commit 699a572c17e0c2fc765728adcbc146bb22d9a6ff Author: ModelHub XC Date: Tue Sep 22 14:24:14 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: bartowski/katanemo_Arch-Function-Chat-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..cd4f399 --- /dev/null +++ b/README.md @@ -0,0 +1,175 @@ +--- +quantized_by: bartowski +pipeline_tag: text-generation +base_model_relation: quantized +license_name: katanemo-research +base_model: katanemo/Arch-Function-Chat-3B +language: +- en +license: other +license_link: https://huggingface.co/katanemo/Arch-Function-Chat-3B/blob/main/LICENSE +--- + +## Llamacpp imatrix Quantizations of Arch-Function-Chat-3B by katanemo + +Using llama.cpp release b5010 for quantization. + +Original model: https://huggingface.co/katanemo/Arch-Function-Chat-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 + +``` +<|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 | +| -------- | ---------- | --------- | ----- | ----------- | +| [Arch-Function-Chat-3B-bf16.gguf](https://huggingface.co/bartowski/katanemo_Arch-Function-Chat-3B-GGUF/blob/main/katanemo_Arch-Function-Chat-3B-bf16.gguf) | bf16 | 6.18GB | false | Full BF16 weights. | +| [Arch-Function-Chat-3B-Q8_0.gguf](https://huggingface.co/bartowski/katanemo_Arch-Function-Chat-3B-GGUF/blob/main/katanemo_Arch-Function-Chat-3B-Q8_0.gguf) | Q8_0 | 3.29GB | false | Extremely high quality, generally unneeded but max available quant. | +| [Arch-Function-Chat-3B-Q6_K_L.gguf](https://huggingface.co/bartowski/katanemo_Arch-Function-Chat-3B-GGUF/blob/main/katanemo_Arch-Function-Chat-3B-Q6_K_L.gguf) | Q6_K_L | 2.61GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. | +| [Arch-Function-Chat-3B-Q6_K.gguf](https://huggingface.co/bartowski/katanemo_Arch-Function-Chat-3B-GGUF/blob/main/katanemo_Arch-Function-Chat-3B-Q6_K.gguf) | Q6_K | 2.54GB | false | Very high quality, near perfect, *recommended*. | +| [Arch-Function-Chat-3B-Q5_K_L.gguf](https://huggingface.co/bartowski/katanemo_Arch-Function-Chat-3B-GGUF/blob/main/katanemo_Arch-Function-Chat-3B-Q5_K_L.gguf) | Q5_K_L | 2.30GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. | +| [Arch-Function-Chat-3B-Q5_K_M.gguf](https://huggingface.co/bartowski/katanemo_Arch-Function-Chat-3B-GGUF/blob/main/katanemo_Arch-Function-Chat-3B-Q5_K_M.gguf) | Q5_K_M | 2.22GB | false | High quality, *recommended*. | +| [Arch-Function-Chat-3B-Q5_K_S.gguf](https://huggingface.co/bartowski/katanemo_Arch-Function-Chat-3B-GGUF/blob/main/katanemo_Arch-Function-Chat-3B-Q5_K_S.gguf) | Q5_K_S | 2.17GB | false | High quality, *recommended*. | +| [Arch-Function-Chat-3B-Q4_K_L.gguf](https://huggingface.co/bartowski/katanemo_Arch-Function-Chat-3B-GGUF/blob/main/katanemo_Arch-Function-Chat-3B-Q4_K_L.gguf) | Q4_K_L | 2.01GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. | +| [Arch-Function-Chat-3B-Q4_1.gguf](https://huggingface.co/bartowski/katanemo_Arch-Function-Chat-3B-GGUF/blob/main/katanemo_Arch-Function-Chat-3B-Q4_1.gguf) | Q4_1 | 