commit 84bb5404904fb0b8dee8a9ac6baffc0338e88d2d Author: ModelHub XC Date: Sat Aug 8 17:53:13 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: bartowski/google_txgemma-9b-chat-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f39e726 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,49 @@ +*.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 + +google_txgemma-9b-chat.imatrix 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..de26553 --- /dev/null +++ b/README.md @@ -0,0 +1,186 @@ +--- +quantized_by: bartowski +pipeline_tag: text-generation +tags: +- therapeutics +- drug-development +base_model: google/txgemma-9b-chat +language: +- en +extra_gated_heading: Access TxGemma on Hugging Face +license_name: health-ai-developer-foundations +license: other +extra_gated_prompt: To access TxGemma on Hugging Face, you're required to review and + agree to [Health AI Developer Foundation's terms of use](https://developers.google.com/health-ai-developer-foundations/terms). + To do this, please ensure you're logged in to Hugging Face and click below. Requests + are processed immediately. +extra_gated_button_content: Acknowledge license +base_model_relation: quantized +license_link: https://developers.google.com/health-ai-developer-foundations/terms +--- + +## Llamacpp imatrix Quantizations of txgemma-9b-chat by google + +Using llama.cpp release b4944 for quantization. + +Original model: https://huggingface.co/google/txgemma-9b-chat + +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 + +``` +user +{prompt} +model + +model +``` + +Note that this model does not support a System prompt. + +## Download a file (not the whole branch) from below: + +| Filename | Quant type | File Size | Split | Description | +| -------- | ---------- | --------- | ----- | ----------- | +| [txgemma-9b-chat-bf16.gguf](https://huggingface.co/bartowski/google_txgemma-9b-chat-GGUF/blob/main/google_txgemma-9b-chat-bf16.gguf) | bf16 | 18.49GB | false | Full BF16 weights. | +| [txgemma-9b-chat-Q8_0.gguf](https://huggingface.co/bartowski/google_txgemma-9b-chat-GGUF/blob/main/google_txgemma-9b-chat-Q8_0.gguf) | Q8_0 | 9.83GB | false | Extremely high quality, generally unneeded but max available quant. | +| [txgemma-9b-chat-Q6_K_L.gguf](https://huggingface.co/bartowski/google_txgemma-9b-chat-GGUF/blob/main/google_txgemma-9b-chat-Q6_K_L.gguf) | Q6_K_L | 7.81GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. | +| [txgemma-9b-chat-Q6_K.gguf](https://huggingface.co/bartowski/google_txgemma-9b-chat-GGUF/blob/main/google_txgemma-9b-chat-Q6_K.gguf) | Q6_K | 7.59GB | false | Very high quality, near perfect, *recommended*. | +| [txgemma-9b-chat-Q5_K_L.gguf](https://huggingface.co/bartowski/google_txgemma-9b-chat-GGUF/blob/main/google_txgemma-9b-chat-Q5_K_L.gguf) | Q5_K_L | 6.87GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. | +| [txgemma-9b-chat-Q5_K_M.gguf](https://huggingface.co/bartowski/google_txgemma-9b-chat-GGUF/blob/main/google_txgemma-9b-chat-Q5_K_M.gguf) | Q5_K_M | 6.65GB | false | High quality, *recommended*. | +| [txgemma-9b-chat-Q5_K_S.gguf](https://huggingface.co/bartowski/google_txgemma-9b-chat-GGUF/blob/main/google_txgemma-9b-chat-Q5_K_S.gguf) | Q5_K_S | 6.48GB | false | High quality, *recommended*. | +| [txgemma-9b-chat-Q4_K_L.gguf](https://huggingface.co/bartowski/google_txgemma-9b-chat-GGUF/blob/main/google_txgemma-9b-chat-Q4_K_L.gguf) | Q4_K_L | 