeded but max available quant. |
+| [Nemotron-Cascade-8B-Thinking-Q6_K_L.gguf](https://huggingface.co/bartowski/nvidia_Nemotron-Cascade-8B-Thinking-GGUF/blob/main/nvidia_Nemotron-Cascade-8B-Thinking-Q6_K_L.gguf) | Q6_K_L | 7.03GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. |
+| [Nemotron-Cascade-8B-Thinking-Q6_K.gguf](https://huggingface.co/bartowski/nvidia_Nemotron-Cascade-8B-Thinking-GGUF/blob/main/nvidia_Nemotron-Cascade-8B-Thinking-Q6_K.gguf) | Q6_K | 6.73GB | false | Very high quality, near perfect, *recommended*. |
+| [Nemotron-Cascade-8B-Thinking-Q5_K_L.gguf](https://huggingface.co/bartowski/nvidia_Nemotron-Cascade-8B-Thinking-GGUF/blob/main/nvidia_Nemotron-Cascade-8B-Thinking-Q5_K_L.gguf) | Q5_K_L | 6.24GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. |
+| [Nemotron-Cascade-8B-Thinking-Q5_K_M.gguf](https://huggingface.co/bartowski/nvidia_Nemotron-Cascade-8B-Thinking-GGUF/blob/main/nvidia_Nemotron-Cascade-8B-Thinking-Q5_K_M.gguf) | Q5_K_M | 5.85GB | false | High quality, *recommended*. |
+| [Nemotron-Cascade-8B-Thinking-Q5_K_S.gguf](https://huggingface.co/bartowski/nvidia_Nemotron-Cascade-8B-Thinking-GGUF/blob/main/nvidia_Nemotron-Cascade-8B-Thinking-Q5_K_S.gguf) | Q5_K_S | 5.72GB | false | High quality, *recommended*. |
+| [Nemotron-Cascade-8B-Thinking-Q4_K_L.gguf](https://huggingface.co/bartowski/nvidia_Nemotron-Cascade-8B-Thinking-GGUF/blob/main/nvidia_Nemotron-Cascade-8B-Thinking-Q4_K_L.gguf) | Q4_K_L | 5.49GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. |
+| [Nemotron-Cascade-8B-Thinking-Q4_1.gguf](https://huggingface.co/bartowski/nvidia_Nemotron-Cascade-8B-Thinking-GGUF/blob/main/nvidia_Nemotron-Cascade-8B-Thinking-Q4_1.gguf) | Q4_1 | 5.25GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. |
+| [Nemotron-Cascade-8B-Thinking-Q4_K_M.gguf](https://huggingface.co/bartowski/nvidia_Nemotron-Cascade-8B-Thinking-GGUF/blob/main/nvidia_Nemotron-Cascade-8B-Thinking-Q4_K_M.gguf) | Q4_K_M | 5.03GB | false | Good quality, default size for most use cases, *recommended*. |
+| [Nemotron-Cascade-8B-Thinking-Q3_K_XL.gguf](https://huggingface.co/bartowski/nvidia_Nemotron-Cascade-8B-Thinking-GGUF/blob/main/nvidia_Nemotron-Cascade-8B-Thinking-Q3_K_XL.gguf) | Q3_K_XL | 4.98GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. |
+| [Nemotron-Cascade-8B-Thinking-Q4_K_S.gguf](https://huggingface.co/bartowski/nvidia_Nemotron-Cascade-8B-Thinking-GGUF/blob/main/nvidia_Nemotron-Cascade-8B-Thinking-Q4_K_S.gguf) | Q4_K_S | 4.80GB | false | Slightly lower quality with more space savings, *recommended*. |
+| [Nemotron-Cascade-8B-Thinking-Q4_0.gguf](https://huggingface.co/bartowski/nvidia_Nemotron-Cascade-8B-Thinking-GGUF/blob/main/nvidia_Nemotron-Cascade-8B-Thinking-Q4_0.gguf) | Q4_0 | 4.79GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. |
+| [Nemotron-Cascade-8B-Thinking-IQ4_NL.gguf](https://huggingface.co/bartowski/nvidia_Nemotron-Cascade-8B-Thinking-GGUF/blob/main/nvidia_Nemotron-Cascade-8B-Thinking-IQ4_NL.gguf) | IQ4_NL | 4.79GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. |
+| [Nemotron-Cascade-8B-Thinking-IQ4_XS.gguf](https://huggingface.co/bartowski/nvidia_Nemotron-Cascade-8B-Thinking-GGUF/blob/main/nvidia_Nemotron-Cascade-8B-Thinking-IQ4_XS.gguf) | IQ4_XS | 4.56GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
+| [Nemotron-Cascade-8B-Thinking-Q3_K_L.gguf](https://huggingface.co/bartowski/nvidia_Nemotron-Cascade-8B-Thinking-GGUF/blob/main/nvidia_Nemotron-Cascade-8B-Thinking-Q3_K_L.gguf) | Q3_K_L | 4.43GB | false | Lower quality but usable, good for low RAM availability. |
