commit 33e524173116d36f8a981f3868d790e0a8eb879f Author: ModelHub XC Date: Mon Jul 13 22:19:06 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: bartowski/nvidia_Orchestrator-8B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..231d9e2 --- /dev/null +++ b/.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 +*.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 + +*.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_Orchestrator-8B-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +nvidia_Orchestrator-8B-imatrix.gguf filter=lfs diff=lfs merge=lfs -text +nvidia_Orchestrator-8B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +nvidia_Orchestrator-8B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +nvidia_Orchestrator-8B-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +nvidia_Orchestrator-8B-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +nvidia_Orchestrator-8B-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text +nvidia_Orchestrator-8B-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +nvidia_Orchestrator-8B-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +nvidia_Orchestrator-8B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +nvidia_Orchestrator-8B-bf16.gguf filter=lfs diff=lfs merge=lfs -text +nvidia_Orchestrator-8B-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +nvidia_Orchestrator-8B-Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text +nvidia_Orchestrator-8B-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +nvidia_Orchestrator-8B-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +nvidia_Orchestrator-8B-Q6_K_L.gguf filter=lfs diff=lfs merge=lfs -text +nvidia_Orchestrator-8B-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +nvidia_Orchestrator-8B-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +nvidia_Orchestrator-8B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +nvidia_Orchestrator-8B-Q5_K_L.gguf filter=lfs diff=lfs merge=lfs -text +nvidia_Orchestrator-8B-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +nvidia_Orchestrator-8B-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +nvidia_Orchestrator-8B-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +nvidia_Orchestrator-8B-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text +nvidia_Orchestrator-8B-Q6_K.gguf 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..16b8c4d --- /dev/null +++ b/README.md @@ -0,0 +1,170 @@ +--- +quantized_by: bartowski +pipeline_tag: text-generation +base_model: nvidia/Orchestrator-8B +base_model_relation: quantized +--- + +## Llamacpp imatrix Quantizations of Orchestrator-8B by nvidia + +Using llama.cpp release b7187 for quantization. + +Original model: https://huggingface.co/nvidia/Orchestrator-8B + +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}<|im_end|> +<|im_start|>assistant +``` + +## Download a file (not the whole branch) from below: + +| Filename | Quant type | File Size | Split | Description | +| -------- | ---------- | --------- | ----- | ----------- | +| [Orchestrator-8B-bf16.gguf](https://huggingface.co/bartowski/nvidia_Orchestrator-8B-GGUF/blob/main/nvidia_Orchestrator-8B-bf16.gguf) | bf16 | 16.39GB | false | Full BF16 weights. | +| [Orchestrator-8B-Q8_0.gguf](https://huggingface.co/bartowski/nvidia_Orchestrator-8B-GGUF/blob/main/nvidia_Orchestrator-8B-Q8_0.gguf) | Q8_0 | 8.71GB | false | Extremely high quality, generally unneeded but max available quant. | +| [Orchestrator-8B-Q6_K_L.gguf](https://huggingface.co/bartowski/nvidia_Orchestrator-8B-GGUF/blob/main/nvidia_Orchestrator-8B-Q6_K_L.gguf) | Q6_K_L | 7.03GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. | +| [Orchestrator-8B-Q6_K.gguf](https://huggingface.co/bartowski/nvidia_Orchestrator-8B-GGUF/blob/main/nvidia_Orchestrator-8B-Q6_K.gguf) | Q6_K | 6.73GB | false | Very high quality, near perfect, *recommended*. | +| [Orchestrator-8B-Q5_K_L.gguf](https://huggingface.co/bartowski/nvidia_Orchestrator-8B-GGUF/blob/main/nvidia_Orchestrator-8B-Q5_K_L.gguf) | Q5_K_L | 