5.98GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. | +| [txgemma-9b-chat-Q4_1.gguf](https://huggingface.co/bartowski/google_txgemma-9b-chat-GGUF/blob/main/google_txgemma-9b-chat-Q4_1.gguf) | Q4_1 | 5.96GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. | +| [txgemma-9b-chat-Q4_K_M.gguf](https://huggingface.co/bartowski/google_txgemma-9b-chat-GGUF/blob/main/google_txgemma-9b-chat-Q4_K_M.gguf) | Q4_K_M | 5.76GB | false | Good quality, default size for most use cases, *recommended*. | +| [txgemma-9b-chat-Q4_K_S.gguf](https://huggingface.co/bartowski/google_txgemma-9b-chat-GGUF/blob/main/google_txgemma-9b-chat-Q4_K_S.gguf) | Q4_K_S | 5.48GB | false | Slightly lower quality with more space savings, *recommended*. | +| [txgemma-9b-chat-Q4_0.gguf](https://huggingface.co/bartowski/google_txgemma-9b-chat-GGUF/blob/main/google_txgemma-9b-chat-Q4_0.gguf) | Q4_0 | 5.46GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. | +| [txgemma-9b-chat-IQ4_NL.gguf](https://huggingface.co/bartowski/google_txgemma-9b-chat-GGUF/blob/main/google_txgemma-9b-chat-IQ4_NL.gguf) | IQ4_NL | 5.44GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. | +| [txgemma-9b-chat-Q3_K_XL.gguf](https://huggingface.co/bartowski/google_txgemma-9b-chat-GGUF/blob/main/google_txgemma-9b-chat-Q3_K_XL.gguf) | Q3_K_XL | 5.35GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. | +| [txgemma-9b-chat-IQ4_XS.gguf](https://huggingface.co/bartowski/google_txgemma-9b-chat-GGUF/blob/main/google_txgemma-9b-chat-IQ4_XS.gguf) | IQ4_XS | 5.18GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. | +| [txgemma-9b-chat-Q3_K_L.gguf](https://huggingface.co/bartowski/google_txgemma-9b-chat-GGUF/blob/main/google_txgemma-9b-chat-Q3_K_L.gguf) | Q3_K_L | 5.13GB | false | Lower quality but usable, good for low RAM availability. | +| [txgemma-9b-chat-Q3_K_M.gguf](https://huggingface.co/bartowski/google_txgemma-9b-chat-GGUF/blob/main/google_txgemma-9b-chat-Q3_K_M.gguf) | Q3_K_M | 4.76GB | false | Low quality. | +| [txgemma-9b-chat-IQ3_M.gguf](https://huggingface.co/bartowski/google_txgemma-9b-chat-GGUF/blob/main/google_txgemma-9b-chat-IQ3_M.gguf) | IQ3_M | 4.49GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. | +| [txgemma-9b-chat-Q3_K_S.gguf](https://huggingface.co/bartowski/google_txgemma-9b-chat-GGUF/blob/main/google_txgemma-9b-chat-Q3_K_S.gguf) | Q3_K_S | 4.34GB | false | Low quality, not recommended. | +| [txgemma-9b-chat-IQ3_XS.gguf](https://huggingface.co/bartowski/google_txgemma-9b-chat-GGUF/blob/main/google_txgemma-9b-chat-IQ3_XS.gguf) | IQ3_XS | 4.14GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. | +| [txgemma-9b-chat-Q2_K_L.gguf](https://huggingface.co/bartowski/google_txgemma-9b-chat-GGUF/blob/main/google_txgemma-9b-chat-Q2_K_L.gguf) | Q2_K_L | 4.03GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. | +| [txgemma-9b-chat-Q2_K.gguf](https://huggingface.co/bartowski/google_txgemma-9b-chat-GGUF/blob/main/google_txgemma-9b-chat-Q2_K.gguf) | Q2_K | 3.81GB | false | Very low quality but surprisingly usable. | +| [txgemma-9b-chat-IQ3_XXS.gguf](https://huggingface.co/bartowski/google_txgemma-9b-chat-GGUF/blob/main/google_txgemma-9b-chat-IQ3_XXS.gguf) | IQ3_XXS | 3.80GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. | +| [txgemma-9b-chat-IQ2_M.gguf](https://huggingface.co/bartowski/google_txgemma-9b-chat-GGUF/blob/main/google_txgemma-9b-chat-IQ2_M.gguf) | IQ2_M | 3.43GB | 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/google_txgemma-9b-chat-GGUF --include "google_txgemma-9b-chat-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/google_txgemma-9b-chat-GGUF --include "google_txgemma-9b-chat-Q8_0/*" --local-dir ./ +``` + +You can either specify a new local-dir (google_txgemma-9b-chat-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/google_txgemma-9b-chat-IQ2_M.gguf b/google_txgemma-9b-chat-IQ2_M.gguf new file mode 100644 index 0000000..144aa75 --- /dev/null +++ b/google_txgemma-9b-chat-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13438ace4c89079c5a08968e4f635ffe8b99e7e3df545a72246691f4a25814f8 +size 3434669536 diff --git a/google_txgemma-9b-chat-IQ3_M.gguf b/google_txgemma-9b-chat-IQ3_M.gguf new file mode 100644 index 0000000..613949d --- /dev/null +++ b/google_txgemma-9b-chat-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1227cc8c6c53958b03e68aaa14596e91f38cf191d2b16641d7cb06e01d6b1dbd +size 4494616032 diff --git a/google_txgemma-9b-chat-IQ3_XS.gguf b/google_txgemma-9b-chat-IQ3_XS.gguf new file mode 100644 index 0000000..d340384 --- /dev/null +++ b/google_txgemma-9b-chat-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a96c23062cbd62bb8617c0389ea4cd90bba8ca9fea3f66ff23418621fda2fdc4 +size 4144989664 diff --git a/google_txgemma-9b-chat-IQ3_XXS.gguf b/google_txgemma-9b-chat-IQ3_XXS.gguf new file mode 100644 index 0000000..e945d66 --- /dev/null +++ b/google_txgemma-9b-chat-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c63430471c140c0e74a2ec7fd0549f39ac5b77ae6e4bb8c6df56bd2e47d0c131 +size 3796739552 diff --git a/google_txgemma-9b-chat-IQ4_NL.gguf b/google_txgemma-9b-chat-IQ4_NL.gguf new file mode 100644 index 0000000..4695735 --- /dev/null +++ b/google_txgemma-9b-chat-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0cfa7f8e093948e4d88caf7488ddbd7d53401cc8f122c33aa551e6c44a91251f +size 5443143136 diff --git a/google_txgemma-9b-chat-IQ4_XS.gguf b/google_txgemma-9b-chat-IQ4_XS.gguf new file mode 100644 index 0000000..9fcdd5b --- /dev/null +++ b/google_txgemma-9b-chat-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95c776221dcad5997fdb80879d1eacd36072ae114556945221af28e6ff6f4d13 +size 5183030752 diff --git a/google_txgemma-9b-chat-Q2_K.gguf b/google_txgemma-9b-chat-Q2_K.gguf new file mode 100644 index 0000000..52870dc --- /dev/null +++ b/google_txgemma-9b-chat-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9680499255d822cb54259bd96c391a011201000d1f993d9a200f42beb428895 +size 3805398496 diff --git a/google_txgemma-9b-chat-Q2_K_L.gguf b/google_txgemma-9b-chat-Q2_K_L.gguf new file mode 100644 index 0000000..3f26391 --- /dev/null +++ b/google_txgemma-9b-chat-Q2_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b67abdb4130cecca8c75e55cb7ae12aea54423fba69ccce4b9a85b3b7c4be71 +size 4027606496 diff --git a/google_txgemma-9b-chat-Q3_K_L.gguf b/google_txgemma-9b-chat-Q3_K_L.gguf new file mode 100644 index 0000000..5ee4311 --- /dev/null +++ b/google_txgemma-9b-chat-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50d15b7fc25fa5ecac5ccc0b10a2bc884a7bb81d746032129dee39c99389fd1d +size 5132453344 diff --git a/google_txgemma-9b-chat-Q3_K_M.gguf b/google_txgemma-9b-chat-Q3_K_M.gguf new file mode 100644 index 0000000..9c6f5f1 --- /dev/null +++ b/google_txgemma-9b-chat-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0df65a1ecfe6b37e9d369aa829a431bad541233bd48ffa61b71eef860f79b64 +size 4761781728 diff --git a/google_txgemma-9b-chat-Q3_K_S.gguf b/google_txgemma-9b-chat-Q3_K_S.gguf new file mode 100644 