+| [Nemotron-Cascade-8B-Thinking-Q3_K_M.gguf](https://huggingface.co/bartowski/nvidia_Nemotron-Cascade-8B-Thinking-GGUF/blob/main/nvidia_Nemotron-Cascade-8B-Thinking-Q3_K_M.gguf) | Q3_K_M | 4.12GB | false | Low quality. |
+| [Nemotron-Cascade-8B-Thinking-IQ3_M.gguf](https://huggingface.co/bartowski/nvidia_Nemotron-Cascade-8B-Thinking-GGUF/blob/main/nvidia_Nemotron-Cascade-8B-Thinking-IQ3_M.gguf) | IQ3_M | 3.90GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
+| [Nemotron-Cascade-8B-Thinking-Q2_K_L.gguf](https://huggingface.co/bartowski/nvidia_Nemotron-Cascade-8B-Thinking-GGUF/blob/main/nvidia_Nemotron-Cascade-8B-Thinking-Q2_K_L.gguf) | Q2_K_L | 3.89GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. |
+| [Nemotron-Cascade-8B-Thinking-Q3_K_S.gguf](https://huggingface.co/bartowski/nvidia_Nemotron-Cascade-8B-Thinking-GGUF/blob/main/nvidia_Nemotron-Cascade-8B-Thinking-Q3_K_S.gguf) | Q3_K_S | 3.77GB | false | Low quality, not recommended. |
+| [Nemotron-Cascade-8B-Thinking-IQ3_XS.gguf](https://huggingface.co/bartowski/nvidia_Nemotron-Cascade-8B-Thinking-GGUF/blob/main/nvidia_Nemotron-Cascade-8B-Thinking-IQ3_XS.gguf) | IQ3_XS | 3.63GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
+| [Nemotron-Cascade-8B-Thinking-IQ3_XXS.gguf](https://huggingface.co/bartowski/nvidia_Nemotron-Cascade-8B-Thinking-GGUF/blob/main/nvidia_Nemotron-Cascade-8B-Thinking-IQ3_XXS.gguf) | IQ3_XXS | 3.37GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. |
+| [Nemotron-Cascade-8B-Thinking-Q2_K.gguf](https://huggingface.co/bartowski/nvidia_Nemotron-Cascade-8B-Thinking-GGUF/blob/main/nvidia_Nemotron-Cascade-8B-Thinking-Q2_K.gguf) | Q2_K | 3.28GB | false | Very low quality but surprisingly usable. |
+| [Nemotron-Cascade-8B-Thinking-IQ2_M.gguf](https://huggingface.co/bartowski/nvidia_Nemotron-Cascade-8B-Thinking-GGUF/blob/main/nvidia_Nemotron-Cascade-8B-Thinking-IQ2_M.gguf) | IQ2_M | 3.05GB | 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
+
+<details>
+  <summary>Click to view download instructions</summary>
+
+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_Nemotron-Cascade-8B-Thinking-GGUF --include "nvidia_Nemotron-Cascade-8B-Thinking-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_Nemotron-Cascade-8B-Thinking-GGUF --include "nvidia_Nemotron-Cascade-8B-Thinking-Q8_0/*" --local-dir ./
+```
+
+You can either specify a new local-dir (nvidia_Nemotron-Cascade-8B-Thinking-Q8_0) or download them all in place (./)
+
+</details>
+
+## 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/ggml-org/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/ggml-org/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/ggml-org/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.
+
+<details>
+  <summary>Click to view Q4_0_X_X information (deprecated</summary>
+
+I'm keeping this section to show the potential theoretical uplift in performance from using the Q4_0 with online repacking.
+
+<details>
+  <summary>Click to view benchmarks on an AVX2 system (EPYC7702)</summary>
+
+| 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
+
+</details>
+
+</details>
+
+## Which file should I choose?
+
+<details>
+  <summary>Click here for details</summary>
+
+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/ggml-org/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.
+
+</details>
+
+## 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