6.24GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. | +| [Orchestrator-8B-Q5_K_M.gguf](https://huggingface.co/bartowski/nvidia_Orchestrator-8B-GGUF/blob/main/nvidia_Orchestrator-8B-Q5_K_M.gguf) | Q5_K_M | 5.85GB | false | High quality, *recommended*. | +| [Orchestrator-8B-Q5_K_S.gguf](https://huggingface.co/bartowski/nvidia_Orchestrator-8B-GGUF/blob/main/nvidia_Orchestrator-8B-Q5_K_S.gguf) | Q5_K_S | 5.72GB | false | High quality, *recommended*. | +| [Orchestrator-8B-Q4_K_L.gguf](https://huggingface.co/bartowski/nvidia_Orchestrator-8B-GGUF/blob/main/nvidia_Orchestrator-8B-Q4_K_L.gguf) | Q4_K_L | 5.49GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. | +| [Orchestrator-8B-Q4_1.gguf](https://huggingface.co/bartowski/nvidia_Orchestrator-8B-GGUF/blob/main/nvidia_Orchestrator-8B-Q4_1.gguf) | Q4_1 | 5.25GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. | +| [Orchestrator-8B-Q4_K_M.gguf](https://huggingface.co/bartowski/nvidia_Orchestrator-8B-GGUF/blob/main/nvidia_Orchestrator-8B-Q4_K_M.gguf) | Q4_K_M | 5.03GB | false | Good quality, default size for most use cases, *recommended*. | +| [Orchestrator-8B-Q3_K_XL.gguf](https://huggingface.co/bartowski/nvidia_Orchestrator-8B-GGUF/blob/main/nvidia_Orchestrator-8B-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. | +| [Orchestrator-8B-Q4_K_S.gguf](https://huggingface.co/bartowski/nvidia_Orchestrator-8B-GGUF/blob/main/nvidia_Orchestrator-8B-Q4_K_S.gguf) | Q4_K_S | 4.80GB | false | Slightly lower quality with more space savings, *recommended*. | +| [Orchestrator-8B-Q4_0.gguf](https://huggingface.co/bartowski/nvidia_Orchestrator-8B-GGUF/blob/main/nvidia_Orchestrator-8B-Q4_0.gguf) | Q4_0 | 4.79GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. | +| [Orchestrator-8B-IQ4_NL.gguf](https://huggingface.co/bartowski/nvidia_Orchestrator-8B-GGUF/blob/main/nvidia_Orchestrator-8B-IQ4_NL.gguf) | IQ4_NL | 4.79GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. | +| [Orchestrator-8B-IQ4_XS.gguf](https://huggingface.co/bartowski/nvidia_Orchestrator-8B-GGUF/blob/main/nvidia_Orchestrator-8B-IQ4_XS.gguf) | IQ4_XS | 4.56GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. | +| [Orchestrator-8B-Q3_K_L.gguf](https://huggingface.co/bartowski/nvidia_Orchestrator-8B-GGUF/blob/main/nvidia_Orchestrator-8B-Q3_K_L.gguf) | Q3_K_L | 4.43GB | false | Lower quality but usable, good for low RAM availability. | +| [Orchestrator-8B-Q3_K_M.gguf](https://huggingface.co/bartowski/nvidia_Orchestrator-8B-GGUF/blob/main/nvidia_Orchestrator-8B-Q3_K_M.gguf) | Q3_K_M | 4.12GB | false | Low quality. | +| [Orchestrator-8B-IQ3_M.gguf](https://huggingface.co/bartowski/nvidia_Orchestrator-8B-GGUF/blob/main/nvidia_Orchestrator-8B-IQ3_M.gguf) | IQ3_M | 3.90GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. | +| [Orchestrator-8B-Q2_K_L.gguf](https://huggingface.co/bartowski/nvidia_Orchestrator-8B-GGUF/blob/main/nvidia_Orchestrator-8B-Q2_K_L.gguf) | Q2_K_L | 3.89GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. | +| [Orchestrator-8B-Q3_K_S.gguf](https://huggingface.co/bartowski/nvidia_Orchestrator-8B-GGUF/blob/main/nvidia_Orchestrator-8B-Q3_K_S.gguf) | Q3_K_S | 3.77GB | false | Low quality, not recommended. | +| [Orchestrator-8B-IQ3_XS.gguf](https://huggingface.co/bartowski/nvidia_Orchestrator-8B-GGUF/blob/main/nvidia_Orchestrator-8B-IQ3_XS.gguf) | IQ3_XS | 3.63GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. | +| [Orchestrator-8B-IQ3_XXS.gguf](https://huggingface.co/bartowski/nvidia_Orchestrator-8B-GGUF/blob/main/nvidia_Orchestrator-8B-IQ3_XXS.gguf) | IQ3_XXS | 3.37GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. | +| [Orchestrator-8B-Q2_K.gguf](https://huggingface.co/bartowski/nvidia_Orchestrator-8B-GGUF/blob/main/nvidia_Orchestrator-8B-Q2_K.gguf) | Q2_K | 3.28GB | false | Very low quality but surprisingly usable. | +| [Orchestrator-8B-IQ2_M.gguf](https://huggingface.co/bartowski/nvidia_Orchestrator-8B-GGUF/blob/main/nvidia_Orchestrator-8B-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 + +
