commit 1e49946e52d700f5dbb0e6ab0bb9f76f328d0541 Author: ModelHub XC Date: Wed Jul 8 12:55:06 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: bartowski/deepcogito_cogito-v1-preview-llama-3B-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..df1d305 --- /dev/null +++ b/README.md @@ -0,0 +1,171 @@ +--- +quantized_by: bartowski +pipeline_tag: text-generation +license: llama3.2 +base_model: deepcogito/cogito-v1-preview-llama-3B +base_model_relation: quantized +--- + +## Llamacpp imatrix Quantizations of cogito-v1-preview-llama-3B by deepcogito + +Using llama.cpp release b5074 for quantization. + +Original model: https://huggingface.co/deepcogito/cogito-v1-preview-llama-3B + +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_text|><|start_header_id|>system<|end_header_id|> + +{system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|> + +{prompt}<|eot_id|><|start_header_id|>assistant<|end_header_id|> +``` + +## Download a file (not the whole branch) from below: + +| Filename | Quant type | File Size | Split | Description | +| -------- | ---------- | --------- | ----- | ----------- | +| [cogito-v1-preview-llama-3B-bf16.gguf](https://huggingface.co/bartowski/deepcogito_cogito-v1-preview-llama-3B-GGUF/blob/main/deepcogito_cogito-v1-preview-llama-3B-bf16.gguf) | bf16 | 7.22GB | false | Full BF16 weights. | +| [cogito-v1-preview-llama-3B-Q8_0.gguf](https://huggingface.co/bartowski/deepcogito_cogito-v1-preview-llama-3B-GGUF/blob/main/deepcogito_cogito-v1-preview-llama-3B-Q8_0.gguf) | Q8_0 | 3.84GB | false | Extremely high quality, generally unneeded but max available quant. | +| [cogito-v1-preview-llama-3B-Q6_K_L.gguf](https://huggingface.co/bartowski/deepcogito_cogito-v1-preview-llama-3B-GGUF/blob/main/deepcogito_cogito-v1-preview-llama-3B-Q6_K_L.gguf) | Q6_K_L | 3.16GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. | +| [cogito-v1-preview-llama-3B-Q6_K.gguf](https://huggingface.co/bartowski/deepcogito_cogito-v1-preview-llama-3B-GGUF/blob/main/deepcogito_cogito-v1-preview-llama-3B-Q6_K.gguf) | Q6_K | 2.97GB | false | Very high quality, near perfect, *recommended*. | +| [cogito-v1-preview-llama-3B-Q5_K_L.gguf](https://huggingface.co/bartowski/deepcogito_cogito-v1-preview-llama-3B-GGUF/blob/main/deepcogito_cogito-v1-preview-llama-3B-Q5_K_L.gguf) | Q5_K_L | 2.84GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. | +| [cogito-v1-preview-llama-3B-Q5_K_M.gguf](https://huggingface.co/bartowski/deepcogito_cogito-v1-preview-llama-3B-GGUF/blob/main/deepcogito_cogito-v1-preview-llama-3B-Q5_K_M.gguf) | Q5_K_M | 2.59GB | false | High quality, *recommended*. | +| [cogito-v1-preview-llama-3B-Q5_K_S.gguf](https://huggingface.co/bartowski/deepcogito_cogito-v1-preview-llama-3B-GGUF/blob/main/deepcogito_cogito-v1-preview-llama-3B-Q5_K_S.gguf) | Q5_K_S | 2.54GB | false | High quality, *recommended*. | +| [cogito-v1-preview-llama-3B-Q4_K_L.gguf](https://huggingface.co/bartowski/deepcogito_cogito-v1-preview-llama-3B-GGUF/blob/main/deepcogito_cogito-v1-preview-llama-3B-Q4_K_L.gguf) | Q4_K_L | 2.53GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. | +| [cogito-v1-preview-llama-3B-Q4_1.gguf](https://huggingface.co/bartowski/deepcogito_cogito-v1-preview-llama-3B-GGUF/blob/main/deepcogito_cogito-v1-preview-llama-3B-Q4_1.gguf) | Q4_1 | 2.34GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. | +| [cogito-v1-preview-llama-3B-Q3_K_XL.gguf](https://huggingface.co/bartowski/deepcogito_cogito-v1-preview-llama-3B-GGUF/blob/main/deepcogito_cogito-v1-preview-llama-3B-Q3_K_XL.gguf) | Q3_K_XL | 2.33GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. | +| [cogito-v1-preview-llama-3B-Q4_K_M.gguf](https://huggingface.co/bartowski/deepcogito_cogito-v1-preview-llama-3B-GGUF/blob/main/deepcogito_cogito-v1-preview-llama-3B-Q4_K_M.gguf) | Q4_K_M | 2.24GB | false | Good quality, default size for most use cases, *recommended*. | +| [cogito-v1-preview-llama-3B-Q4_K_S.gguf](https://huggingface.co/bartowski/deepcogito_cogito-v1-preview-llama-3B-GGUF/blob/main/deepcogito_cogito-v1-preview-llama-3B-Q4_K_S.gguf) | Q4_K_S | 2.15GB | false | Slightly lower quality with more space savings, *recommended*. | +| [cogito-v1-preview-llama-3B-Q4_0.gguf](https://huggingface.co/bartowski/deepcogito_cogito-v1-preview-llama-3B-GGUF/blob/main/deepcogito_cogito-v1-preview-llama-3B-Q4_0.gguf) | Q4_0 | 2.14GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. | +| [cogito-v1-preview-llama-3B-IQ4_NL.gguf](https://huggingface.co/bartowski/deepcogito_cogito-v1-preview-llama-3B-GGUF/blob/main/deepcogito_cogito-v1-preview-llama-3B-IQ4_NL.gguf) | IQ4_NL | 2.14GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. | +| [cogito-v1-preview-llama-3B-IQ4_XS.gguf](https://huggingface.co/bartowski/deepcogito_cogito-v1-preview-llama-3B-GGUF/blob/main/deepcogito_cogito-v1-preview-llama-3B-IQ4_XS.gguf) | IQ4_XS | 2.04GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. | +| [cogito-v1-preview-llama-3B-Q3_K_L.gguf](https://huggingface.co/bartowski/deepcogito_cogito-v1-preview-llama-3B-GGUF/blob/main/deepcogito_cogito-v1-preview-llama-3B-Q3_K_L.gguf) | Q3_K_L | 1.98GB | false | Lower quality but usable, good for low RAM availability. | +| [cogito-v1-preview-llama-3B-Q2_K_L.gguf](https://huggingface.co/bartowski/deepcogito_cogito-v1-preview-llama-3B-GGUF/blob/main/deepcogito_cogito-v1-preview-llama-3B-Q2_K_L.gguf) | Q2_K_L | 1.88GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. | +| [cogito-v1-preview-llama-3B-Q3_K_M.gguf](https://huggingface.co/bartowski/deepcogito_cogito-v1-preview-llama-3B-GGUF/blob/main/deepcogito_cogito-v1-preview-llama-3B-Q3_K_M.gguf) | Q3_K_M | 1.86GB | false | Low quality. | +| [cogito-v1-preview-llama-3B-IQ3_M.gguf](https://huggingface.co/bartowski/deepcogito_cogito-v1-preview-llama-3B-GGUF/blob/main/deepcogito_cogito-v1-preview-llama-3B-IQ3_M.gguf) | IQ3_M | 1.77GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. | +| [cogito-v1-preview-llama-3B-Q3_K_S.gguf](https://huggingface.co/bartowski/deepcogito_cogito-v1-preview-llama-3B-GGUF/blob/main/deepcogito_cogito-v1-preview-llama-3B-Q3_K_S.gguf) | Q3_K_S | 1.71GB | false | Low quality, not recommended. | +| [cogito-v1-preview-llama-3B-IQ3_XS.gguf](https://huggingface.co/bartowski/deepcogito_cogito-v1-preview-llama-3B-GGUF/blob/main/deepcogito_cogito-v1-preview-llama-3B-IQ3_XS.gguf) | IQ3_XS | 1.65GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. | +| [cogito-v1-preview-llama-3B-IQ3_XXS.gguf](https://huggingface.co/bartowski/deepcogito_cogito-v1-preview-llama-3B-GGUF/blob/main/deepcogito_cogito-v1-preview-llama-3B-IQ3_XXS.gguf) | IQ3_XXS | 1.52GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. | +| [cogito-v1-preview-llama-3B-Q2_K.gguf](https://huggingface.co/bartowski/deepcogito_cogito-v1-preview-llama-3B-GGUF/blob/main/deepcogito_cogito-v1-preview-llama-3B-Q2_K.gguf) | Q2_K | 1.49GB | false | Very low quality but surprisingly usable. | +| [cogito-v1-preview-llama-3B-IQ2_M.gguf](https://huggingface.co/bartowski/deepcogito_cogito-v1-preview-llama-3B-GGUF/blob/main/deepcogito_cogito-v1-preview-llama-3B-IQ2_M.gguf) | IQ2_M | 1.40GB | 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/deepcogito_cogito-v1-preview-llama-3B-GGUF --include "deepcogito_cogito-v1-preview-llama-3B-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/deepcogito_cogito-v1-preview-llama-3B-GGUF --include "deepcogito_cogito-v1-preview-llama-3B-Q8_0/*" --local-dir ./ +``` + +You can either specify a new local-dir (deepcogito_cogito-v1-preview-llama-3B-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/deepcogito_cogito-v1-preview-llama-3B-IQ2_M.gguf b/deepcogito_cogito-v1-preview-llama-3B-IQ2_M.gguf new file mode 100644 index 0000000..a08612e --- /dev/null +++ b/deepcogito_cogito-v1-preview-llama-3B-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50228f2cba06f88fdc854a4f98eb070c78a050afea88b2d8b3cafe93c87f6497 +size 1398330592 diff --git a/deepcogito_cogito-v1-preview-llama-3B-IQ3_M.gguf b/deepcogito_cogito-v1-preview-llama-3B-IQ3_M.gguf new file mode 100644 index 0000000..3125453 --- /dev/null +++ b/deepcogito_cogito-v1-preview-llama-3B-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d978a97cf7e76a05cffc9cf6c16cece64f5754e5fecb476f58df29a641cc5653 +size 1768967392 diff --git a/deepcogito_cogito-v1-preview-llama-3B-IQ3_XS.gguf b/deepcogito_cogito-v1-preview-llama-3B-IQ3_XS.gguf new file mode 100644 index 0000000..e1d1567 --- /dev/null +++ b/deepcogito_cogito-v1-preview-llama-3B-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9963b10fb3bbce817a9207a1197b2796a3b642bed3b19f4070557e8cdd125c90 +size 1646087392 diff --git a/deepcogito_cogito-v1-preview-llama-3B-IQ3_XXS.gguf b/deepcogito_cogito-v1-preview-llama-3B-IQ3_XXS.gguf new file mode 100644 index 0000000..3e1bd00 --- /dev/null +++ b/deepcogito_cogito-v1-preview-llama-3B-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49b01ad9096baa8058b0396b2a2366f64c94ed630d6533dab8a4b7eff065c63b +size 1518064864 diff --git a/deepcogito_cogito-v1-preview-llama-3B-IQ4_NL.gguf b/deepcogito_cogito-v1-preview-llama-3B-IQ4_NL.gguf new file mode 100644 index 0000000..e8ee758 --- /dev/null +++ b/deepcogito_cogito-v1-preview-llama-3B-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13aa6612904db9d23c1c95df2d3bb535d89d131f1f1b28f0f265949d44d32f2c +size 2138817760 diff --git a/deepcogito_cogito-v1-preview-llama-3B-IQ4_XS.gguf b/deepcogito_cogito-v1-preview-llama-3B-IQ4_XS.gguf new file mode 100644 index 0000000..893563f --- /dev/null +++ b/deepcogito_cogito-v1-preview-llama-3B-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:460a046001788d8975536c6ca5f5981c595a9ef69aed9371194f8b593270571b +size 2038424800 diff --git a/deepcogito_cogito-v1-preview-llama-3B-Q2_K.gguf