commit 8a5629924f8ffcc282062d06a6b96a5ad5fb36ed Author: ModelHub XC Date: Tue Jul 21 17:32:08 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: bartowski/ibm-granite_granite-3.3-2b-instruct-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..191ba51 --- /dev/null +++ b/README.md @@ -0,0 +1,173 @@ +--- +quantized_by: bartowski +pipeline_tag: text-generation +tags: +- language +- granite-3.3 +license: apache-2.0 +inference: false +base_model: ibm-granite/granite-3.3-2b-instruct +base_model_relation: quantized +--- + +## Llamacpp imatrix Quantizations of granite-3.3-2b-instruct by ibm-granite + +Using llama.cpp release b5147 for quantization. + +Original model: https://huggingface.co/ibm-granite/granite-3.3-2b-instruct + +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 + +``` +<|start_of_role|>system<|end_of_role|>{system_prompt}<|end_of_text|> +<|start_of_role|>user<|end_of_role|>{prompt}<|end_of_text|> +<|start_of_role|>assistant<|end_of_role|> +``` + +## Download a file (not the whole branch) from below: + +| Filename | Quant type | File Size | Split | Description | +| -------- | ---------- | --------- | ----- | ----------- | +| [granite-3.3-2b-instruct-bf16.gguf](https://huggingface.co/bartowski/ibm-granite_granite-3.3-2b-instruct-GGUF/blob/main/ibm-granite_granite-3.3-2b-instruct-bf16.gguf) | bf16 | 5.07GB | false | Full BF16 weights. | +| [granite-3.3-2b-instruct-Q8_0.gguf](https://huggingface.co/bartowski/ibm-granite_granite-3.3-2b-instruct-GGUF/blob/main/ibm-granite_granite-3.3-2b-instruct-Q8_0.gguf) | Q8_0 | 2.69GB | false | Extremely high quality, generally unneeded but max available quant. | +| [granite-3.3-2b-instruct-Q6_K_L.gguf](https://huggingface.co/bartowski/ibm-granite_granite-3.3-2b-instruct-GGUF/blob/main/ibm-granite_granite-3.3-2b-instruct-Q6_K_L.gguf) | Q6_K_L | 2.10GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. | +| [granite-3.3-2b-instruct-Q6_K.gguf](https://huggingface.co/bartowski/ibm-granite_granite-3.3-2b-instruct-GGUF/blob/main/ibm-granite_granite-3.3-2b-instruct-Q6_K.gguf) | Q6_K | 2.08GB | false | Very high quality, near perfect, *recommended*. | +| [granite-3.3-2b-instruct-Q5_K_L.gguf](https://huggingface.co/bartowski/ibm-granite_granite-3.3-2b-instruct-GGUF/blob/main/ibm-granite_granite-3.3-2b-instruct-Q5_K_L.gguf) | Q5_K_L | 1.83GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. | +| [granite-3.3-2b-instruct-Q5_K_M.gguf](https://huggingface.co/bartowski/ibm-granite_granite-3.3-2b-instruct-GGUF/blob/main/ibm-granite_granite-3.3-2b-instruct-Q5_K_M.gguf) | Q5_K_M | 1.80GB | false | High quality, *recommended*. | +| [granite-3.3-2b-instruct-Q5_K_S.gguf](https://huggingface.co/bartowski/ibm-granite_granite-3.3-2b-instruct-GGUF/blob/main/ibm-granite_granite-3.3-2b-instruct-Q5_K_S.gguf) | Q5_K_S | 1.76GB | false | High quality, *recommended*. | +| [granite-3.3-2b-instruct-Q4_1.gguf](https://huggingface.co/bartowski/ibm-granite_granite-3.3-2b-instruct-GGUF/blob/main/ibm-granite_granite-3.3-2b-instruct-Q4_1.gguf) | Q4_1 | 1.61GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. | +| [granite-3.3-2b-instruct-Q4_K_L.gguf](https://huggingface.co/bartowski/ibm-granite_granite-3.3-2b-instruct-GGUF/blob/main/ibm-granite_granite-3.3-2b-instruct-Q4_K_L.gguf) | Q4_K_L | 1.57GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. | +| [granite-3.3-2b-instruct-Q4_K_M.gguf](https://huggingface.co/bartowski/ibm-granite_granite-3.3-2b-instruct-GGUF/blob/main/ibm-granite_granite-3.3-2b-instruct-Q4_K_M.gguf) | Q4_K_M | 1.55GB | false | Good quality, default size for most use cases, *recommended*. | +| [granite-3.3-2b-instruct-Q4_K_S.gguf](https://huggingface.co/bartowski/ibm-granite_granite-3.3-2b-instruct-GGUF/blob/main/ibm-granite_granite-3.3-2b-instruct-Q4_K_S.gguf) | Q4_K_S | 1.46GB | false | Slightly lower quality with more space savings, *recommended*. | +| [granite-3.3-2b-instruct-Q4_0.gguf](https://huggingface.co/bartowski/ibm-granite_granite-3.3-2b-instruct-GGUF/blob/main/ibm-granite_granite-3.3-2b-instruct-Q4_0.gguf) | Q4_0 | 1.46GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. | +| [granite-3.3-2b-instruct-IQ4_NL.gguf](https://huggingface.co/bartowski/ibm-granite_granite-3.3-2b-instruct-GGUF/blob/main/ibm-granite_granite-3.3-2b-instruct-IQ4_NL.gguf) | IQ4_NL | 1.46GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. | +| [granite-3.3-2b-instruct-IQ4_XS.gguf](https://huggingface.co/bartowski/ibm-granite_granite-3.3-2b-instruct-GGUF/blob/main/ibm-granite_granite-3.3-2b-instruct-IQ4_XS.gguf) | IQ4_XS | 1.38GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. | +| [granite-3.3-2b-instruct-Q3_K_XL.gguf](https://huggingface.co/bartowski/ibm-granite_granite-3.3-2b-instruct-GGUF/blob/main/ibm-granite_granite-3.3-2b-instruct-Q3_K_XL.gguf) | Q3_K_XL | 1.38GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. | +| [granite-3.3-2b-instruct-Q3_K_L.gguf](https://huggingface.co/bartowski/ibm-granite_granite-3.3-2b-instruct-GGUF/blob/main/ibm-granite_granite-3.3-2b-instruct-Q3_K_L.gguf) | Q3_K_L | 1.36GB | false | Lower quality but usable, good for low RAM availability. | +| [granite-3.3-2b-instruct-Q3_K_M.gguf](https://huggingface.co/bartowski/ibm-granite_granite-3.3-2b-instruct-GGUF/blob/main/ibm-granite_granite-3.3-2b-instruct-Q3_K_M.gguf) | Q3_K_M | 1.25GB | false | Low quality. | +| [granite-3.3-2b-instruct-IQ3_M.gguf](https://huggingface.co/bartowski/ibm-granite_granite-3.3-2b-instruct-GGUF/blob/main/ibm-granite_granite-3.3-2b-instruct-IQ3_M.gguf) | IQ3_M | 1.17GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. | +| [granite-3.3-2b-instruct-Q3_K_S.gguf](https://huggingface.co/bartowski/ibm-granite_granite-3.3-2b-instruct-GGUF/blob/main/ibm-granite_granite-3.3-2b-instruct-Q3_K_S.gguf) | Q3_K_S | 1.13GB | false | Low quality, not recommended. | +| [granite-3.3-2b-instruct-IQ3_XS.gguf](https://huggingface.co/bartowski/ibm-granite_granite-3.3-2b-instruct-GGUF/blob/main/ibm-granite_granite-3.3-2b-instruct-IQ3_XS.gguf) | IQ3_XS | 1.08GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. | +| [granite-3.3-2b-instruct-IQ3_XXS.gguf](https://huggingface.co/bartowski/ibm-granite_granite-3.3-2b-instruct-GGUF/blob/main/ibm-granite_granite-3.3-2b-instruct-IQ3_XXS.gguf) | IQ3_XXS | 1.01GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. | +| [granite-3.3-2b-instruct-Q2_K_L.gguf](https://huggingface.co/bartowski/ibm-granite_granite-3.3-2b-instruct-GGUF/blob/main/ibm-granite_granite-3.3-2b-instruct-Q2_K_L.gguf) | Q2_K_L | 1.00GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. | +| [granite-3.3-2b-instruct-Q2_K.gguf](https://huggingface.co/bartowski/ibm-granite_granite-3.3-2b-instruct-GGUF/blob/main/ibm-granite_granite-3.3-2b-instruct-Q2_K.gguf) | Q2_K | 0.98GB | false | Very low quality but surprisingly usable. | +| [granite-3.3-2b-instruct-IQ2_M.gguf](https://huggingface.co/bartowski/ibm-granite_granite-3.3-2b-instruct-GGUF/blob/main/ibm-granite_granite-3.3-2b-instruct-IQ2_M.gguf) | IQ2_M | 0.89GB | 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/ibm-granite_granite-3.3-2b-instruct-GGUF --include "ibm-granite_granite-3.3-2b-instruct-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/ibm-granite_granite-3.3-2b-instruct-GGUF --include "ibm-granite_granite-3.3-2b-instruct-Q8_0/*" --local-dir ./ +``` + +You can either specify a new local-dir (ibm-granite_granite-3.3-2b-instruct-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/ibm-granite_granite-3.3-2b-instruct-IQ2_M.gguf b/ibm-granite_granite-3.3-2b-instruct-IQ2_M.gguf new file mode 100644 index 0000000..b877701 --- /dev/null +++ b/ibm-granite_granite-3.3-2b-instruct-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08bdccf9dd7cd4a378a6c280f8a828ab18c6a47d6f832d2832f3347261512c65 +size 888532672 diff --git a/ibm-granite_granite-3.3-2b-instruct-IQ3_M.gguf b/ibm-granite_granite-3.3-2b-instruct-IQ3_M.gguf new file mode 100644 index 0000000..d7948e3 --- /dev/null +++ b/ibm-granite_granite-3.3-2b-instruct-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b38effafc86a641e5e33a4ef0f3ee5774f19ac2ccdd52d287ef3ca036c767b9 +size 1169290816 diff --git a/ibm-granite_granite-3.3-2b-instruct-IQ3_XS.gguf b/ibm-granite_granite-3.3-2b-instruct-IQ3_XS.gguf new file mode 100644 index 0000000..1aad342 --- /dev/null +++ b/ibm-granite_granite-3.3-2b-instruct-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa5ae87946c922915736859dd6fc3bdd4b39005608bcfea81fa4a3cec1007a0c +size 1078851136 diff --git a/ibm-granite_granite-3.3-2b-instruct-IQ3_XXS.gguf b/ibm-granite_granite-3.3-2b-instruct-IQ3_XXS.gguf new file mode 100644 index 0000000..a2d2e92 --- /dev/null +++ b/ibm-granite_granite-3.3-2b-instruct-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a525a74e9f9febe029caa228fd11246e18e4d383f96fd782b7a1417c5aef2c6f +size 1005186752 diff --git a/ibm-granite_granite-3.3-2b-instruct-IQ4_NL.gguf b/ibm-granite_granite-3.3-2b-instruct-IQ4_NL.gguf new file mode 100644 index 0000000..e9fc057 --- /dev/null +++ b/ibm-granite_granite-3.3-2b-instruct-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0df19f03b7f248b16682255bf3a7f340557580cf54ddd9afa0f3dfdb58b64ba1 +size 1458632256 diff --git a/ibm-granite_granite-3.3-2b-instruct-IQ4_XS.gguf b/ibm-granite_granite-3.3-2b-instruct-IQ4_XS.gguf new file mode 100644 index 0000000..98d25bd --- /dev/null +++ b/ibm-granite_granite-3.3-2b-instruct-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c13e05f57bd75ccd6241928ded9689ae4a7f51ad931695f850b0cf9304b6fccd +size 1383921216 diff --git a/ibm-granite_granite-3.3-2b-instruct-Q2_K.gguf