+ 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_Orchestrator-8B-GGUF --include "nvidia_Orchestrator-8B-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_Orchestrator-8B-GGUF --include "nvidia_Orchestrator-8B-Q8_0/*" --local-dir ./ +``` + +You can either specify a new local-dir (nvidia_Orchestrator-8B-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/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. + +
+ 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/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. + +
+ +## 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_Orchestrator-8B-IQ2_M.gguf b/nvidia_Orchestrator-8B-IQ2_M.gguf new file mode 100644 index 0000000..2971ec1 --- /dev/null +++ b/nvidia_Orchestrator-8B-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2a983de58f466a5a0d4fd9c015540113aa3d4ca0877739a4d21cb6b3460a44e +size 3051914400 diff --git a/nvidia_Orchestrator-8B-IQ3_M.gguf b/nvidia_Orchestrator-8B-IQ3_M.gguf new file mode 100644 index 0000000..e818207 --- /dev/null +++ b/nvidia_Orchestrator-8B-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5d4867d64f321e8a58a45728f0f0b7a275ab18b928fcb87db317d1f9a3bd8c8 +size 3896620192 diff --git a/nvidia_Orchestrator-8B-IQ3_XS.gguf b/nvidia_Orchestrator-8B-IQ3_XS.gguf new file mode 100644 index 0000000..f0cf32b --- /dev/null +++ b/nvidia_Orchestrator-8B-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f739fc4fb514c8b0c1723fe6043da46d0da385e536179bc02fbebf363fda1008 +size 3626874016 diff --git a/nvidia_Orchestrator-8B-IQ3_XXS.gguf b/nvidia_Orchestrator-8B-IQ3_XXS.gguf new file mode 100644 index 0000000..8cb3cc4 --- /dev/null +++ b/nvidia_Orchestrator-8B-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de904786b1b5297a6d299197133009d9337a78c8592082dec53dadb52743d30a +size 3369632928 diff --git a/nvidia_Orchestrator-8B-IQ4_NL.gguf b/nvidia_Orchestrator-8B-IQ4_NL.gguf new file mode 100644 index 0000000..eca1232 --- /dev/null +++ b/nvidia_Orchestrator-8B-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf9bc43b27cde2cd19f98419397614f27831bd3ba0ba315ae059347df3eed7df +size 4793623712 diff --git a/nvidia_Orchestrator-8B-IQ4_XS.gguf b/nvidia_Orchestrator-8B-IQ4_XS.gguf new file mode 100644 index 0000000..716efb2 --- /dev/null +++ b/nvidia_Orchestrator-8B-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef229a7e54b236dd537a37833526c8859cf99749fca3af5bc5478dfe3bb98aaf +size 4561839264 diff --git a/nvidia_Orchestrator-8B-Q2_K.gguf b/nvidia_Orchestrator-8B-Q2_K.gguf new file mode 100644 index 0000000..c613da8 --- /dev/null +++ b/nvidia_Orchestrator-8B-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c8fb9018be0ec2167d21500b538bc0eafddb5a20773fc6cc2101e5b47461cd2 +size 3281732768 diff --git a/nvidia_Orchestrator-8B-Q2_K_L.gguf b/nvidia_Orchestrator-8B-Q2_K_L.gguf new file mode 100644 index 0000000..9907bc5 --- /dev/null +++ b/nvidia_Orchestrator-8B-Q2_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c540a247b68885db103cc5afc1ccab52d9d0f516cf603f34cd1bbcf00be5d2ba +size 3889476768 diff --git a/nvidia_Orchestrator-8B-Q3_K_L.gguf b/nvidia_Orchestrator-8B-Q3_K_L.gguf new file mode 100644 index 0000000..9e5a03c --- /dev/null +++ b/nvidia_Orchestrator-8B-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3fe081012cedefda0e02ce28c0cce8edfffec9eec9e5eec302c54265630736e2 +size 4431393952 diff --git a/nvidia_Orchestrator-8B-Q3_K_M.gguf b/nvidia_Orchestrator-8B-Q3_K_M.gguf new file mode 100644 index 0000000..4b036e4 --- /dev/null +++ b/nvidia_Orchestrator-8B-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cca27a1954871b197f0144c930cecab162fe27e8e024261db81476b100b1a281 +size 4124161184 diff --git a/nvidia_Orchestrator-8B-Q3_K_S.gguf b/nvidia_Orchestrator-8B-Q3_K_S.gguf new file mode 100644 index 0000000..8683c89 --- /dev/null +++ b/nvidia_Orchestrator-8B-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae7b52caab968a5c1f7f65ec64d93118d3afe3e6301d8a283ee7709a795faef1 +size 3769611424 diff --git a/nvidia_Orchestrator-8B-Q3_K_XL.gguf b/nvidia_Orchestrator-8B-Q3_K_XL.gguf new file mode 100644 index 0000000..4e46b8f --- /dev/null +++ b/nvidia_Orchestrator-8B-Q3_K_XL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5886f4997eb15a5bf9bf9afacfb2d45baa391c153e9849bb68c1f6d4b7a0b184 +size 4975932576 diff --git a/nvidia_Orchestrator-8B-Q4_0.gguf b/nvidia_Orchestrator-8B-Q4_0.gguf new file mode 100644 index 0000000..d5bf53e --- /dev/null +++ b/nvidia_Orchestrator-8B-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22d7cb661261ba19e651a98ce1be00f62875a758d137fcf58e5cd7eab3ce2611 +size 4787332256 diff --git a/nvidia_Orchestrator-8B-Q4_1.gguf b/nvidia_Orchestrator-8B-Q4_1.gguf new file mode 100644 index 0000000..b6903c2 --- /dev/null +++ b/nvidia_Orchestrator-8B-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f725f79a907560a0a80b09dd04f31c35bbada74ff0850436154120386a209af8 +size 5247755424 diff --git a/nvidia_Orchestrator-8B-Q4_K_L.gguf b/nvidia_Orchestrator-8B-Q4_K_L.gguf new file mode 100644 index 0000000..2b014cb --- /dev/null +++ b/nvidia_Orchestrator-8B-Q4_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3fabe2c27bd1d0878085c8657c9f397ce7c397436e7ae24dc77c9711ab85b952 +size 5489669280 diff --git a/nvidia_Orchestrator-8B-Q4_K_M.gguf b/nvidia_Orchestrator-8B-Q4_K_M.gguf new file mode 100644 index 0000000..17358d4 --- /dev/null +++ b/nvidia_Orchestrator-8B-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1cc7077e20b3339d1a46bc72e29959cdd4c7249ebbd73e6977e76f23625995c7 +size 5027783840 diff --git a/nvidia_Orchestrator-8B-Q4_K_S.gguf b/nvidia_Orchestrator-8B-Q4_K_S.gguf new file mode 100644 index 0000000..fc5756b --- /dev/null +++ b/nvidia_Orchestrator-8B-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97c63344b80819518100b990f43dd09d02620d759a39d5f8dad59616e40e4dc3 +size 4802012320 diff --git a/nvidia_Orchestrator-8B-Q5_K_L.gguf b/nvidia_Orchestrator-8B-Q5_K_L.gguf new file mode 100644 index 0000000..4639d0d --- /dev/null +++ b/nvidia_Orchestrator-8B-Q5_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a153bb4866a1fe41ec67a471baff7175690377e81592491c044e2fbbd2d1ec6 +size 6235206816 diff --git a/nvidia_Orchestrator-8B-Q5_K_M.gguf b/nvidia_Orchestrator-8B-Q5_K_M.gguf new file mode 100644 index 0000000..8bc47ae --- /dev/null +++ b/nvidia_Orchestrator-8B-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65f0487a1810253f79538044d1aea3d13241f09a5de8a502c176bd6758e9fa0f +size 5851112608 diff --git a/nvidia_Orchestrator-8B-Q5_K_S.gguf b/nvidia_Orchestrator-8B-Q5_K_S.gguf new file mode 100644 index 0000000..6fd2c6b --- /dev/null +++ b/nvidia_Orchestrator-8B-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff7e2ec14fe38fb1ff75359d32abc502a2916291b23163dcfcb438b45f937756 +size 5720761504 diff --git a/nvidia_Orchestrator-8B-Q6_K.gguf b/nvidia_Orchestrator-8B-Q6_K.gguf new file mode 100644 index 0000000..e4e18b8 --- /dev/null +++ b/nvidia_Orchestrator-8B-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4f1ed501779e371d93b1e499a3949398bdfaefefa32f879cabd9196dcf3f960 +size 6725899424 diff --git a/nvidia_Orchestrator-8B-Q6_K_L.gguf b/nvidia_Orchestrator-8B-Q6_K_L.gguf new file mode 100644 index 0000000..d563d55 --- /dev/null +++ b/nvidia_Orchestrator-8B-Q6_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2119db90338340677ff6e2aad39ef6add74aa15449b6c7330bbfe502e606380f +size 7027340448 diff --git a/nvidia_Orchestrator-8B-Q8_0.gguf b/nvidia_Orchestrator-8B-Q8_0.gguf new file mode 100644 index 0000000..8b92bec --- /dev/null +++ b/nvidia_Orchestrator-8B-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d197ec92c2e03f0df8bdc1997f72c341e1eb819c786028c34844ada623fd41b +size 8709518496 diff --git a/nvidia_Orchestrator-8B-bf16.gguf b/nvidia_Orchestrator-8B-bf16.gguf new file mode 100644 index 0000000..f645ab3 --- /dev/null +++ b/nvidia_Orchestrator-8B-bf16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c319ab06641bc60437934e9a95f4042a4a49cfcc0daec637137fac16221ee92 +size 16388043648 diff --git a/nvidia_Orchestrator-8B-imatrix.gguf b/nvidia_Orchestrator-8B-imatrix.gguf new file mode 100644 index 0000000..108a472 --- /dev/null +++ b/nvidia_Orchestrator-8B-imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e668e3938a4d3abc8afbad3a0f2710a0f972cd15b0b3498534aa1dfec470abf1 +size 5347200