configuration.json

@@ -0,0 +1 @@
+{"framework": "pytorch", "task": "text-generation", "allow_remote": true}

nvidia_Nemotron-Cascade-8B-Thinking-IQ2_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06bfadf3a74234f50cd402e70fafdfc1f3f39658fa2878505f71c66281b63861
+size 3051915328

nvidia_Nemotron-Cascade-8B-Thinking-IQ3_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea82a31ed6381f9d2f99ab326444b4cf812a63195e8e6d7badf9e704415326c9
+size 3896621120

nvidia_Nemotron-Cascade-8B-Thinking-IQ3_XS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01025b7abbfbf1c426e8cdf823668ff5ff15881d9e7f188eca1b05442d63fbaf
+size 3626874944

nvidia_Nemotron-Cascade-8B-Thinking-IQ3_XXS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8073ec4d9938eea1deed5cb4d23b6add9dec17ee6d112f1d864015f944e2997
+size 3369633856

nvidia_Nemotron-Cascade-8B-Thinking-IQ4_NL.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5aed2bb68688c5eb2be56e0a56afc42f3dbeab8b40ff06feab3309e2bdfbcf75
+size 4793624640

nvidia_Nemotron-Cascade-8B-Thinking-IQ4_XS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e873ed364f27fe63c53cea74812b3c51323c02d7755716ba2fd45bfb8e4211ba
+size 4561840192

nvidia_Nemotron-Cascade-8B-Thinking-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41735d14fe43a7a53053f57e83bd23999a3a8c403d74228c365abff8e52a6d58
+size 3281733696

nvidia_Nemotron-Cascade-8B-Thinking-Q2_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfcbe99c2634127c350b1b1ee16e73ea73f9faba804b78f667b898d6b2ba554e
+size 3889477696

nvidia_Nemotron-Cascade-8B-Thinking-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3271458598c50f0d53a523daddc5506494472631f949ec636c8fb2f6b49aec6c
+size 4431394880

nvidia_Nemotron-Cascade-8B-Thinking-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff5afcc9441de2711dc5c9544cf193ab2380c048122d649d5ee49cfb66883380
+size 4124162112

nvidia_Nemotron-Cascade-8B-Thinking-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0a9a77c894918700ddd8686eb4df5f97a2bfac9eca2263ad9e87e2ece8f4c7d
+size 3769612352

nvidia_Nemotron-Cascade-8B-Thinking-Q3_K_XL.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8a8f963e2cfe3703c0d876925ba2c587b614a912b44598c25e3772a51efcaca
+size 4975933504

nvidia_Nemotron-Cascade-8B-Thinking-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ff5d387ee7f24344e19303f924d097733a5a5f90bbb36b2787251bae7f00758
+size 4787333184

nvidia_Nemotron-Cascade-8B-Thinking-Q4_1.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:270324d2a0e77fe20ae3d3cf593ad375e8af0a4a966d33fe0513227db4bc6b26
+size 5247756352

nvidia_Nemotron-Cascade-8B-Thinking-Q4_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e437d7172753e94251b3c91d840a4e0392a78ccd1c956d71372306bb4a0cb0c5
+size 5489670208

nvidia_Nemotron-Cascade-8B-Thinking-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f678eddef92d4967010101ae1f2f437893fe69125914b9623b524b51b4e19780
+size 5027784768

nvidia_Nemotron-Cascade-8B-Thinking-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd9e600f4ea3f7ecfde15e316ef8ea3c3423ed3e8020aecd4c27985d42d645ba
+size 4802013248

nvidia_Nemotron-Cascade-8B-Thinking-Q5_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27e9156cd9c54bd67756084559d673539f05f7530048daa7fcaac2288349a9ef
+size 6235207744

nvidia_Nemotron-Cascade-8B-Thinking-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4049672643913838379982466957669b85b8ad7ddfb92dc4b4b8b59ce9f20687
+size 5851113536

nvidia_Nemotron-Cascade-8B-Thinking-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f6abc50e526d91ba8a683ac2101d7968fffc38823773d5861fd0fa118c5fb4f
+size 5720762432

nvidia_Nemotron-Cascade-8B-Thinking-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a8fd4bd69937b2b3b04eaacd50f07bb8428679281dd2c27ad82c62313c0901f
+size 6725900352

nvidia_Nemotron-Cascade-8B-Thinking-Q6_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a31ff959e167902c988f90a49d2490d6745d700cf65833423ef1ca911bc5a38
+size 7027341376

nvidia_Nemotron-Cascade-8B-Thinking-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef53d405398c69ec00dd4f52fca889ed372e32246d37d7b55a91ec448d226396
+size 8709519424

nvidia_Nemotron-Cascade-8B-Thinking-bf16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0636664b1c4b43d28fec2b16a2a88e763aa3859112ad5b2e101d40cda3e4f85
+size 16388044544

nvidia_Nemotron-Cascade-8B-Thinking-imatrix.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0ee1d5928850bc3fc3b6abd165d76ac8ee6da3d876ee1f910d57dfb782dc46e
+size 5347200