commit b7cedbab8d896386a140b9fc5079025ca1a7d2f8 Author: ModelHub XC Date: Mon Nov 2 12:45:13 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: bartowski/pszemraj_jamba-900M-v0.13-KIx2-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..4ce6a39 --- /dev/null +++ b/README.md @@ -0,0 +1,176 @@ +--- +quantized_by: bartowski +pipeline_tag: text-generation +base_model: pszemraj/jamba-900M-v0.13-KIx2 +base_model_relation: quantized +metrics: +- accuracy +license: apache-2.0 +inference: false +language: +- en +tags: +- jamba +- smol MoE +- smol +datasets: +- BEE-spoke-data/knowledge-inoc-concat-v1 +- BEE-spoke-data/wikipedia-20230901.en-deduped +- BEE-spoke-data/fineweb-100k_en-med +- BEE-spoke-data/fineweb-1M_en-med +- BEE-spoke-data/fineweb-1M_longish +--- + +## Llamacpp imatrix Quantizations of jamba-900M-v0.13-KIx2 by pszemraj + +Using llama.cpp release b5856 for quantization. + +Original model: https://huggingface.co/pszemraj/jamba-900M-v0.13-KIx2 + +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 + +No prompt format found, check original model page + +## Download a file (not the whole branch) from below: + +| Filename | Quant type | File Size | Split | Description | +| -------- | ---------- | --------- | ----- | ----------- | +| [jamba-900M-v0.13-KIx2-bf16.gguf](https://huggingface.co/bartowski/pszemraj_jamba-900M-v0.13-KIx2-GGUF/blob/main/pszemraj_jamba-900M-v0.13-KIx2-bf16.gguf) | bf16 | 1.78GB | false | Full BF16 weights. | +| [jamba-900M-v0.13-KIx2-Q8_0.gguf](https://huggingface.co/bartowski/pszemraj_jamba-900M-v0.13-KIx2-GGUF/blob/main/pszemraj_jamba-900M-v0.13-KIx2-Q8_0.gguf) | Q8_0 | 0.95GB | false | Extremely high quality, generally unneeded but max available quant. | +| [jamba-900M-v0.13-KIx2-Q6_K_L.gguf](https://huggingface.co/bartowski/pszemraj_jamba-900M-v0.13-KIx2-GGUF/blob/main/pszemraj_jamba-900M-v0.13-KIx2-Q6_K_L.gguf) | Q6_K_L | 0.76GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. | +| [jamba-900M-v0.13-KIx2-Q6_K.gguf](https://huggingface.co/bartowski/pszemraj_jamba-900M-v0.13-KIx2-GGUF/blob/main/pszemraj_jamba-900M-v0.13-KIx2-Q6_K.gguf) | Q6_K | 0.73GB | false | Very high quality, near perfect, *recommended*. | +| [jamba-900M-v0.13-KIx2-Q5_K_L.gguf](https://huggingface.co/bartowski/pszemraj_jamba-900M-v0.13-KIx2-GGUF/blob/main/pszemraj_jamba-900M-v0.13-KIx2-Q5_K_L.gguf) | Q5_K_L | 0.68GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. | +| [jamba-900M-v0.13-KIx2-Q5_K_M.gguf](https://huggingface.co/bartowski/pszemraj_jamba-900M-v0.13-KIx2-GGUF/blob/main/pszemraj_jamba-900M-v0.13-KIx2-Q5_K_M.gguf) | Q5_K_M | 0.63GB | false | High quality, *recommended*. | +| [jamba-900M-v0.13-KIx2-Q5_K_S.gguf](https://huggingface.co/bartowski/pszemraj_jamba-900M-v0.13-KIx2-GGUF/blob/main/pszemraj_jamba-900M-v0.13-KIx2-Q5_K_S.gguf) | Q5_K_S | 0.62GB | false | High quality, *recommended*. | +| [jamba-900M-v0.13-KIx2-Q4_K_L.gguf](https://huggingface.co/bartowski/pszemraj_jamba-900M-v0.13-KIx2-GGUF/blob/main/pszemraj_jamba-900M-v0.13-KIx2-Q4_K_L.gguf) | Q4_K_L | 0.59GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. | +| [jamba-900M-v0.13-KIx2-Q4_1.gguf](https://huggingface.co/bartowski/pszemraj_jamba-900M-v0.13-KIx2-GGUF/blob/main/pszemraj_jamba-900M-v0.13-KIx2-Q4_1.gguf) | Q4_1 | 