From 21d0bdec5a9a0b42b058b92d0253fdf31d4e44d1 Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Sat, 19 Sep 2026 09:45:12 +0800 Subject: [PATCH] =?UTF-8?q?=E5=88=9D=E5=A7=8B=E5=8C=96=E9=A1=B9=E7=9B=AE?= =?UTF-8?q?=EF=BC=8C=E7=94=B1ModelHub=20XC=E7=A4=BE=E5=8C=BA=E6=8F=90?= =?UTF-8?q?=E4=BE=9B=E6=A8=A1=E5=9E=8B?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Model: bartowski/janhq_Jan-v1-4B-GGUF Source: Original Platform --- .gitattributes | 47 ++++++++++ README.md | 164 +++++++++++++++++++++++++++++++++++ configuration.json | 1 + janhq_Jan-v1-4B-IQ2_M.gguf | 3 + janhq_Jan-v1-4B-IQ3_M.gguf | 3 + janhq_Jan-v1-4B-IQ3_XS.gguf | 3 + janhq_Jan-v1-4B-IQ3_XXS.gguf | 3 + janhq_Jan-v1-4B-IQ4_NL.gguf | 3 + janhq_Jan-v1-4B-IQ4_XS.gguf | 3 + janhq_Jan-v1-4B-Q2_K.gguf | 3 + janhq_Jan-v1-4B-Q2_K_L.gguf | 3 + janhq_Jan-v1-4B-Q3_K_L.gguf | 3 + janhq_Jan-v1-4B-Q3_K_M.gguf | 3 + janhq_Jan-v1-4B-Q3_K_S.gguf | 3 + janhq_Jan-v1-4B-Q3_K_XL.gguf | 3 + janhq_Jan-v1-4B-Q4_0.gguf | 3 + janhq_Jan-v1-4B-Q4_1.gguf | 3 + janhq_Jan-v1-4B-Q4_K_L.gguf | 3 + janhq_Jan-v1-4B-Q4_K_M.gguf | 3 + janhq_Jan-v1-4B-Q4_K_S.gguf | 3 + janhq_Jan-v1-4B-Q5_K_L.gguf | 3 + janhq_Jan-v1-4B-Q5_K_M.gguf | 3 + janhq_Jan-v1-4B-Q5_K_S.gguf | 3 + janhq_Jan-v1-4B-Q6_K.gguf | 3 + janhq_Jan-v1-4B-Q6_K_L.gguf | 3 + janhq_Jan-v1-4B-Q8_0.gguf | 3 + janhq_Jan-v1-4B-bf16.gguf | 3 + janhq_Jan-v1-4B-imatrix.gguf | 3 + 28 files changed, 287 insertions(+) create mode 100644 .gitattributes create mode 100644 README.md create mode 100644 configuration.json create mode 100644 janhq_Jan-v1-4B-IQ2_M.gguf create mode 100644 janhq_Jan-v1-4B-IQ3_M.gguf create mode 100644 janhq_Jan-v1-4B-IQ3_XS.gguf create mode 100644 janhq_Jan-v1-4B-IQ3_XXS.gguf create mode 100644 janhq_Jan-v1-4B-IQ4_NL.gguf create mode 100644 janhq_Jan-v1-4B-IQ4_XS.gguf create mode 100644 janhq_Jan-v1-4B-Q2_K.gguf create mode 100644 janhq_Jan-v1-4B-Q2_K_L.gguf create mode 100644 janhq_Jan-v1-4B-Q3_K_L.gguf create mode 100644 janhq_Jan-v1-4B-Q3_K_M.gguf create mode 100644 janhq_Jan-v1-4B-Q3_K_S.gguf create mode 100644 janhq_Jan-v1-4B-Q3_K_XL.gguf create mode 100644 janhq_Jan-v1-4B-Q4_0.gguf create mode 100644 janhq_Jan-v1-4B-Q4_1.gguf create mode 100644 janhq_Jan-v1-4B-Q4_K_L.gguf create mode 100644 janhq_Jan-v1-4B-Q4_K_M.gguf create mode 100644 janhq_Jan-v1-4B-Q4_K_S.gguf create mode 100644 janhq_Jan-v1-4B-Q5_K_L.gguf create mode 100644 janhq_Jan-v1-4B-Q5_K_M.gguf create mode 100644 janhq_Jan-v1-4B-Q5_K_S.gguf create mode 100644 janhq_Jan-v1-4B-Q6_K.gguf create mode 100644 janhq_Jan-v1-4B-Q6_K_L.gguf create mode 100644 janhq_Jan-v1-4B-Q8_0.gguf create mode 100644 janhq_Jan-v1-4B-bf16.gguf create mode 100644 janhq_Jan-v1-4B-imatrix.gguf 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..e0e1969 --- /dev/null +++ b/README.md @@ -0,0 +1,164 @@ +--- +quantized_by: bartowski +pipeline_tag: text-generation +base_model_relation: quantized +base_model: janhq/Jan-v1-4B +--- + +## Llamacpp imatrix Quantizations of Jan-v1-4B by janhq + +Using llama.cpp release b6115 for quantization. + +Original model: https://huggingface.co/janhq/Jan-v1-4B + +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/ggerganov/llama.cpp), or any other llama.cpp based project + +## Prompt format + +No prompt format found, check original model page + +## Download a file (not the whole branch) from below: + +| Filename | Quant type | File Size | Split | Description | +| -------- | ---------- | --------- | ----- | ----------- | +| [Jan-v1-4B-bf16.gguf](https://huggingface.co/bartowski/janhq_Jan-v1-4B-GGUF/blob/main/janhq_Jan-v1-4B-bf16.gguf) | bf16 | 8.05GB | false | Full BF16 weights. | +| [Jan-v1-4B-Q8_0.gguf](https://huggingface.co/bartowski/janhq_Jan-v1-4B-GGUF/blob/main/janhq_Jan-v1-4B-Q8_0.gguf) | Q8_0 | 4.28GB | false | Extremely high quality, generally unneeded but max available quant. | +| [Jan-v1-4B-Q6_K_L.gguf](https://huggingface.co/bartowski/janhq_Jan-v1-4B-GGUF/blob/main/janhq_Jan-v1-4B-Q6_K_L.gguf) | Q6_K_L | 3.40GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. | +| [Jan-v1-4B-Q6_K.gguf](https://huggingface.co/bartowski/janhq_Jan-v1-4B-GGUF/blob/main/janhq_Jan-v1-4B-Q6_K.gguf) | Q6_K | 3.31GB | false | Very high quality, near perfect, *recommended*. | +| [Jan-v1-4B-Q5_K_L.gguf](https://huggingface.co/bartowski/janhq_Jan-v1-4B-GGUF/blob/main/janhq_Jan-v1-4B-Q5_K_L.gguf) | Q5_K_L | 2.98GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. | +| [Jan-v1-4B-Q5_K_M.gguf](https://huggingface.co/bartowski/janhq_Jan-v1-4B-GGUF/blob/main/janhq_Jan-v1-4B-Q5_K_M.gguf) | Q5_K_M | 2.89GB | false | High quality, *recommended*. | +| [Jan-v1-4B-Q5_K_S.gguf](https://huggingface.co/bartowski/janhq_Jan-v1-4B-GGUF/blob/main/janhq_Jan-v1-4B-Q5_K_S.gguf) | Q5_K_S | 2.82GB | false | High quality, *recommended*. | +| [Jan-v1-4B-Q4_1.gguf](https://huggingface.co/bartowski/janhq_Jan-v1-4B-GGUF/blob/main/janhq_Jan-v1-4B-Q4_1.gguf) | Q4_1 | 2.60GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. | +| [Jan-v1-4B-Q4_K_L.gguf](https://huggingface.co/bartowski/janhq_Jan-v1-4B-GGUF/blob/main/janhq_Jan-v1-4B-Q4_K_L.gguf) | Q4_K_L | 2.59GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. | +| [Jan-v1-4B-Q4_K_M.gguf](https://huggingface.co/bartowski/janhq_Jan-v1-4B-GGUF/blob/main/janhq_Jan-v1-4B-Q4_K_M.gguf) | Q4_K_M | 2.50GB | false | Good quality, default size for most use cases, *recommended*. | +| [Jan-v1-4B-Q4_K_S.gguf](https://huggingface.co/bartowski/janhq_Jan-v1-4B-GGUF/blob/main/janhq_Jan-v1-4B-Q4_K_S.gguf) | Q4_K_S | 2.38GB | false | Slightly lower quality with more space savings, *recommended*. | +| [Jan-v1-4B-Q4_0.gguf](https://huggingface.co/bartowski/janhq_Jan-v1-4B-GGUF/blob/main/janhq_Jan-v1-4B-Q4_0.gguf) | Q4_0 | 2.38GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. | +| [Jan-v1-4B-IQ4_NL.gguf](https://huggingface.co/bartowski/janhq_Jan-v1-4B-GGUF/blob/main/janhq_Jan-v1-4B-IQ4_NL.gguf) | IQ4_NL | 2.38GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. | +| [Jan-v1-4B-Q3_K_XL.gguf](https://huggingface.co/bartowski/janhq_Jan-v1-4B-GGUF/blob/main/janhq_Jan-v1-4B-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. | +| [Jan-v1-4B-IQ4_XS.gguf](https://huggingface.co/bartowski/janhq_Jan-v1-4B-GGUF/blob/main/janhq_Jan-v1-4B-IQ4_XS.gguf) | IQ4_XS | 2.27GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. | +| [Jan-v1-4B-Q3_K_L.gguf](https://huggingface.co/bartowski/janhq_Jan-v1-4B-GGUF/blob/main/janhq_Jan-v1-4B-Q3_K_L.gguf) | Q3_K_L | 2.24GB | false | Lower quality but usable, good for low RAM availability. | +| [Jan-v1-4B-Q3_K_M.gguf](https://huggingface.co/bartowski/janhq_Jan-v1-4B-GGUF/blob/main/janhq_Jan-v1-4B-Q3_K_M.gguf) | Q3_K_M | 2.08GB | false | Low quality. | +| [Jan-v1-4B-IQ3_M.gguf](https://huggingface.co/bartowski/janhq_Jan-v1-4B-GGUF/blob/main/janhq_Jan-v1-4B-IQ3_M.gguf) | IQ3_M | 1.96GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. | +| [Jan-v1-4B-Q3_K_S.gguf](https://huggingface.co/bartowski/janhq_Jan-v1-4B-GGUF/blob/main/janhq_Jan-v1-4B-Q3_K_S.gguf) | Q3_K_S | 1.89GB | false | Low quality, not recommended. | +| [Jan-v1-4B-IQ3_XS.gguf](https://huggingface.co/bartowski/janhq_Jan-v1-4B-GGUF/blob/main/janhq_Jan-v1-4B-IQ3_XS.gguf) | IQ3_XS | 1.81GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. | +| [Jan-v1-4B-Q2_K_L.gguf](https://huggingface.co/bartowski/janhq_Jan-v1-4B-GGUF/blob/main/janhq_Jan-v1-4B-Q2_K_L.gguf) | Q2_K_L | 1.76GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. | +| [Jan-v1-4B-IQ3_XXS.gguf](https://huggingface.co/bartowski/janhq_Jan-v1-4B-GGUF/blob/main/janhq_Jan-v1-4B-IQ3_XXS.gguf) | IQ3_XXS | 1.67GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. | +| [Jan-v1-4B-Q2_K.gguf](https://huggingface.co/bartowski/janhq_Jan-v1-4B-GGUF/blob/main/janhq_Jan-v1-4B-Q2_K.gguf) | Q2_K | 1.67GB | false | Very low quality but surprisingly usable. | +| [Jan-v1-4B-IQ2_M.gguf](https://huggingface.co/bartowski/janhq_Jan-v1-4B-GGUF/blob/main/janhq_Jan-v1-4B-IQ2_M.gguf) | IQ2_M | 1.51GB | 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/janhq_Jan-v1-4B-GGUF --include "janhq_Jan-v1-4B-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/janhq_Jan-v1-4B-GGUF --include "janhq_Jan-v1-4B-Q8_0/*" --local-dir ./ +``` + +You can either specify a new local-dir (janhq_Jan-v1-4B-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/janhq_Jan-v1-4B-IQ2_M.gguf b/janhq_Jan-v1-4B-IQ2_M.gguf new file mode 100644 index 0000000..b72119e --- /dev/null +++ b/janhq_Jan-v1-4B-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc79ef03fa94d47448d7890406fed974f01f0fc236d42b2c7dc8fa097c3641fa +size 1512984928 diff --git a/janhq_Jan-v1-4B-IQ3_M.gguf b/janhq_Jan-v1-4B-IQ3_M.gguf new file mode 100644 index 0000000..7affea2 --- /dev/null +++ b/janhq_Jan-v1-4B-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66ba9f07f6e53b0fd5a0aa7c6c6083da81efd2e2a358afbb7dd7cfbf0850064b +size 1962897248 diff --git a/janhq_Jan-v1-4B-IQ3_XS.gguf b/janhq_Jan-v1-4B-IQ3_XS.gguf new file mode 100644 index 0000000..49c1ab7 --- /dev/null +++ b/janhq_Jan-v1-4B-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b57f45c5b5816dd20a2c9d6c9d5af8f6657cc44861f91d4694c68dcefb26e464 +size 1814376288 diff --git a/janhq_Jan-v1-4B-IQ3_XXS.gguf b/janhq_Jan-v1-4B-IQ3_XXS.gguf new file mode 100644 index 0000000..081ae43 --- /dev/null +++ b/janhq_Jan-v1-4B-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f10459c24b0ebaf33a1d49e42c0fd531a3c478c59019c29d2e3b8eeaeacd22a5 +size 1670189408 diff --git a/janhq_Jan-v1-4B-IQ4_NL.gguf b/janhq_Jan-v1-4B-IQ4_NL.gguf new file mode 100644 index 0000000..edd7ad6 --- /dev/null +++ b/janhq_Jan-v1-4B-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:419e43a6494307c823032d1b92a107bf028090b39990b8e91026c9139c5e10e6 +size 2381344608 diff --git a/janhq_Jan-v1-4B-IQ4_XS.gguf b/janhq_Jan-v1-4B-IQ4_XS.gguf new file mode 100644 index 0000000..7024dde --- /dev/null +++ b/janhq_Jan-v1-4B-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4d5458dc212e0846315e2e0597e7352f08c5967c44250d62b0cd740772d61b4 +size 2270752608 diff --git a/janhq_Jan-v1-4B-Q2_K.gguf b/janhq_Jan-v1-4B-Q2_K.gguf new file mode 100644 index 0000000..301c059 --- /dev/null +++ b/janhq_Jan-v1-4B-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8f0d69156efb92b79221f8fc16e872fcfea07d3384f5bd7638cde634eac887f +size 1669500768 diff --git a/janhq_Jan-v1-4B-Q2_K_L.gguf b/janhq_Jan-v1-4B-Q2_K_L.gguf new file mode 100644 index 0000000..e852e96 --- /dev/null +++ b/janhq_Jan-v1-4B-Q2_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e475ab2cd9ee53b15efaba12fa3629abb1750e318c9573631e9e9534cd193339 +size 1763701088 diff --git a/janhq_Jan-v1-4B-Q3_K_L.gguf b/janhq_Jan-v1-4B-Q3_K_L.gguf new file mode 100644 index 0000000..0459d8b --- /dev/null +++ b/janhq_Jan-v1-4B-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a87cace7ee60e2e711d98c57ba4a4016755d7490af68ae0493b8f39b87018c9 +size 2239786848 diff --git a/janhq_Jan-v1-4B-Q3_K_M.gguf b/janhq_Jan-v1-4B-Q3_K_M.gguf new file mode 100644 index 0000000..a9cc560 --- /dev/null +++ b/janhq_Jan-v1-4B-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a0b1edfc84b78d21edfd0e5dc3469f8681197d450a8d704c6e182e6c84d06e5 +size 2075619168 diff --git a/janhq_Jan-v1-4B-Q3_K_S.gguf b/janhq_Jan-v1-4B-Q3_K_S.gguf new file mode 100644 index 0000000..c09aec7 --- /dev/null +++ b/janhq_Jan-v1-4B-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69adbeaea4ea21ce2df464dd610a205f82f92a6b130d11ce7e5ad5515648e6f9 +size 1886998368 diff --git a/janhq_Jan-v1-4B-Q3_K_XL.gguf b/janhq_Jan-v1-4B-Q3_K_XL.gguf new file mode 100644 index 0000000..cd8d462 --- /dev/null +++ b/janhq_Jan-v1-4B-Q3_K_XL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62d30e21cf648547223130fa5525f2d875011cde0a7bf07572def752a97c0eac +size 2333987168 diff --git a/janhq_Jan-v1-4B-Q4_0.gguf b/janhq_Jan-v1-4B-Q4_0.gguf new file mode 100644 index 0000000..f553902 --- /dev/null +++ b/janhq_Jan-v1-4B-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f1e6ad7c8a5d8856f15b7c971064ce18275d81663e279050751eb6191405e05 +size 2375774048 diff --git a/janhq_Jan-v1-4B-Q4_1.gguf b/janhq_Jan-v1-4B-Q4_1.gguf new file mode 100644 index 0000000..5fc1e00 --- /dev/null +++ b/janhq_Jan-v1-4B-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7e81c5bd42dbed10a00f92911038d3bc8e669cc76445cb66cade2d7035a415e +size 2596630368 diff --git a/janhq_Jan-v1-4B-Q4_K_L.gguf b/janhq_Jan-v1-4B-Q4_K_L.gguf