commit 61e02518a6d812c276ccec0e6068f7ce39801516 Author: ModelHub XC Date: Mon Jul 13 00:07:07 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: bartowski/Zyphra_ZR1-1.5B-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..a600829 --- /dev/null +++ b/README.md @@ -0,0 +1,175 @@ +--- +quantized_by: bartowski +pipeline_tag: text-generation +language: +- en +datasets: +- AI-MO/NuminaMath-CoT +- codeparrot/apps +- deepmind/code_contests +- BAAI/TACO +- MatrixStudio/Codeforces-Python-Submissions +base_model_relation: quantized +license: mit +base_model: Zyphra/ZR1-1.5B +--- + +## Llamacpp imatrix Quantizations of ZR1-1.5B by Zyphra + +Using llama.cpp release b5074 for quantization. + +Original model: https://huggingface.co/Zyphra/ZR1-1.5B + +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 + +``` +<｜begin▁of▁sentence｜>{system_prompt}<｜User｜>{prompt}<｜Assistant｜><｜end▁of▁sentence｜><｜Assistant｜> +``` + +## Download a file (not the whole branch) from below: + +| Filename | Quant type | File Size | Split | Description | +| -------- | ---------- | --------- | ----- | ----------- | +| [ZR1-1.5B-bf16.gguf](https://huggingface.co/bartowski/Zyphra_ZR1-1.5B-GGUF/blob/main/Zyphra_ZR1-1.5B-bf16.gguf) | bf16 | 3.56GB | false | Full BF16 weights. | +| [ZR1-1.5B-Q8_0.gguf](https://huggingface.co/bartowski/Zyphra_ZR1-1.5B-GGUF/blob/main/Zyphra_ZR1-1.5B-Q8_0.gguf) | Q8_0 | 1.89GB | false | Extremely high quality, generally unneeded but max available quant. | +| [ZR1-1.5B-Q6_K_L.gguf](https://huggingface.co/bartowski/Zyphra_ZR1-1.5B-GGUF/blob/main/Zyphra_ZR1-1.5B-Q6_K_L.gguf) | Q6_K_L | 1.58GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. | +| [ZR1-1.5B-Q6_K.gguf](https://huggingface.co/bartowski/Zyphra_ZR1-1.5B-GGUF/blob/main/Zyphra_ZR1-1.5B-Q6_K.gguf) | Q6_K | 1.46GB | false | Very high quality, near perfect, *recommended*. | +| [ZR1-1.5B-Q5_K_L.gguf](https://huggingface.co/bartowski/Zyphra_ZR1-1.5B-GGUF/blob/main/Zyphra_ZR1-1.5B-Q5_K_L.gguf) | Q5_K_L | 1.43GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. | +| [ZR1-1.5B-Q5_K_M.gguf](https://huggingface.co/bartowski/Zyphra_ZR1-1.5B-GGUF/blob/main/Zyphra_ZR1-1.5B-Q5_K_M.gguf) | Q5_K_M | 1.29GB | false | High quality, *recommended*. | +| [ZR1-1.5B-Q4_K_L.gguf](https://huggingface.co/bartowski/Zyphra_ZR1-1.5B-GGUF/blob/main/Zyphra_ZR1-1.5B-Q4_K_L.gguf) | Q4_K_L | 1.29GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. | +| [ZR1-1.5B-Q5_K_S.gguf](https://huggingface.co/bartowski/Zyphra_ZR1-1.5B-GGUF/blob/main/Zyphra_ZR1-1.5B-Q5_K_S.gguf) | Q5_K_S | 1.26GB | false | High quality, *recommended*. | +| [ZR1-1.5B-Q3_K_XL.gguf](https://huggingface.co/bartowski/Zyphra_ZR1-1.5B-GGUF/blob/main/Zyphra_ZR1-1.5B-Q3_K_XL.gguf) | Q3_K_XL | 1.18GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. | +| [ZR1-1.5B-Q4_1.gguf](https://huggingface.co/bartowski/Zyphra_ZR1-1.5B-GGUF/blob/main/Zyphra_ZR1-1.5B-Q4_1.gguf) | Q4_1 | 1.16GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. | +| [ZR1-1.5B-Q4_K_M.gguf](https://huggingface.co/bartowski/Zyphra_ZR1-1.5B-GGUF/blob/main/Zyphra_ZR1-1.5B-Q4_K_M.gguf) | Q4_K_M | 1.12GB | false | Good quality, default size for most use cases, *recommended*. | +| [ZR1-1.5B-Q4_K_S.gguf](https://huggingface.co/bartowski/Zyphra_ZR1-1.5B-GGUF/blob/main/Zyphra_ZR1-1.5B-Q4_K_S.gguf) | Q4_K_S | 1.07GB | false | Slightly lower quality with more space savings, *recommended*. | +| [ZR1-1.5B-Q4_0.gguf](https://huggingface.co/bartowski/Zyphra_ZR1-1.5B-GGUF/blob/main/Zyphra_ZR1-1.5B-Q4_0.gguf) | Q4_0 | 1.07GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. | +| [ZR1-1.5B-IQ4_NL.gguf](https://huggingface.co/bartowski/Zyphra_ZR1-1.5B-GGUF/blob/main/Zyphra_ZR1-1.5B-IQ4_NL.gguf) | IQ4_NL | 1.07GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. | +| [ZR1-1.5B-IQ4_XS.gguf](https://huggingface.co/bartowski/Zyphra_ZR1-1.5B-GGUF/blob/main/Zyphra_ZR1-1.5B-IQ4_XS.gguf) | IQ4_XS | 1.02GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. | +| [ZR1-1.5B-Q3_K_L.gguf](https://huggingface.co/bartowski/Zyphra_ZR1-1.5B-GGUF/blob/main/Zyphra_ZR1-1.5B-Q3_K_L.gguf) | Q3_K_L | 0.98GB | false | Lower quality but usable, good for low RAM availability. | +| [ZR1-1.5B-Q2_K_L.gguf](https://huggingface.co/bartowski/Zyphra_ZR1-1.5B-GGUF/blob/main/Zyphra_ZR1-1.5B-Q2_K_L.gguf) | Q2_K_L | 0.98GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. | +| [ZR1-1.5B-Q3_K_M.gguf](https://huggingface.co/bartowski/Zyphra_ZR1-1.5B-GGUF/blob/main/Zyphra_ZR1-1.5B-Q3_K_M.gguf) | Q3_K_M | 0.92GB | false | Low quality. | +| [ZR1-1.5B-IQ3_M.gguf](https://huggingface.co/bartowski/Zyphra_ZR1-1.5B-GGUF/blob/main/Zyphra_ZR1-1.5B-IQ3_M.gguf) | IQ3_M | 0.88GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. | +| [ZR1-1.5B-Q3_K_S.gguf](https://huggingface.co/bartowski/Zyphra_ZR1-1.5B-GGUF/blob/main/Zyphra_ZR1-1.5B-Q3_K_S.gguf) | Q3_K_S | 0.86GB | false | Low quality, not recommended. | +| [ZR1-1.5B-IQ3_XS.gguf](https://huggingface.co/bartowski/Zyphra_ZR1-1.5B-GGUF/blob/main/Zyphra_ZR1-1.5B-IQ3_XS.gguf) | IQ3_XS | 0.83GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. | +| [ZR1-1.5B-IQ3_XXS.gguf](https://huggingface.co/bartowski/Zyphra_ZR1-1.5B-GGUF/blob/main/Zyphra_ZR1-1.5B-IQ3_XXS.gguf) | IQ3_XXS | 0.77GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. | +| [ZR1-1.5B-Q2_K.gguf](https://huggingface.co/bartowski/Zyphra_ZR1-1.5B-GGUF/blob/main/Zyphra_ZR1-1.5B-Q2_K.gguf) | Q2_K | 0.75GB | false | Very low quality but surprisingly usable. | +| [ZR1-1.5B-IQ2_M.gguf](https://huggingface.co/bartowski/Zyphra_ZR1-1.5B-GGUF/blob/main/Zyphra_ZR1-1.5B-IQ2_M.gguf) | IQ2_M | 0.70GB | 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/Zyphra_ZR1-1.5B-GGUF --include "Zyphra_ZR1-1.5B-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/Zyphra_ZR1-1.5B-GGUF --include "Zyphra_ZR1-1.5B-Q8_0/*" --local-dir ./ +``` + +You can either specify a new local-dir (Zyphra_ZR1-1.5B-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/Zyphra_ZR1-1.5B-IQ2_M.gguf b/Zyphra_ZR1-1.5B-IQ2_M.gguf new file mode 100644 index 0000000..0d7db88 --- /dev/null +++ b/Zyphra_ZR1-1.5B-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:634b1357601226569f7a8f849bd964f9a4eb74bd1ca7de40a0c874633d6a5002 +size 701333472 diff --git a/Zyphra_ZR1-1.5B-IQ3_M.gguf b/Zyphra_ZR1-1.5B-IQ3_M.gguf new file mode 100644 index 0000000..a04d2b1 --- /dev/null +++ b/Zyphra_ZR1-1.5B-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e5d6c9d968137897a407517f2bd70dd70eb945fdfca9e458ef6f424b0a1ea51 +size 876942816 diff --git a/Zyphra_ZR1-1.5B-IQ3_XS.gguf b/Zyphra_ZR1-1.5B-IQ3_XS.gguf new file mode 100644 index 0000000..d248e7d --- /dev/null +++ b/Zyphra_ZR1-1.5B-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2140b2915c00bc2348943c507a0433f1af610d82d60bd116712c600dc1e0af42 +size 831977952 diff --git a/Zyphra_ZR1-1.5B-IQ3_XXS.gguf b/Zyphra_ZR1-1.5B-IQ3_XXS.gguf new file mode 100644 index 0000000..53dc9d4 --- /dev/null +++ b/Zyphra_ZR1-1.5B-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e452d5e082ca4760476562321b14fcc8f42cb31ca76a649da69533e496ff8b94 +size 769071072 diff --git a/Zyphra_ZR1-1.5B-IQ4_NL.gguf b/Zyphra_ZR1-1.5B-IQ4_NL.gguf new file mode 100644 index 0000000..6fb6916 --- /dev/null +++ b/Zyphra_ZR1-1.5B-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1d185c0dc718eea5d227840429eb6d59eb4de60a3293efcc5f7ece30808162b +size 1067604960 diff --git a/Zyphra_ZR1-1.5B-IQ4_XS.gguf b/Zyphra_ZR1-1.5B-IQ4_XS.gguf new file mode 100644 index 0000000..d86cf59 --- /dev/null +++ b/Zyphra_ZR1-1.5B-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:186e1098aeabb663630bb2be1bbac11ef72a89122c3b7636e36ee0189ca3769f +size 1019712480 diff --git a/Zyphra_ZR1-1.5B-Q2_K.gguf b/Zyphra_ZR1-1.5B-Q2_K.gguf new file mode 100644 index 0000000..3c74918 --- /dev/null +++ b/Zyphra_ZR1-1.5B-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:388983548ca005fe000634e517dcbd695bdf272845ffb29978b492425c445d06 +size 752881632 diff --git a/Zyphra_ZR1-1.5B-Q2_K_L.gguf b/Zyphra_ZR1-1.5B-Q2_K_L.gguf new file mode 100644 index 0000000..3c35f8f --- /dev/null +++ b/Zyphra_ZR1-1.5B-Q2_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31ae7ddb1a29505db7cc28d75c254cd1588d07f636870cdd1e18a2e56513c229 +size 980785632 diff --git a/Zyphra_ZR1-1.5B-Q3_K_L.gguf b/Zyphra_ZR1-1.5B-Q3_K_L.gguf new file mode 100644 index 0000000..03f1787 --- /dev/null +++ b/Zyphra_ZR1-1.5B-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20ec76a06875f2b4e76a49bcda01d1990b37a88812c5cd2d8512612017b2acaf +size 980441568 diff --git a/Zyphra_ZR1-1.5B-Q3_K_M.gguf b/Zyphra_ZR1-1.5B-Q3_K_M.gguf new file mode 100644 index 0000000..85e5348 --- /dev/null +++ b/Zyphra_ZR1-1.5B-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05621f91992e7af76b577704db973091ee8385e75472508c9471a7894a7e386f +size 924457440 diff --git a/Zyphra_ZR1-1.5B-Q3_K_S.gguf b/Zyphra_ZR1-1.5B-Q3_K_S.gguf new file mode 100644 index 0000000..ac0ec67 --- /dev/null +++ b/Zyphra_ZR1-1.5B-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9095816ecd1f72597602864a909b241bd5bffc457a3bb53a8bdf53fa588f1fc2 +size 861223392 diff --git a/Zyphra_ZR1-1.5B-Q3_K_XL.gguf b/Zyphra_ZR1-1.5B-Q3_K_XL.gguf new file mode 100644 index 0000000..4d82267 --- /dev/null +++ b/Zyphra_ZR1-1.5B-Q3_K_XL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04dc3e3cbb850405a759018935f69a47f290372c311a91c243d465246e7ee55e +size 1184643552 diff --git a/Zyphra_ZR1-1.5B-Q4_0.gguf b/Zyphra_ZR1-1.5B-Q4_0.gguf new file mode 100644 index 0000000..492185b --- /dev/null +++ b/Zyphra_ZR1-1.5B-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f501be20e9c313cc40f301095497f57d2d0be3f639ff8e9da21390977117ab43 +size 1068809184 diff --git a/Zyphra_ZR1-1.5B-Q4_1.gguf b/Zyphra_ZR1-1.5B-Q4_1.gguf new file mode 100644 index 0000000..e1a41fd --- /dev/null +++ b/Zyphra_ZR1-1.5B-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85416d723e8366daa251e71eeae26ede43165a9c5fef9004b81d75f58696bda4 +size 1162701792 diff --git a/Zyphra_ZR1-1.5B-Q4_K_L.gguf b/Zyphra_ZR1-1.5B-Q4_K_L.gguf new file mode 100644 index 0000000..7ef5ef6 --- /dev/null +++ b/Zyphra_ZR1-1.5B-Q4_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:752f08d25921b9f5c2c14220930b6f0c88c4ca9a25a9941aed56342736f01642 +size 1290529248 diff --git a/Zyphra_ZR1-1.5B-Q4_K_M.gguf b/Zyphra_ZR1-1.5B-Q4_K_M.gguf new file mode 100644 index 0000000..1b85cf2 --- /dev/null +++ b/Zyphra_ZR1-1.5B-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5442a9303f651eec30d8d17cd649982ddedf3629ff4faf3bf08d187900a7e7bd +size 1117322208 diff --git a/Zyphra_ZR1-1.5B-Q4_K_S.gguf b/Zyphra_ZR1-1.5B-Q4_K_S.gguf new file mode 100644 index 0000000..0227830 --- /dev/null +++ b/Zyphra_ZR1-1.5B-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05cba53ec6abe928a57c7e019181204e93313ecebc43170812a7e756c01af96a +size 1071586272 diff --git a/Zyphra_ZR1-1.5B-Q5_K_L.gguf b/Zyphra_ZR1-1.5B-Q5_K_L.gguf new file mode 100644 index 0000000..2f90446 --- /dev/null +++ b/Zyphra_ZR1-1.5B-Q5_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fda0b7cc495b21f7134005e8631ec4a540e85866aa54a911fa61f96ca7397801 +size 1429531104 diff --git a/Zyphra_ZR1-1.5B-Q5_K_M.gguf b/Zyphra_ZR1-1.5B-Q5_K_M.gguf new file mode 100644 index 0000000..8837f25 --- /dev/null +++ b/Zyphra_ZR1-1.5B-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a01c0f6e7044a23c7901033f99fa5073a222ae0ae8c2e804fa7c25f4abb45aad +size 1285495776 diff --git a/Zyphra_ZR1-1.5B-Q5_K_S.gguf b/Zyphra_ZR1-1.5B-Q5_K_S.gguf new file mode 100644 index 0000000..4f44f24 --- /dev/null +++ b/Zyphra_ZR1-1.5B-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1497633c10eec925910b6bce5da1f5fce1cbf363553cf600e33eb5afbc267e3f +size 1259174880 diff --git a/Zyphra_ZR1-1.5B-Q6_K.gguf b/Zyphra_ZR1-1.5B-Q6_K.gguf new file mode 100644 index 0000000..cc7b837 --- /dev/null +++ b/Zyphra_ZR1-1.5B-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89baa233f49bdce20e5445f995722961503a8f861d6b52a068b0819cb9bddf5a +size 1464180192 diff --git a/Zyphra_ZR1-1.5B-Q6_K_L.gguf b/Zyphra_ZR1-1.5B-Q6_K_L.gguf new file mode 100644 index 0000000..694ddaf --- /dev/null +++ b/Zyphra_ZR1-1.5B-Q6_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab21068db5ef3cf251b7abee1b412ec22c019e3d980ff1ffad1d1617f5282510 +size 1577220576 diff --git a/Zyphra_ZR1-1.5B-Q8_0.gguf b/Zyphra_ZR1-1.5B-Q8_0.gguf new file mode 100644 index 0000000..7cff868 --- /dev/null +++ b/Zyphra_ZR1-1.5B-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:744bbc8db102509445722e85ef1af3821df84d34d8b7d48d987ba817bf7bbfd6 +size 1894533600 diff --git a/Zyphra_ZR1-1.5B-bf16.gguf b/Zyphra_ZR1-1.5B-bf16.gguf new file mode 100644 index 0000000..01f438a --- /dev/null +++ b/Zyphra_ZR1-1.5B-bf16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:207086d2e0b3d1ede11fe6df3fdc929e82f90b297d6c387d9287c244c8477785 +size 3560417504 diff --git a/Zyphra_ZR1-1.5B.imatrix b/Zyphra_ZR1-1.5B.imatrix new file mode 100644 index 0000000..ff6651d Binary files /dev/null and b/Zyphra_ZR1-1.5B.imatrix differ 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