0.57GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. | +| [jamba-900M-v0.13-KIx2-Q4_K_M.gguf](https://huggingface.co/bartowski/pszemraj_jamba-900M-v0.13-KIx2-GGUF/blob/main/pszemraj_jamba-900M-v0.13-KIx2-Q4_K_M.gguf) | Q4_K_M | 0.54GB | false | Good quality, default size for most use cases, *recommended*. | +| [jamba-900M-v0.13-KIx2-Q4_K_S.gguf](https://huggingface.co/bartowski/pszemraj_jamba-900M-v0.13-KIx2-GGUF/blob/main/pszemraj_jamba-900M-v0.13-KIx2-Q4_K_S.gguf) | Q4_K_S | 0.53GB | false | Slightly lower quality with more space savings, *recommended*. | +| [jamba-900M-v0.13-KIx2-Q4_0.gguf](https://huggingface.co/bartowski/pszemraj_jamba-900M-v0.13-KIx2-GGUF/blob/main/pszemraj_jamba-900M-v0.13-KIx2-Q4_0.gguf) | Q4_0 | 0.53GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. | +| [jamba-900M-v0.13-KIx2-IQ4_NL.gguf](https://huggingface.co/bartowski/pszemraj_jamba-900M-v0.13-KIx2-GGUF/blob/main/pszemraj_jamba-900M-v0.13-KIx2-IQ4_NL.gguf) | IQ4_NL | 0.52GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. | +| [jamba-900M-v0.13-KIx2-IQ4_XS.gguf](https://huggingface.co/bartowski/pszemraj_jamba-900M-v0.13-KIx2-GGUF/blob/main/pszemraj_jamba-900M-v0.13-KIx2-IQ4_XS.gguf) | IQ4_XS | 0.50GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. | +| [jamba-900M-v0.13-KIx2-Q3_K_XL.gguf](https://huggingface.co/bartowski/pszemraj_jamba-900M-v0.13-KIx2-GGUF/blob/main/pszemraj_jamba-900M-v0.13-KIx2-Q3_K_XL.gguf) | Q3_K_XL | 0.49GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. | +| [jamba-900M-v0.13-KIx2-Q3_K_L.gguf](https://huggingface.co/bartowski/pszemraj_jamba-900M-v0.13-KIx2-GGUF/blob/main/pszemraj_jamba-900M-v0.13-KIx2-Q3_K_L.gguf) | Q3_K_L | 0.44GB | false | Lower quality but usable, good for low RAM availability. | +| [jamba-900M-v0.13-KIx2-Q3_K_M.gguf](https://huggingface.co/bartowski/pszemraj_jamba-900M-v0.13-KIx2-GGUF/blob/main/pszemraj_jamba-900M-v0.13-KIx2-Q3_K_M.gguf) | Q3_K_M | 0.43GB | false | Low quality. | +| [jamba-900M-v0.13-KIx2-IQ3_M.gguf](https://huggingface.co/bartowski/pszemraj_jamba-900M-v0.13-KIx2-GGUF/blob/main/pszemraj_jamba-900M-v0.13-KIx2-IQ3_M.gguf) | IQ3_M | 0.42GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. | +| [jamba-900M-v0.13-KIx2-Q3_K_S.gguf](https://huggingface.co/bartowski/pszemraj_jamba-900M-v0.13-KIx2-GGUF/blob/main/pszemraj_jamba-900M-v0.13-KIx2-Q3_K_S.gguf) | Q3_K_S | 0.41GB | false | Low quality, not recommended. | +| [jamba-900M-v0.13-KIx2-IQ3_XS.gguf](https://huggingface.co/bartowski/pszemraj_jamba-900M-v0.13-KIx2-GGUF/blob/main/pszemraj_jamba-900M-v0.13-KIx2-IQ3_XS.gguf) | IQ3_XS | 0.40GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. | + +## 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/pszemraj_jamba-900M-v0.13-KIx2-GGUF --include "pszemraj_jamba-900M-v0.13-KIx2-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/pszemraj_jamba-900M-v0.13-KIx2-GGUF --include "pszemraj_jamba-900M-v0.13-KIx2-Q8_0/*" --local-dir ./ +``` + +You can either specify a new local-dir (pszemraj_jamba-900M-v0.13-KIx2-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/pszemraj_jamba-900M-v0.13-KIx2-IQ3_M.gguf b/pszemraj_jamba-900M-v0.13-KIx2-IQ3_M.gguf new file mode 100644 index 0000000..8504071 --- /dev/null +++ b/pszemraj_jamba-900M-v0.13-KIx2-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67ae2b4e9f8f74daef935823cc69d76534f965669898e51afc61a6bd539a460b +size 423922144 diff --git a/pszemraj_jamba-900M-v0.13-KIx2-IQ3_XS.gguf b/pszemraj_jamba-900M-v0.13-KIx2-IQ3_XS.gguf new file mode 100644 index 0000000..27c150b --- /dev/null +++ b/pszemraj_jamba-900M-v0.13-KIx2-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28253f22d2e3212a2dee9b7ee830b269d33d19ea1a0805e10c8a2115ddaf57eb +size 395889120 diff --git a/pszemraj_jamba-900M-v0.13-KIx2-IQ4_NL.gguf b/pszemraj_jamba-900M-v0.13-KIx2-IQ4_NL.gguf new file mode 100644 index 0000000..c3aa59f --- /dev/null +++ b/pszemraj_jamba-900M-v0.13-KIx2-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92de468cced8756be5e43ee85af5ebc736dd414183a9538dd3c8f44189ca21b1 +size 521694176 diff --git a/pszemraj_jamba-900M-v0.13-KIx2-IQ4_XS.gguf b/pszemraj_jamba-900M-v0.13-KIx2-IQ4_XS.gguf new file mode 100644 index 0000000..d7d087c --- /dev/null +++ b/pszemraj_jamba-900M-v0.13-KIx2-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20cc678d7aa5736a3bdc20317b3e4754b2880b5eed22136490c62d56c43ad025 +size 496198624 diff --git a/pszemraj_jamba-900M-v0.13-KIx2-Q3_K_L.gguf b/pszemraj_jamba-900M-v0.13-KIx2-Q3_K_L.gguf new file mode 100644 index 0000000..abd5b71 --- /dev/null +++ b/pszemraj_jamba-900M-v0.13-KIx2-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:816688e694947a37287f2c8c606821debc3346ae640d2cc0a241460aba8e61fe +size 436316640 diff --git a/pszemraj_jamba-900M-v0.13-KIx2-Q3_K_M.gguf b/pszemraj_jamba-900M-v0.13-KIx2-Q3_K_M.gguf new file mode 100644 index 0000000..abe0df3 --- /dev/null +++ b/pszemraj_jamba-900M-v0.13-KIx2-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c85692ce0d9ab4f2844f570f585aa424b9bf93e85e33babaaa83ee94e9d1cc2 +size 425593312 diff --git a/pszemraj_jamba-900M-v0.13-KIx2-Q3_K_S.gguf b/pszemraj_jamba-900M-v0.13-KIx2-Q3_K_S.gguf new file mode 100644 index 0000000..85a650e --- /dev/null +++ b/pszemraj_jamba-900M-v0.13-KIx2-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aaab54e59872c1e2ca5b07dc71ef5a2daf73a7d61ab69e45b22e6d8a1c1e72e7 +size 413338080 diff --git a/pszemraj_jamba-900M-v0.13-KIx2-Q3_K_XL.gguf b/pszemraj_jamba-900M-v0.13-KIx2-Q3_K_XL.gguf new file mode 100644 index 0000000..6e89d14 --- /dev/null +++ b/pszemraj_jamba-900M-v0.13-KIx2-Q3_K_XL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8baea54f8da4649e12979f588a82a2930d15b7138e069fef8fa1385f4673a4bd +size 494578144 diff --git a/pszemraj_jamba-900M-v0.13-KIx2-Q4_0.gguf b/pszemraj_jamba-900M-v0.13-KIx2-Q4_0.gguf new file mode 100644 index 0000000..c8c37e5 --- /dev/null +++ b/pszemraj_jamba-900M-v0.13-KIx2-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab963eb0bcec4f454c1692bddc2e70dd0fa7e25541288721aa2e6a6f5d49c4b1 +size 525757408 diff --git a/pszemraj_jamba-900M-v0.13-KIx2-Q4_1.gguf b/pszemraj_jamba-900M-v0.13-KIx2-Q4_1.gguf new file mode 100644 index 0000000..26a48f3 --- /dev/null +++ b/pszemraj_jamba-900M-v0.13-KIx2-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca6979c5397b370b6e829ba3a999265e4365f275debc610fa6ca6a89f910f353 +size 572488672 diff --git a/pszemraj_jamba-900M-v0.13-KIx2-Q4_K_L.gguf b/pszemraj_jamba-900M-v0.13-KIx2-Q4_K_L.gguf new file mode 100644 index 0000000..38827f5 --- /dev/null +++ b/pszemraj_jamba-900M-v0.13-KIx2-Q4_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21c2a139b823e87e6beedc33950b5a614deeff4f62e2cc880562a0cfbf44c35b +size 591657952 diff --git a/pszemraj_jamba-900M-v0.13-KIx2-Q4_K_M.gguf b/pszemraj_jamba-900M-v0.13-KIx2-Q4_K_M.gguf new file mode 100644 index 0000000..c84d08e --- /dev/null +++ b/pszemraj_jamba-900M-v0.13-KIx2-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1c1154338e7d9f929a39800dc5bb5391e66a8400342bb9a74f88b6488540a69 +size 542239712 diff --git a/pszemraj_jamba-900M-v0.13-KIx2-Q4_K_S.gguf b/pszemraj_jamba-900M-v0.13-KIx2-Q4_K_S.gguf new file mode 100644 index 0000000..29bc4e4 --- /dev/null +++ b/pszemraj_jamba-900M-v0.13-KIx2-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:939c9431ed576768d0bdf3db372762846e6cef398c3d855e1e9c2ed43158a3b4 +size 530607072 diff --git a/pszemraj_jamba-900M-v0.13-KIx2-Q5_K_L.gguf b/pszemraj_jamba-900M-v0.13-KIx2-Q5_K_L.gguf new file mode 100644 index 0000000..206b65b --- /dev/null +++ b/pszemraj_jamba-900M-v0.13-KIx2-Q5_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0daf0064e7de6f46c89b496b314749c4da170b9e5e4909648acd296b5de8aa47 +size 675355616 diff --git a/pszemraj_jamba-900M-v0.13-KIx2-Q5_K_M.gguf b/pszemraj_jamba-900M-v0.13-KIx2-Q5_K_M.gguf new file mode 100644 index 0000000..e30d979 --- /dev/null +++ b/pszemraj_jamba-900M-v0.13-KIx2-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e9c10c9da37ab8cdbdcf9ee1000c19ef6917e1836240fea1be1571ed7505827 +size 634260448 diff --git a/pszemraj_jamba-900M-v0.13-KIx2-Q5_K_S.gguf b/pszemraj_jamba-900M-v0.13-KIx2-Q5_K_S.gguf new file mode 100644 index 0000000..5314f82 --- /dev/null +++ b/pszemraj_jamba-900M-v0.13-KIx2-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14b6f72069aa525dc3c762d8c5b61cdc30a80d94e1fa261baa75eae5b34e34d7 +size 623676384 diff --git a/pszemraj_jamba-900M-v0.13-KIx2-Q6_K.gguf b/pszemraj_jamba-900M-v0.13-KIx2-Q6_K.gguf new file mode 100644 index 0000000..930d845 --- /dev/null +++ b/pszemraj_jamba-900M-v0.13-KIx2-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d77bb43187ad7b6bc89ebe865b2ad1ba6b64a40129542f804867105e230ac78f +size 732450272 diff --git a/pszemraj_jamba-900M-v0.13-KIx2-Q6_K_L.gguf b/pszemraj_jamba-900M-v0.13-KIx2-Q6_K_L.gguf new file mode 100644 index 0000000..51e25cf --- /dev/null +++ b/pszemraj_jamba-900M-v0.13-KIx2-Q6_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26f2408bf770057619e10af05ccc7f6bf59020f44fd894a05154aa6778d765a2 +size 764702176 diff --git a/pszemraj_jamba-900M-v0.13-KIx2-Q8_0.gguf b/pszemraj_jamba-900M-v0.13-KIx2-Q8_0.gguf new file mode 100644 index 0000000..b0a4dcd --- /dev/null +++ b/pszemraj_jamba-900M-v0.13-KIx2-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4511988975f4f4200f6f3fa89692bf672776286de01985d76f3e140ed00be121 +size 946928608 diff --git a/pszemraj_jamba-900M-v0.13-KIx2-bf16.gguf b/pszemraj_jamba-900M-v0.13-KIx2-bf16.gguf new file mode 100644 index 0000000..f96f929 --- /dev/null +++ b/pszemraj_jamba-900M-v0.13-KIx2-bf16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1e3c6a5a795491ba34e5b8bfdbf58f5392614f25ee9d1f58d6bb108ea0263a7 +size 1778641600 diff --git a/pszemraj_jamba-900M-v0.13-KIx2.imatrix b/pszemraj_jamba-900M-v0.13-KIx2.imatrix new file mode 100644 index 0000000..d78e84d Binary files /dev/null and b/pszemraj_jamba-900M-v0.13-KIx2.imatrix differ