new file mode 100644 index 0000000..843650b --- /dev/null +++ b/janhq_Jan-v1-4B-Q4_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba9b0b25ac7591e1d3c0f010bdc09aeb935d716e79f2763bf80076b03e19e1a0 +size 2591482208 diff --git a/janhq_Jan-v1-4B-Q4_K_M.gguf b/janhq_Jan-v1-4B-Q4_K_M.gguf new file mode 100644 index 0000000..8850946 --- /dev/null +++ b/janhq_Jan-v1-4B-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b9ed12488e20c4a66a248c153edef5a32d6be650041d1bd9699c6262a4eefe9 +size 2497281888 diff --git a/janhq_Jan-v1-4B-Q4_K_S.gguf b/janhq_Jan-v1-4B-Q4_K_S.gguf new file mode 100644 index 0000000..da31d7e --- /dev/null +++ b/janhq_Jan-v1-4B-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:949f8bdd99294aa0bd21886ab9929828d1c302827e8f26e7f1f9b9ac9ed1f307 +size 2383310688 diff --git a/janhq_Jan-v1-4B-Q5_K_L.gguf b/janhq_Jan-v1-4B-Q5_K_L.gguf new file mode 100644 index 0000000..326f32e --- /dev/null +++ b/janhq_Jan-v1-4B-Q5_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:800363dd50e57de1ade0c111ef80912c0ebfcd7e4bbc2f66c0638dba1c816110 +size 2983715168 diff --git a/janhq_Jan-v1-4B-Q5_K_M.gguf b/janhq_Jan-v1-4B-Q5_K_M.gguf new file mode 100644 index 0000000..b535342 --- /dev/null +++ b/janhq_Jan-v1-4B-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d4a9f1fc318d13eec20ba35d21fce4e04fb3470a781baa8964846c6774b398e +size 2889514848 diff --git a/janhq_Jan-v1-4B-Q5_K_S.gguf b/janhq_Jan-v1-4B-Q5_K_S.gguf new file mode 100644 index 0000000..6af2098 --- /dev/null +++ b/janhq_Jan-v1-4B-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3fd1257c7deab2e8a546512881b101a31678a9e34d39030a949a3d621a79755 +size 2823712608 diff --git a/janhq_Jan-v1-4B-Q6_K.gguf b/janhq_Jan-v1-4B-Q6_K.gguf new file mode 100644 index 0000000..d8610f5 --- /dev/null +++ b/janhq_Jan-v1-4B-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31c58b042dd4b3f99354dff2560d879525db1aa01420133f067a34e3c3e288f9 +size 3306262368 diff --git a/janhq_Jan-v1-4B-Q6_K_L.gguf b/janhq_Jan-v1-4B-Q6_K_L.gguf new file mode 100644 index 0000000..b2d7c8f --- /dev/null +++ b/janhq_Jan-v1-4B-Q6_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec08591dff2ed9143ca577ad44422848db08d57b97ada78d9a1986805b04831b +size 3400462688 diff --git a/janhq_Jan-v1-4B-Q8_0.gguf b/janhq_Jan-v1-4B-Q8_0.gguf new file mode 100644 index 0000000..dac79d1 --- /dev/null +++ b/janhq_Jan-v1-4B-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53ac3c1b4911681a8d25468a7e903249e89838355a05de9ebee305fde296db53 +size 4280406368 diff --git a/janhq_Jan-v1-4B-bf16.gguf b/janhq_Jan-v1-4B-bf16.gguf new file mode 100644 index 0000000..de9f27c --- /dev/null +++ b/janhq_Jan-v1-4B-bf16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5568e217ff22e471849ac973789ad8f9a7008e020525783de329687bb6714aee +size 8051286080 diff --git a/janhq_Jan-v1-4B-imatrix.gguf b/janhq_Jan-v1-4B-imatrix.gguf new file mode 100644 index 0000000..0919764 --- /dev/null +++ b/janhq_Jan-v1-4B-imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33af42ebe6e3f6c5bc3b2649e2f4f0b8c8b9d939c0a141beaa2f764e9f3934fe +size 3872640