2.00GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. | +| [Arch-Function-Chat-3B-Q4_K_M.gguf](https://huggingface.co/bartowski/katanemo_Arch-Function-Chat-3B-GGUF/blob/main/katanemo_Arch-Function-Chat-3B-Q4_K_M.gguf) | Q4_K_M | 1.93GB | false | Good quality, default size for most use cases, *recommended*. | +| [Arch-Function-Chat-3B-Q4_K_S.gguf](https://huggingface.co/bartowski/katanemo_Arch-Function-Chat-3B-GGUF/blob/main/katanemo_Arch-Function-Chat-3B-Q4_K_S.gguf) | Q4_K_S | 1.83GB | false | Slightly lower quality with more space savings, *recommended*. | +| [Arch-Function-Chat-3B-Q4_0.gguf](https://huggingface.co/bartowski/katanemo_Arch-Function-Chat-3B-GGUF/blob/main/katanemo_Arch-Function-Chat-3B-Q4_0.gguf) | Q4_0 | 1.83GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. | +| [Arch-Function-Chat-3B-IQ4_NL.gguf](https://huggingface.co/bartowski/katanemo_Arch-Function-Chat-3B-GGUF/blob/main/katanemo_Arch-Function-Chat-3B-IQ4_NL.gguf) | IQ4_NL | 1.83GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. | +| [Arch-Function-Chat-3B-Q3_K_XL.gguf](https://huggingface.co/bartowski/katanemo_Arch-Function-Chat-3B-GGUF/blob/main/katanemo_Arch-Function-Chat-3B-Q3_K_XL.gguf) | Q3_K_XL | 1.78GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. | +| [Arch-Function-Chat-3B-IQ4_XS.gguf](https://huggingface.co/bartowski/katanemo_Arch-Function-Chat-3B-GGUF/blob/main/katanemo_Arch-Function-Chat-3B-IQ4_XS.gguf) | IQ4_XS | 1.74GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. | +| [Arch-Function-Chat-3B-Q3_K_L.gguf](https://huggingface.co/bartowski/katanemo_Arch-Function-Chat-3B-GGUF/blob/main/katanemo_Arch-Function-Chat-3B-Q3_K_L.gguf) | Q3_K_L | 1.71GB | false | Lower quality but usable, good for low RAM availability. | +| [Arch-Function-Chat-3B-Q3_K_M.gguf](https://huggingface.co/bartowski/katanemo_Arch-Function-Chat-3B-GGUF/blob/main/katanemo_Arch-Function-Chat-3B-Q3_K_M.gguf) | Q3_K_M | 1.59GB | false | Low quality. | +| [Arch-Function-Chat-3B-IQ3_M.gguf](https://huggingface.co/bartowski/katanemo_Arch-Function-Chat-3B-GGUF/blob/main/katanemo_Arch-Function-Chat-3B-IQ3_M.gguf) | IQ3_M | 1.49GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. | +| [Arch-Function-Chat-3B-Q3_K_S.gguf](https://huggingface.co/bartowski/katanemo_Arch-Function-Chat-3B-GGUF/blob/main/katanemo_Arch-Function-Chat-3B-Q3_K_S.gguf) | Q3_K_S | 1.45GB | false | Low quality, not recommended. | +| [Arch-Function-Chat-3B-IQ3_XS.gguf](https://huggingface.co/bartowski/katanemo_Arch-Function-Chat-3B-GGUF/blob/main/katanemo_Arch-Function-Chat-3B-IQ3_XS.gguf) | IQ3_XS | 1.39GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. | +| [Arch-Function-Chat-3B-Q2_K_L.gguf](https://huggingface.co/bartowski/katanemo_Arch-Function-Chat-3B-GGUF/blob/main/katanemo_Arch-Function-Chat-3B-Q2_K_L.gguf) | Q2_K_L | 1.35GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. | +| [Arch-Function-Chat-3B-IQ3_XXS.gguf](https://huggingface.co/bartowski/katanemo_Arch-Function-Chat-3B-GGUF/blob/main/katanemo_Arch-Function-Chat-3B-IQ3_XXS.gguf) | IQ3_XXS | 1.28GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. | +| [Arch-Function-Chat-3B-Q2_K.gguf](https://huggingface.co/bartowski/katanemo_Arch-Function-Chat-3B-GGUF/blob/main/katanemo_Arch-Function-Chat-3B-Q2_K.gguf) | Q2_K | 1.27GB | false | Very low quality but surprisingly usable. | +| [Arch-Function-Chat-3B-IQ2_M.gguf](https://huggingface.co/bartowski/katanemo_Arch-Function-Chat-3B-GGUF/blob/main/katanemo_Arch-Function-Chat-3B-IQ2_M.gguf) | IQ2_M | 1.14GB | 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/katanemo_Arch-Function-Chat-3B-GGUF --include "katanemo_Arch-Function-Chat-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/katanemo_Arch-Function-Chat-3B-GGUF --include "katanemo_Arch-Function-Chat-3B-Q8_0/*" --local-dir ./ +``` + +You can either specify a new local-dir (katanemo_Arch-Function-Chat-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/katanemo_Arch-Function-Chat-3B-IQ2_M.gguf b/katanemo_Arch-Function-Chat-3B-IQ2_M.gguf new file mode 100644 index 0000000..ef8b164 --- /dev/null +++ b/katanemo_Arch-Function-Chat-3B-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac67c641baab04c1ba6af7d8c6c3dc8864fb4d314577a661f6bfc2f136a5e4f2 +size 1140516256 diff --git a/katanemo_Arch-Function-Chat-3B-IQ3_M.gguf b/katanemo_Arch-Function-Chat-3B-IQ3_M.gguf new file mode 100644 index 0000000..652c961 --- /dev/null +++ b/katanemo_Arch-Function-Chat-3B-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e28456542cd4e3f13c01092c47bcf583642ff50be49ce31d581052d31a0c19e5 +size 1488895392 diff --git a/katanemo_Arch-Function-Chat-3B-IQ3_XS.gguf b/katanemo_Arch-Function-Chat-3B-IQ3_XS.gguf new file mode 100644 index 0000000..7465b7e --- /dev/null +++ b/katanemo_Arch-Function-Chat-3B-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7f71cffd0993e17f4662be5b9e15147b7fb1fbf7734ad749cb79d08eed0bdc1 +size 1391836576 diff --git a/katanemo_Arch-Function-Chat-3B-IQ3_XXS.gguf b/katanemo_Arch-Function-Chat-3B-IQ3_XXS.gguf new file mode 100644 index 0000000..727fc36 --- /dev/null +++ b/katanemo_Arch-Function-Chat-3B-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:482dd5e9d61334f665b2704b71958133909041183f522ec15f48fa38e67d264a +size 1282827680 diff --git a/katanemo_Arch-Function-Chat-3B-IQ4_NL.gguf b/katanemo_Arch-Function-Chat-3B-IQ4_NL.gguf new file mode 100644 index 0000000..8609557 --- /dev/null +++ b/katanemo_Arch-Function-Chat-3B-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22d7efb46eaa4dffca75bb4cad4a4093fc65d7140e0a93efbf377ca46b0574be +size 1825209760 diff --git a/katanemo_Arch-Function-Chat-3B-IQ4_XS.gguf b/katanemo_Arch-Function-Chat-3B-IQ4_XS.gguf new file mode 100644 index 0000000..55c2b16 --- /dev/null +++ b/katanemo_Arch-Function-Chat-3B-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e19bbf1fb968df94264c9298f6b0dbc4cdb40ffb202101c573a8f3e331c2f25 +size 1739095456 diff --git a/katanemo_Arch-Function-Chat-3B-Q2_K.gguf b/katanemo_Arch-Function-Chat-3B-Q2_K.gguf new file mode 100644 index 0000000..dd15142 --- /dev/null +++ b/katanemo_Arch-Function-Chat-3B-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21eabb4c183749a1b7d241db1dddc5099f865a47eada4b712a9550760b19fa2f +size 1274756512 diff --git a/katanemo_Arch-Function-Chat-3B-Q2_K_L.gguf b/katanemo_Arch-Function-Chat-3B-Q2_K_L.gguf new file mode 100644 index 0000000..3219912 --- /dev/null +++ b/katanemo_Arch-Function-Chat-3B-Q2_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b21dcc6c16324bbdd43a9293431eddfcc289e0c15c0c6743d5baa6ad4321f2e +size 1350116768 diff --git a/katanemo_Arch-Function-Chat-3B-Q3_K_L.gguf b/katanemo_Arch-Function-Chat-3B-Q3_K_L.gguf new file mode 100644 index 0000000..0528fd1 --- /dev/null +++ b/katanemo_Arch-Function-Chat-3B-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ece8d0acf17427be9921197f674f89af5475698057d6f918451bff0252b19b6d +size 1707392416 diff --git a/katanemo_Arch-Function-Chat-3B-Q3_K_M.gguf b/katanemo_Arch-Function-Chat-3B-Q3_K_M.gguf new file mode 100644 index 0000000..39ea5d7 --- /dev/null +++ b/katanemo_Arch-Function-Chat-3B-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ca21e9dff281a7bc886dc8630c0bf697acf2112c04281bb6068e6da303a44b1 +size 1590476192 diff --git a/katanemo_Arch-Function-Chat-3B-Q3_K_S.gguf b/katanemo_Arch-Function-Chat-3B-Q3_K_S.gguf new file mode 100644 index 0000000..27c16fd --- /dev/null +++ b/katanemo_Arch-Function-Chat-3B-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae1db7519c71e985d07ecd21ea7e8848ea61624e8f9d70cc951ac7bd465529d1 +size 1454357920 diff --git a/katanemo_Arch-Function-Chat-3B-Q3_K_XL.gguf b/katanemo_Arch-Function-Chat-3B-Q3_K_XL.gguf new file mode 100644 index 0000000..8032b61 --- /dev/null +++ b/katanemo_Arch-Function-Chat-3B-Q3_K_XL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7bbcb9ccd39bfadfb8ede381291ba95e48d28f332073a30429508286cdbb4af5 +size 1782752672 diff --git a/katanemo_Arch-Function-Chat-3B-Q4_0.gguf b/katanemo_Arch-Function-Chat-3B-Q4_0.gguf new file mode 100644 index 0000000..a4cd30b --- /dev/null +++ b/katanemo_Arch-Function-Chat-3B-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70c8f1b2d37c6901bcfcad8abd355dc7a68b942f550181a5de06ff1c15c271bf +size 1828486560 diff --git a/katanemo_Arch-Function-Chat-3B-Q4_1.gguf b/katanemo_Arch-Function-Chat-3B-Q4_1.gguf new file mode 100644 index 0000000..9d4e11e --- /dev/null +++ b/katanemo_Arch-Function-Chat-3B-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f6d059bdaca30965516e59abe4fdb6076ff423e0db452ee8d9cd7e1d84baaab +size 1996258720 diff --git a/katanemo_Arch-Function-Chat-3B-Q4_K_L.gguf b/katanemo_Arch-Function-Chat-3B-Q4_K_L.gguf new file mode 100644 index 0000000..ba182fb --- /dev/null +++ b/katanemo_Arch-Function-Chat-3B-Q4_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51d82c2e88bd27021e88ea7c51b492cc1b9f2f6fb50cf1aed86a3713b5a93e4d +size 2005263776 diff --git a/katanemo_Arch-Function-Chat-3B-Q4_K_M.gguf b/katanemo_Arch-Function-Chat-3B-Q4_K_M.gguf new file mode 100644 index 0000000..6c3bf31 --- /dev/null +++ b/katanemo_Arch-Function-Chat-3B-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f59dbef397bf1364b5f0a2c23a7f67c40ec63cc666036c4e7615fa7d79d4e1a0 +size 1929903520 diff --git a/katanemo_Arch-Function-Chat-3B-Q4_K_S.gguf b/katanemo_Arch-Function-Chat-3B-Q4_K_S.gguf new file mode 100644 index 0000000..8ca873c --- /dev/null +++ b/katanemo_Arch-Function-Chat-3B-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:789847559604e0d29fa84b81293716e0a026763c77b43c8fb8a7086227bb5d01 +size 1834384800 diff --git a/katanemo_Arch-Function-Chat-3B-Q5_K_L.gguf b/katanemo_Arch-Function-Chat-3B-Q5_K_L.gguf new file mode 100644 index 0000000..d2e13fa --- /dev/null +++ b/katanemo_Arch-Function-Chat-3B-Q5_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c202a7f2f3b262ffec3c7e029e47bd3dc47d6a6810b2db448500cd2a461e310e +size 2300175776 diff --git a/katanemo_Arch-Function-Chat-3B-Q5_K_M.gguf b/katanemo_Arch-Function-Chat-3B-Q5_K_M.gguf new file mode 100644 index 0000000..c9a21bb --- /dev/null +++ b/katanemo_Arch-Function-Chat-3B-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96a00313b3890135acf0d0861d2723913bb7fa4c00d1f65ee82ac0ade0150d78 +size 2224815520 diff --git a/katanemo_Arch-Function-Chat-3B-Q5_K_S.gguf b/katanemo_Arch-Function-Chat-3B-Q5_K_S.gguf new file mode 100644 index 0000000..343ed5f --- /dev/null +++ b/katanemo_Arch-Function-Chat-3B-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29e301f85ff03ed1a5a798f8a222d3e957bbbc4bfeadd92e182ba5e4e8e0bcaf +size 2169666976 diff --git a/katanemo_Arch-Function-Chat-3B-Q6_K.gguf b/katanemo_Arch-Function-Chat-3B-Q6_K.gguf new file mode 100644 index 0000000..712a61c --- /dev/null +++ b/katanemo_Arch-Function-Chat-3B-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:465ced08f114d999b612f641aa10570abab1ee74c34303966298e6c6e9f09653 +size 2538159520 diff --git a/katanemo_Arch-Function-Chat-3B-Q6_K_L.gguf b/katanemo_Arch-Function-Chat-3B-Q6_K_L.gguf new file mode 100644 index 0000000..dda7941 --- /dev/null +++ b/katanemo_Arch-Function-Chat-3B-Q6_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89fe399e93edc0bc5a3382440952542f7b951f0f8dd3c9d30d4204139ddd5833 +size 2613519776 diff --git a/katanemo_Arch-Function-Chat-3B-Q8_0.gguf b/katanemo_Arch-Function-Chat-3B-Q8_0.gguf new file mode 100644 index 0000000..f2afd0c --- /dev/null +++ b/katanemo_Arch-Function-Chat-3B-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bff95422400d54f045018dc44a58c90ba14729b8d3d013b237bef98ed021cb27 +size 3285476768 diff --git a/katanemo_Arch-Function-Chat-3B-bf16.gguf b/katanemo_Arch-Function-Chat-3B-bf16.gguf new file mode 100644 index 0000000..fdaca19 --- /dev/null +++ b/katanemo_Arch-Function-Chat-3B-bf16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:041a47f892b6508a81f76a3e1530277a4e3e38bc5f4687ce1b1a7de58dcd289f +size 6178317440 diff --git a/katanemo_Arch-Function-Chat-3B.imatrix b/katanemo_Arch-Function-Chat-3B.imatrix new file mode 100644 index 0000000..eb90ac7 Binary files /dev/null and b/katanemo_Arch-Function-Chat-3B.imatrix differ