commit bdd2bcafb8e768b0a98ff50b04a9c86bf17b1098 Author: ModelHub XC Date: Fri Sep 4 09:16:12 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: bartowski/ai21labs_AI21-Jamba2-3B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..5740375 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,73 @@ +*.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 + +*.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 + +ai21labs_AI21-Jamba2-3B-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +ai21labs_AI21-Jamba2-3B-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +ai21labs_AI21-Jamba2-3B-bf16.gguf filter=lfs diff=lfs merge=lfs -text +ai21labs_AI21-Jamba2-3B-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +ai21labs_AI21-Jamba2-3B-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +ai21labs_AI21-Jamba2-3B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ai21labs_AI21-Jamba2-3B-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +ai21labs_AI21-Jamba2-3B-Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text +ai21labs_AI21-Jamba2-3B-Q5_K_L.gguf filter=lfs diff=lfs merge=lfs -text +ai21labs_AI21-Jamba2-3B-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ai21labs_AI21-Jamba2-3B-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text +ai21labs_AI21-Jamba2-3B-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ai21labs_AI21-Jamba2-3B-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text +ai21labs_AI21-Jamba2-3B-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +ai21labs_AI21-Jamba2-3B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ai21labs_AI21-Jamba2-3B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +ai21labs_AI21-Jamba2-3B-imatrix.gguf filter=lfs diff=lfs merge=lfs -text +ai21labs_AI21-Jamba2-3B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +ai21labs_AI21-Jamba2-3B-Q6_K_L.gguf filter=lfs diff=lfs merge=lfs -text +ai21labs_AI21-Jamba2-3B-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ai21labs_AI21-Jamba2-3B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ai21labs_AI21-Jamba2-3B-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +ai21labs_AI21-Jamba2-3B-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +ai21labs_AI21-Jamba2-3B-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +ai21labs_AI21-Jamba2-3B-IQ4_XS.gguf 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..3a2aa7f --- /dev/null +++ b/README.md @@ -0,0 +1,178 @@ +--- +quantized_by: bartowski +pipeline_tag: text-generation +base_model_relation: quantized +base_model: ai21labs/AI21-Jamba2-3B +license: apache-2.0 +--- + +## Llamacpp imatrix Quantizations of AI21-Jamba2-3B by ai21labs + +Using llama.cpp release b7652 for quantization. + +Original model: https://huggingface.co/ai21labs/AI21-Jamba2-3B + +All quants made using imatrix option with dataset from [here](https://gist.github.com/bartowski1182/82ae9b520227f57d79ba04add13d0d0d) + +Run them in your choice of tools: + +- [llama.cpp](https://github.com/ggml-org/llama.cpp) +- [LM Studio](https://lmstudio.ai/) +- [koboldcpp](https://github.com/LostRuins/koboldcpp) +- [Jan AI](https://www.jan.ai/) +- [Text Generation Web UI](https://github.com/oobabooga/text-generation-webui) +- [LoLLMs](https://github.com/ParisNeo/lollms) + +Note: if it's a newly supported model, you may need to wait for an update from the developers. + +## Prompt format + +``` +<|startoftext|><|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 | +| -------- | ---------- | --------- | ----- | ----------- | +| [AI21-Jamba2-3B-bf16.gguf](https://huggingface.co/bartowski/ai21labs_AI21-Jamba2-3B-GGUF/blob/main/ai21labs_AI21-Jamba2-3B-bf16.gguf) | bf16 | 6.40GB | false | Full BF16 weights. | +| [AI21-Jamba2-3B-Q8_0.gguf](https://huggingface.co/bartowski/ai21labs_AI21-Jamba2-3B-GGUF/blob/main/ai21labs_AI21-Jamba2-3B-Q8_0.gguf) | Q8_0 | 3.41GB | false | Extremely high quality, generally unneeded but max available quant. | +| [AI21-Jamba2-3B-Q6_K_L.gguf](https://huggingface.co/bartowski/ai21labs_AI21-Jamba2-3B-GGUF/blob/main/ai21labs_AI21-Jamba2-3B-Q6_K_L.gguf) | Q6_K_L | 2.72GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. | +| [AI21-Jamba2-3B-Q6_K.gguf](https://huggingface.co/bartowski/ai21labs_AI21-Jamba2-3B-GGUF/blob/main/ai21labs_AI21-Jamba2-3B-Q6_K.gguf) | Q6_K | 2.64GB | false | Very high quality, near perfect, *recommended*. | +| [AI21-Jamba2-3B-Q5_K_L.gguf](https://huggingface.co/bartowski/ai21labs_AI21-Jamba2-3B-GGUF/blob/main/ai21labs_AI21-Jamba2-3B-Q5_K_L.gguf) | Q5_K_L | 2.38GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. | +| [AI21-Jamba2-3B-Q5_K_M.gguf](https://huggingface.co/bartowski/ai21labs_AI21-Jamba2-3B-GGUF/blob/main/ai21labs_AI21-Jamba2-3B-Q5_K_M.gguf) | Q5_K_M | 2.27GB | false | High quality, *recommended*. | +| [AI21-Jamba2-3B-Q5_K_S.gguf](https://huggingface.co/bartowski/ai21labs_AI21-Jamba2-3B-GGUF/blob/main/ai21labs_AI21-Jamba2-3B-Q5_K_S.gguf) | Q5_K_S | 2.23GB | false | High quality, *recommended*. | +| [AI21-Jamba2-3B-Q4_K_L.gguf](https://huggingface.co/bartowski/ai21labs_AI21-Jamba2-3B-GGUF/blob/main/ai21labs_AI21-Jamba2-3B-Q4_K_L.gguf) | Q4_K_L | 2.06GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. | +| [AI21-Jamba2-3B-Q4_1.gguf](https://huggingface.co/bartowski/ai21labs_AI21-Jamba2-3B-GGUF/blob/main/ai21labs_AI21-Jamba2-3B-Q4_1.gguf) | Q4_1 | 2.04GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. | +| [AI21-Jamba2-3B-Q4_K_M.gguf](https://huggingface.co/bartowski/ai21labs_AI21-Jamba2-3B-GGUF/blob/main/ai21labs_AI21-Jamba2-3B-Q4_K_M.gguf) | Q4_K_M | 1.93GB | false | Good quality, default size for most use cases, *recommended*. | +| [AI21-Jamba2-3B-Q4_K_S.gguf](https://huggingface.co/bartowski/ai21labs_AI21-Jamba2-3B-GGUF/blob/main/ai21labs_AI21-Jamba2-3B-Q4_K_S.gguf) | Q4_K_S | 1.86GB | false | Slightly lower quality with more space savings, *recommended*. | +| [AI21-Jamba2-3B-Q4_0.gguf](https://huggingface.co/bartowski/ai21labs_AI21-Jamba2-3B-GGUF/blob/main/ai21labs_AI21-Jamba2-3B-Q4_0.gguf) | Q4_0 | 1.86GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. | +| [AI21-Jamba2-3B-IQ4_NL.gguf](https://huggingface.co/bartowski/ai21labs_AI21-Jamba2-3B-GGUF/blob/main/ai21labs_AI21-Jamba2-3B-IQ4_NL.gguf) | IQ4_NL | 1.85GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. | +| [AI21-Jamba2-3B-IQ4_XS.gguf](https://huggingface.co/bartowski/ai21labs_AI21-Jamba2-3B-GGUF/blob/main/ai21labs_AI21-Jamba2-3B-IQ4_XS.gguf) | IQ4_XS | 1.76GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. | +| [AI21-Jamba2-3B-Q3_K_XL.gguf](https://huggingface.co/bartowski/ai21labs_AI21-Jamba2-3B-GGUF/blob/main/ai21labs_AI21-Jamba2-3B-Q3_K_XL.gguf) | Q3_K_XL | 1.76GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. | +| [AI21-Jamba2-3B-Q3_K_L.gguf](https://huggingface.co/bartowski/ai21labs_AI21-Jamba2-3B-GGUF/blob/main/ai21labs_AI21-Jamba2-3B-Q3_K_L.gguf) | Q3_K_L | 1.61GB | false | Lower quality but usable, good for low RAM availability. | +| [AI21-Jamba2-3B-Q3_K_M.gguf](https://huggingface.co/bartowski/ai21labs_AI21-Jamba2-3B-GGUF/blob/main/ai21labs_AI21-Jamba2-3B-Q3_K_M.gguf) | Q3_K_M | 1.54GB | false | Low quality. | +| [AI21-Jamba2-3B-IQ3_M.gguf](https://huggingface.co/bartowski/ai21labs_AI21-Jamba2-3B-GGUF/blob/main/ai21labs_AI21-Jamba2-3B-IQ3_M.gguf) | IQ3_M | 1.47GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. | +| [AI21-Jamba2-3B-Q3_K_S.gguf](https://huggingface.co/bartowski/ai21labs_AI21-Jamba2-3B-GGUF/blob/main/ai21labs_AI21-Jamba2-3B-Q3_K_S.gguf) | Q3_K_S | 1.46GB | false | Low quality, not recommended. | +| [AI21-Jamba2-3B-IQ3_XS.gguf](https://huggingface.co/bartowski/ai21labs_AI21-Jamba2-3B-GGUF/blob/main/ai21labs_AI21-Jamba2-3B-IQ3_XS.gguf) | IQ3_XS | 1.41GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. | +| [AI21-Jamba2-3B-Q2_K_L.gguf](https://huggingface.co/bartowski/ai21labs_AI21-Jamba2-3B-GGUF/blob/main/ai21labs_AI21-Jamba2-3B-Q2_K_L.gguf) | Q2_K_L | 1.37GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. | +| [AI21-Jamba2-3B-IQ3_XXS.gguf](https://huggingface.co/bartowski/ai21labs_AI21-Jamba2-3B-GGUF/blob/main/ai21labs_AI21-Jamba2-3B-IQ3_XXS.gguf) | IQ3_XXS | 1.30GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. | +| [AI21-Jamba2-3B-Q2_K.gguf](https://huggingface.co/bartowski/ai21labs_AI21-Jamba2-3B-GGUF/blob/main/ai21labs_AI21-Jamba2-3B-Q2_K.gguf) | Q2_K | 1.21GB | false | Very low quality but surprisingly usable. | +| [AI21-Jamba2-3B-IQ2_M.gguf](https://huggingface.co/bartowski/ai21labs_AI21-Jamba2-3B-GGUF/blob/main/ai21labs_AI21-Jamba2-3B-IQ2_M.gguf) | IQ2_M | 1.13GB | 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/ai21labs_AI21-Jamba2-3B-GGUF --include "ai21labs_AI21-Jamba2-3B-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/ai21labs_AI21-Jamba2-3B-GGUF --include "ai21labs_AI21-Jamba2-3B-Q8_0/*" --local-dir ./ +``` + +You can either specify a new local-dir (ai21labs_AI21-Jamba2-3B-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/ggml-org/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/ggml-org/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/ggml-org/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/ggml-org/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/ai21labs_AI21-Jamba2-3B-IQ2_M.gguf b/ai21labs_AI21-Jamba2-3B-IQ2_M.gguf new file mode 100644 index 0000000..0f38b19 --- /dev/null +++ b/ai21labs_AI21-Jamba2-3B-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1aec91f4f91bdb800ef84727d18a7b8b528cbca321c66c6acdccc06dff81e88 +size 1130978688 diff --git a/ai21labs_AI21-Jamba2-3B-IQ3_M.gguf b/ai21labs_AI21-Jamba2-3B-IQ3_M.gguf new file mode 100644 index 0000000..24b3a03 --- /dev/null +++ b/ai21labs_AI21-Jamba2-3B-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e449d88575e025b5087da0fa6bb47c2e6f0089c1cb6c8803f8bc75d90291334 +size 1465360768 diff --git a/ai21labs_AI21-Jamba2-3B-IQ3_XS.gguf b/ai21labs_AI21-Jamba2-3B-IQ3_XS.gguf new file mode 100644 index 0000000..d48cc82 --- /dev/null +++ b/ai21labs_AI21-Jamba2-3B-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5be9246ef423acbf52727afaf527e69e7caeca4088227af062b816804f6d468c +size 1413244288 diff --git a/ai21labs_AI21-Jamba2-3B-IQ3_XXS.gguf b/ai21labs_AI21-Jamba2-3B-IQ3_XXS.gguf