b/ibm-granite_granite-3.3-2b-instruct-Q2_K.gguf new file mode 100644 index 0000000..a8f0c69 --- /dev/null +++ b/ibm-granite_granite-3.3-2b-instruct-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:587a46fe07f02b0cfb1cb8188306c467f210674dcd9028fde150c5d78cd9ee67 +size 978253376 diff --git a/ibm-granite_granite-3.3-2b-instruct-Q2_K_L.gguf b/ibm-granite_granite-3.3-2b-instruct-Q2_K_L.gguf new file mode 100644 index 0000000..480342f --- /dev/null +++ b/ibm-granite_granite-3.3-2b-instruct-Q2_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3261aa0c63e7e0d53d73b4a1d92c0a0362e2cc3f8f59062ae2b89feeb6585630 +size 1002636224 diff --git a/ibm-granite_granite-3.3-2b-instruct-Q3_K_L.gguf b/ibm-granite_granite-3.3-2b-instruct-Q3_K_L.gguf new file mode 100644 index 0000000..b254e1e --- /dev/null +++ b/ibm-granite_granite-3.3-2b-instruct-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49a713d912774522b67593a3f7fb290cbd8edd99b290460f0d972c283a8ab77f +size 1357379136 diff --git a/ibm-granite_granite-3.3-2b-instruct-Q3_K_M.gguf b/ibm-granite_granite-3.3-2b-instruct-Q3_K_M.gguf new file mode 100644 index 0000000..915c8f3 --- /dev/null +++ b/ibm-granite_granite-3.3-2b-instruct-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2cb2782e06d8f79b89ae0e29e43dfdbc875c2e7c6a433c0948a89da1710c4f2 +size 1251735104 diff --git a/ibm-granite_granite-3.3-2b-instruct-Q3_K_S.gguf b/ibm-granite_granite-3.3-2b-instruct-Q3_K_S.gguf new file mode 100644 index 0000000..8749a9d --- /dev/null +++ b/ibm-granite_granite-3.3-2b-instruct-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40b83cf008a03342f10386bd064601d9d42381e7814ce6f11cb5bb2a5b446a04 +size 1130296896 diff --git a/ibm-granite_granite-3.3-2b-instruct-Q3_K_XL.gguf b/ibm-granite_granite-3.3-2b-instruct-Q3_K_XL.gguf new file mode 100644 index 0000000..c095027 --- /dev/null +++ b/ibm-granite_granite-3.3-2b-instruct-Q3_K_XL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ac77d1d61f8983ae1524485168d47ffd2bf2a94342d492bd3f7e9c8f027477d +size 1381761984 diff --git a/ibm-granite_granite-3.3-2b-instruct-Q4_0.gguf b/ibm-granite_granite-3.3-2b-instruct-Q4_0.gguf new file mode 100644 index 0000000..6fbba9e --- /dev/null +++ b/ibm-granite_granite-3.3-2b-instruct-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:417330dc64f62dde19b285952097b60f2f5a04f73ef7c87d99345749d6d8a896 +size 1458632256 diff --git a/ibm-granite_granite-3.3-2b-instruct-Q4_1.gguf b/ibm-granite_granite-3.3-2b-instruct-Q4_1.gguf new file mode 100644 index 0000000..648cda1 --- /dev/null +++ b/ibm-granite_granite-3.3-2b-instruct-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:256c30073c3abfe4690489e5d1bf6f9321e96e7a57a02ba39587e435acfb4659 +size 1605432896 diff --git a/ibm-granite_granite-3.3-2b-instruct-Q4_K_L.gguf b/ibm-granite_granite-3.3-2b-instruct-Q4_K_L.gguf new file mode 100644 index 0000000..0eea138 --- /dev/null +++ b/ibm-granite_granite-3.3-2b-instruct-Q4_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14fd5b193376ac7b31a6bdb45f5488a781476a59a32662406ebef5eb319b5be2 +size 1569686464 diff --git a/ibm-granite_granite-3.3-2b-instruct-Q4_K_M.gguf b/ibm-granite_granite-3.3-2b-instruct-Q4_K_M.gguf new file mode 100644 index 0000000..5c6a83f --- /dev/null +++ b/ibm-granite_granite-3.3-2b-instruct-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:555b91485955bc96eb445b57dd4bbf8809aa7d8cce7c313f4f8bc5b2340896b4 +size 1545303616 diff --git a/ibm-granite_granite-3.3-2b-instruct-Q4_K_S.gguf b/ibm-granite_granite-3.3-2b-instruct-Q4_K_S.gguf new file mode 100644 index 0000000..2464f97 --- /dev/null +++ b/ibm-granite_granite-3.3-2b-instruct-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5712c30774a369040664da3749ef47508e11504f0c36acf6c66356a446b1b1af +size 1464399424 diff --git a/ibm-granite_granite-3.3-2b-instruct-Q5_K_L.gguf b/ibm-granite_granite-3.3-2b-instruct-Q5_K_L.gguf new file mode 100644 index 0000000..086fea2 --- /dev/null +++ b/ibm-granite_granite-3.3-2b-instruct-Q5_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac6a7d44f83cf11ccce3459cbc16f85b9226ae428678d2456ffdc5a73e851d7a +size 1829209024 diff --git a/ibm-granite_granite-3.3-2b-instruct-Q5_K_M.gguf b/ibm-granite_granite-3.3-2b-instruct-Q5_K_M.gguf new file mode 100644 index 0000000..d957cd8 --- /dev/null +++ b/ibm-granite_granite-3.3-2b-instruct-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1cea20687ecc06a9bc4fca281bcca5a13e6953c2881308abb7fae352a743259f +size 1804826176 diff --git a/ibm-granite_granite-3.3-2b-instruct-Q5_K_S.gguf b/ibm-granite_granite-3.3-2b-instruct-Q5_K_S.gguf new file mode 100644 index 0000000..dbc167f --- /dev/null +++ b/ibm-granite_granite-3.3-2b-instruct-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67be532ede40781dd92d34337ab9c9a5b78894d88c2a4883af9ab9da003562dd +size 1757476416 diff --git a/ibm-granite_granite-3.3-2b-instruct-Q6_K.gguf b/ibm-granite_granite-3.3-2b-instruct-Q6_K.gguf new file mode 100644 index 0000000..d2135b5 --- /dev/null +++ b/ibm-granite_granite-3.3-2b-instruct-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ed1776f322ed46c462460bbaac28e465d4b5a091f6db7d127107f2c546898ca +size 2080568896 diff --git a/ibm-granite_granite-3.3-2b-instruct-Q6_K_L.gguf b/ibm-granite_granite-3.3-2b-instruct-Q6_K_L.gguf new file mode 100644 index 0000000..cc08cdc --- /dev/null +++ b/ibm-granite_granite-3.3-2b-instruct-Q6_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56f980677d86b7f48ac405e21c42fa925991e725f381390fcfd233b566445290 +size 2104951744 diff --git a/ibm-granite_granite-3.3-2b-instruct-Q8_0.gguf b/ibm-granite_granite-3.3-2b-instruct-Q8_0.gguf new file mode 100644 index 0000000..24efa93 --- /dev/null +++ b/ibm-granite_granite-3.3-2b-instruct-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:057edd409b4d56773c90587655300d848d467cfec72c5529f9bab9ba46be0775 +size 2694120384 diff --git a/ibm-granite_granite-3.3-2b-instruct-bf16.gguf b/ibm-granite_granite-3.3-2b-instruct-bf16.gguf new file mode 100644 index 0000000..d7d8f17 --- /dev/null +++ b/ibm-granite_granite-3.3-2b-instruct-bf16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da687838c084d01dbcc218c1ffc945e2be3e0c4b16811f0ddce4959205fa0793 +size 5069158176 diff --git a/ibm-granite_granite-3.3-2b-instruct.imatrix b/ibm-granite_granite-3.3-2b-instruct.imatrix new file mode 100644 index 0000000..994cff0 Binary files /dev/null and b/ibm-granite_granite-3.3-2b-instruct.imatrix differ