b/deepcogito_cogito-v1-preview-llama-3B-Q2_K.gguf new file mode 100644 index 0000000..cf06e65 --- /dev/null +++ b/deepcogito_cogito-v1-preview-llama-3B-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33e0a8892d763a05fe62c62c37aa76a5314cc0e7258fed1930ac05fdc8cd8d06 +size 1493218528 diff --git a/deepcogito_cogito-v1-preview-llama-3B-Q2_K_L.gguf b/deepcogito_cogito-v1-preview-llama-3B-Q2_K_L.gguf new file mode 100644 index 0000000..a2b1771 --- /dev/null +++ b/deepcogito_cogito-v1-preview-llama-3B-Q2_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a32b98bf05d5a7149f078c604c3703e5e2985e08bde93c7c9232e410a1b7d123 +size 1877986528 diff --git a/deepcogito_cogito-v1-preview-llama-3B-Q3_K_L.gguf b/deepcogito_cogito-v1-preview-llama-3B-Q3_K_L.gguf new file mode 100644 index 0000000..c2d30c0 --- /dev/null +++ b/deepcogito_cogito-v1-preview-llama-3B-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e49084d55f08338e42f94f9c947d0415430068f0ab27e0c8a0fd20612bfb56eb +size 1984646368 diff --git a/deepcogito_cogito-v1-preview-llama-3B-Q3_K_M.gguf b/deepcogito_cogito-v1-preview-llama-3B-Q3_K_M.gguf new file mode 100644 index 0000000..fcbf1b8 --- /dev/null +++ b/deepcogito_cogito-v1-preview-llama-3B-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89bb4eeb4bd915928b3d64ea31d986b30bb9b9e19623b04ca0fab3641077016f +size 1856457952 diff --git a/deepcogito_cogito-v1-preview-llama-3B-Q3_K_S.gguf b/deepcogito_cogito-v1-preview-llama-3B-Q3_K_S.gguf new file mode 100644 index 0000000..0cd4af6 --- /dev/null +++ b/deepcogito_cogito-v1-preview-llama-3B-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dff1f7cfefe963b21d17d9663fca9c3d867c9add16f8d06fc8a5adb20e46ea45 +size 1712147680 diff --git a/deepcogito_cogito-v1-preview-llama-3B-Q3_K_XL.gguf b/deepcogito_cogito-v1-preview-llama-3B-Q3_K_XL.gguf new file mode 100644 index 0000000..8a19172 --- /dev/null +++ b/deepcogito_cogito-v1-preview-llama-3B-Q3_K_XL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83494bf321209c29b94459acbd4d7d02cbb3f89b667a960cc8ac32ffa8bb6101 +size 2329398496 diff --git a/deepcogito_cogito-v1-preview-llama-3B-Q4_0.gguf b/deepcogito_cogito-v1-preview-llama-3B-Q4_0.gguf new file mode 100644 index 0000000..04980ab --- /dev/null +++ b/deepcogito_cogito-v1-preview-llama-3B-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1bef4cf7a81d14ab63b53a8845898c895a3a23e8c28678a6184de6325e9ab52 +size 2143536352 diff --git a/deepcogito_cogito-v1-preview-llama-3B-Q4_1.gguf b/deepcogito_cogito-v1-preview-llama-3B-Q4_1.gguf new file mode 100644 index 0000000..0f433ca --- /dev/null +++ b/deepcogito_cogito-v1-preview-llama-3B-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba559ed76a5adadb9bd5b44dadccc2a185e99dac7c9beb4a725ad4bce368807b +size 2339603680 diff --git a/deepcogito_cogito-v1-preview-llama-3B-Q4_K_L.gguf b/deepcogito_cogito-v1-preview-llama-3B-Q4_K_L.gguf new file mode 100644 index 0000000..3231a47 --- /dev/null +++ b/deepcogito_cogito-v1-preview-llama-3B-Q4_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52326592e60ac49330095c7a62da93768efed91344a143469cc572550265277c +size 2533428448 diff --git a/deepcogito_cogito-v1-preview-llama-3B-Q4_K_M.gguf b/deepcogito_cogito-v1-preview-llama-3B-Q4_K_M.gguf new file mode 100644 index 0000000..f793d41 --- /dev/null +++ b/deepcogito_cogito-v1-preview-llama-3B-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:726a0ef5f818b8d238f2844f3204848bea66fb9c172b8ae0f6dc51b7bc081dd5 +size 2241004768 diff --git a/deepcogito_cogito-v1-preview-llama-3B-Q4_K_S.gguf b/deepcogito_cogito-v1-preview-llama-3B-Q4_K_S.gguf new file mode 100644 index 0000000..c9f13a7 --- /dev/null +++ b/deepcogito_cogito-v1-preview-llama-3B-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01dad2c5314bb1197bafbc97211dae1ca2e0d031541906bb25047f159d534de2 +size 2149827808 diff --git a/deepcogito_cogito-v1-preview-llama-3B-Q5_K_L.gguf b/deepcogito_cogito-v1-preview-llama-3B-Q5_K_L.gguf new file mode 100644 index 0000000..4add527 --- /dev/null +++ b/deepcogito_cogito-v1-preview-llama-3B-Q5_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e278912fa117757ac0fe9a2fd7101a4e3a28743d3d95f74ebd4a3fe0cb873860 +size 2836204768 diff --git a/deepcogito_cogito-v1-preview-llama-3B-Q5_K_M.gguf b/deepcogito_cogito-v1-preview-llama-3B-Q5_K_M.gguf new file mode 100644 index 0000000..a3d3cf8 --- /dev/null +++ b/deepcogito_cogito-v1-preview-llama-3B-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b277fac0b93e8050ef5e190eb866e5547df2f6c5d4b2aa9479385ae33c5e5024 +size 2593031392 diff --git a/deepcogito_cogito-v1-preview-llama-3B-Q5_K_S.gguf b/deepcogito_cogito-v1-preview-llama-3B-Q5_K_S.gguf new file mode 100644 index 0000000..90455dd --- /dev/null +++ b/deepcogito_cogito-v1-preview-llama-3B-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fdfb6c6129c1214c2bb7320556b118ca57fd38aa9f25933ff75856577f05ce4f +size 2540389600 diff --git a/deepcogito_cogito-v1-preview-llama-3B-Q6_K.gguf b/deepcogito_cogito-v1-preview-llama-3B-Q6_K.gguf new file mode 100644 index 0000000..9985528 --- /dev/null +++ b/deepcogito_cogito-v1-preview-llama-3B-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f8ef18ce36e5bacd5485cfcef29f4e36d161201d8889c19ccc498fd48389fa8 +size 2967059680 diff --git a/deepcogito_cogito-v1-preview-llama-3B-Q6_K_L.gguf b/deepcogito_cogito-v1-preview-llama-3B-Q6_K_L.gguf new file mode 100644 index 0000000..22bb39e --- /dev/null +++ b/deepcogito_cogito-v1-preview-llama-3B-Q6_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4bad367d0f3ae051b1669de61ee7a2b039518352459fe2bcc48583f5f152b8ae +size 3157904608 diff --git a/deepcogito_cogito-v1-preview-llama-3B-Q8_0.gguf b/deepcogito_cogito-v1-preview-llama-3B-Q8_0.gguf new file mode 100644 index 0000000..1faed32 --- /dev/null +++ b/deepcogito_cogito-v1-preview-llama-3B-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ff07f6809d4e66165a027f5ef24c2b7659295461d9c9312805f233e2c25d452 +size 3840527584 diff --git a/deepcogito_cogito-v1-preview-llama-3B-bf16.gguf b/deepcogito_cogito-v1-preview-llama-3B-bf16.gguf new file mode 100644 index 0000000..40f70ec --- /dev/null +++ b/deepcogito_cogito-v1-preview-llama-3B-bf16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62c19a0ab4dd0a6c8045abe56a9a2c4cea5ff73fda761b5fc7487db9f6de1568 +size 7221693344 diff --git a/deepcogito_cogito-v1-preview-llama-3B.imatrix b/deepcogito_cogito-v1-preview-llama-3B.imatrix new file mode 100644 index 0000000..994f01f Binary files /dev/null and b/deepcogito_cogito-v1-preview-llama-3B.imatrix differ