new file mode 100644 index 0000000..5609c8e --- /dev/null +++ b/ai21labs_AI21-Jamba2-3B-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b80495a1c32738c94b54df5fb6c7704c852eabc1d402aa6b740570639efd984a +size 1299662208 diff --git a/ai21labs_AI21-Jamba2-3B-IQ4_NL.gguf b/ai21labs_AI21-Jamba2-3B-IQ4_NL.gguf new file mode 100644 index 0000000..d80749b --- /dev/null +++ b/ai21labs_AI21-Jamba2-3B-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4d6b3a3df94c6c92d4e63bcb997cc85d99a3396b9b0b2fc3761a68ca553f47b +size 1854255488 diff --git a/ai21labs_AI21-Jamba2-3B-IQ4_XS.gguf b/ai21labs_AI21-Jamba2-3B-IQ4_XS.gguf new file mode 100644 index 0000000..62e5b01 --- /dev/null +++ b/ai21labs_AI21-Jamba2-3B-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:136e2fa1a913f9c94d42012f87099420cedb528a3997d83ab9b83a8e437fc7d3 +size 1760354688 diff --git a/ai21labs_AI21-Jamba2-3B-Q2_K.gguf b/ai21labs_AI21-Jamba2-3B-Q2_K.gguf new file mode 100644 index 0000000..ffc799c --- /dev/null +++ b/ai21labs_AI21-Jamba2-3B-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac179c7ff43868d43e544b66ac5079c126fe1ef8d1ae11ccc56ad14e25c7350d +size 1211035008 diff --git a/ai21labs_AI21-Jamba2-3B-Q2_K_L.gguf b/ai21labs_AI21-Jamba2-3B-Q2_K_L.gguf new file mode 100644 index 0000000..fc4da8e --- /dev/null +++ b/ai21labs_AI21-Jamba2-3B-Q2_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0d9786605b858ce94c44dd3c4cf4a76515a432809b91d38aca0a80d6681b1e2 +size 1374875008 diff --git a/ai21labs_AI21-Jamba2-3B-Q3_K_L.gguf b/ai21labs_AI21-Jamba2-3B-Q3_K_L.gguf new file mode 100644 index 0000000..298efd5 --- /dev/null +++ b/ai21labs_AI21-Jamba2-3B-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ae50495f7eb08803df61bd07994646e29f73d3e6ac3c8a4a940dded75d9bcbc +size 1610113408 diff --git a/ai21labs_AI21-Jamba2-3B-Q3_K_M.gguf b/ai21labs_AI21-Jamba2-3B-Q3_K_M.gguf new file mode 100644 index 0000000..4175d8b --- /dev/null +++ b/ai21labs_AI21-Jamba2-3B-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4d7de0c1c89c751a54efd858ddfb80cfde4dffec582c9bd9fe47b139583eaee +size 1537696128 diff --git a/ai21labs_AI21-Jamba2-3B-Q3_K_S.gguf b/ai21labs_AI21-Jamba2-3B-Q3_K_S.gguf new file mode 100644 index 0000000..428bcb9 --- /dev/null +++ b/ai21labs_AI21-Jamba2-3B-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0fb7dc388d44ef2e84c9491c09a91174a2607f9069ce1aa12d97f8b98002029 +size 1455177088 diff --git a/ai21labs_AI21-Jamba2-3B-Q3_K_XL.gguf b/ai21labs_AI21-Jamba2-3B-Q3_K_XL.gguf new file mode 100644 index 0000000..2b478aa --- /dev/null +++ b/ai21labs_AI21-Jamba2-3B-Q3_K_XL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe22d48907f35048217db2cedf729145d61315fc7f9e33c04d8907e978c255d2 +size 1756914048 diff --git a/ai21labs_AI21-Jamba2-3B-Q4_0.gguf b/ai21labs_AI21-Jamba2-3B-Q4_0.gguf new file mode 100644 index 0000000..798c8e7 --- /dev/null +++ b/ai21labs_AI21-Jamba2-3B-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24cf1839927e02d8b4efa014bf766698a740e3d0b5f0958cb81d7e6715f7502c +size 1858187648 diff --git a/ai21labs_AI21-Jamba2-3B-Q4_1.gguf b/ai21labs_AI21-Jamba2-3B-Q4_1.gguf new file mode 100644 index 0000000..40cbee8 --- /dev/null +++ b/ai21labs_AI21-Jamba2-3B-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e29bc061ad0ff298071c07a8d7b81a3dd8381afb9916cd83de7ccb920d4a923e +size 2043388288 diff --git a/ai21labs_AI21-Jamba2-3B-Q4_K_L.gguf b/ai21labs_AI21-Jamba2-3B-Q4_K_L.gguf new file mode 100644 index 0000000..d8a4c32 --- /dev/null +++ b/ai21labs_AI21-Jamba2-3B-Q4_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0fb0b377222f2a865ee88f11c73a9650817ff3cadef925e23a45dea17dadcf1c +size 2057214848 diff --git a/ai21labs_AI21-Jamba2-3B-Q4_K_M.gguf b/ai21labs_AI21-Jamba2-3B-Q4_K_M.gguf new file mode 100644 index 0000000..8d0117b --- /dev/null +++ b/ai21labs_AI21-Jamba2-3B-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa0876fa152f38689cefd6d498907d6255cf515780d65b16346d3190df6a0794 +size 1932696448 diff --git a/ai21labs_AI21-Jamba2-3B-Q4_K_S.gguf b/ai21labs_AI21-Jamba2-3B-Q4_K_S.gguf new file mode 100644 index 0000000..eba7c3c --- /dev/null +++ b/ai21labs_AI21-Jamba2-3B-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05e361b42b89c4d315a67b25a37e81bceedbfc27cb99b61cbba22e8fbfda56bc +size 1864864128 diff --git a/ai21labs_AI21-Jamba2-3B-Q5_K_L.gguf b/ai21labs_AI21-Jamba2-3B-Q5_K_L.gguf new file mode 100644 index 0000000..a0cae2d --- /dev/null +++ b/ai21labs_AI21-Jamba2-3B-Q5_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f9e269bb5030d895dabae4898aed7831a2a90c53357a4e7f14e6a864559adb2 +size 2376436608 diff --git a/ai21labs_AI21-Jamba2-3B-Q5_K_M.gguf b/ai21labs_AI21-Jamba2-3B-Q5_K_M.gguf new file mode 100644 index 0000000..5ee17c0 --- /dev/null +++ b/ai21labs_AI21-Jamba2-3B-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a55643e2f70b3000542d41f5003dd57f512f8506f816ff1dd9c758ed6fcd916b +size 2272889728 diff --git a/ai21labs_AI21-Jamba2-3B-Q5_K_S.gguf b/ai21labs_AI21-Jamba2-3B-Q5_K_S.gguf new file mode 100644 index 0000000..88a7cf5 --- /dev/null +++ b/ai21labs_AI21-Jamba2-3B-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f818e1247b159cb666714bf8e3499abe234b780a0a8e5686becc750c8bb984f +size 2233852288 diff --git a/ai21labs_AI21-Jamba2-3B-Q6_K.gguf b/ai21labs_AI21-Jamba2-3B-Q6_K.gguf new file mode 100644 index 0000000..92b0135 --- /dev/null +++ b/ai21labs_AI21-Jamba2-3B-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf1628802987516f105893df8f9c2cd6e3eddc3a39046d463cfe6247897dc9b7 +size 2639586688 diff --git a/ai21labs_AI21-Jamba2-3B-Q6_K_L.gguf b/ai21labs_AI21-Jamba2-3B-Q6_K_L.gguf new file mode 100644 index 0000000..25c34c1 --- /dev/null +++ b/ai21labs_AI21-Jamba2-3B-Q6_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d428ea6e819493d787e4f9902c6bcd54595923bddfc4177eb9675b2ee9691bbf +size 2720851328 diff --git a/ai21labs_AI21-Jamba2-3B-Q8_0.gguf b/ai21labs_AI21-Jamba2-3B-Q8_0.gguf new file mode 100644 index 0000000..939e2fd --- /dev/null +++ b/ai21labs_AI21-Jamba2-3B-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c624f1d663d2d9e1008d718c3e8d67ae62a19733ddde89ee90872e0c84eb50b +size 3407950208 diff --git a/ai21labs_AI21-Jamba2-3B-bf16.gguf b/ai21labs_AI21-Jamba2-3B-bf16.gguf new file mode 100644 index 0000000..087ef00 --- /dev/null +++ b/ai21labs_AI21-Jamba2-3B-bf16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8d1bfd86cdb47739ab0996a89ccece1845648dfafa273d20a4cb060c748bd1e +size 6402228320 diff --git a/ai21labs_AI21-Jamba2-3B-imatrix.gguf b/ai21labs_AI21-Jamba2-3B-imatrix.gguf new file mode 100644 index 0000000..5789b11 --- /dev/null +++ b/ai21labs_AI21-Jamba2-3B-imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef2c5d9418698424e05f429d64b96eb2746ca009e6fcc785d1925c9bf8d5a599 +size 2950624 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