index 0000000..726cb68 --- /dev/null +++ b/google_txgemma-9b-chat-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70e480c3c56c23b9b5c22695f1c5af9b1953c7ae8b739c33d8e7f83331b1da6c +size 4337665504 diff --git a/google_txgemma-9b-chat-Q3_K_XL.gguf b/google_txgemma-9b-chat-Q3_K_XL.gguf new file mode 100644 index 0000000..7921fbb --- /dev/null +++ b/google_txgemma-9b-chat-Q3_K_XL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:256dd77fda1bbff8d3440a4da78fd25711db7ab75eaef9e8760022da5a85fc99 +size 5354661344 diff --git a/google_txgemma-9b-chat-Q4_0.gguf b/google_txgemma-9b-chat-Q4_0.gguf new file mode 100644 index 0000000..0659f84 --- /dev/null +++ b/google_txgemma-9b-chat-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07e32f26989f31206601e75f7cce52eacd46ba590c94049e124fa4149ff17e51 +size 5459199456 diff --git a/google_txgemma-9b-chat-Q4_1.gguf b/google_txgemma-9b-chat-Q4_1.gguf new file mode 100644 index 0000000..932f746 --- /dev/null +++ b/google_txgemma-9b-chat-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4fc47f1949eccf9fae21569347ce84d9937d2389e4c2c14c30318b942c5262c8 +size 5963367904 diff --git a/google_txgemma-9b-chat-Q4_K_L.gguf b/google_txgemma-9b-chat-Q4_K_L.gguf new file mode 100644 index 0000000..cd0146f --- /dev/null +++ b/google_txgemma-9b-chat-Q4_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5f0390ba1ace6a8b01587905eee90f02ac6e3f4cb10cc38d087e938c636c530 +size 5983266272 diff --git a/google_txgemma-9b-chat-Q4_K_M.gguf b/google_txgemma-9b-chat-Q4_K_M.gguf new file mode 100644 index 0000000..bed8be9 --- /dev/null +++ b/google_txgemma-9b-chat-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8af059c47612672e2d51d764968f5a45c73513e3f4e4f2c408c7c303e9847bd5 +size 5761058272 diff --git a/google_txgemma-9b-chat-Q4_K_S.gguf b/google_txgemma-9b-chat-Q4_K_S.gguf new file mode 100644 index 0000000..f5e327a --- /dev/null +++ b/google_txgemma-9b-chat-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4706dd83196edaa7ca01528f5589295a9a3cd24257ba6a1c4e7443f3cab6b5ca +size 5478925792 diff --git a/google_txgemma-9b-chat-Q5_K_L.gguf b/google_txgemma-9b-chat-Q5_K_L.gguf new file mode 100644 index 0000000..4047c79 --- /dev/null +++ b/google_txgemma-9b-chat-Q5_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8be4d671315877de77303d2f03b254183e6bc2ab3516757476c988f4c76cf6fb +size 6869575136 diff --git a/google_txgemma-9b-chat-Q5_K_M.gguf b/google_txgemma-9b-chat-Q5_K_M.gguf new file mode 100644 index 0000000..ecf80ef --- /dev/null +++ b/google_txgemma-9b-chat-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e61f4dd93e780eaa191b40735e25e647aa817fcf30c1ccc98155236354299f6d +size 6647367136 diff --git a/google_txgemma-9b-chat-Q5_K_S.gguf b/google_txgemma-9b-chat-Q5_K_S.gguf new file mode 100644 index 0000000..a601167 --- /dev/null +++ b/google_txgemma-9b-chat-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d066d9e3f73a6389879a7db52e4e312c3dcce706e4e984d7de97801ce716831a +size 6483592672 diff --git a/google_txgemma-9b-chat-Q6_K.gguf b/google_txgemma-9b-chat-Q6_K.gguf new file mode 100644 index 0000000..ffe4e3a --- /dev/null +++ b/google_txgemma-9b-chat-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3886f08a656456c91566daeb2846fbc65a0215a50f0840ec0fbe0326b591ff6b +size 7589070304 diff --git a/google_txgemma-9b-chat-Q6_K_L.gguf b/google_txgemma-9b-chat-Q6_K_L.gguf new file mode 100644 index 0000000..3c291ab --- /dev/null +++ b/google_txgemma-9b-chat-Q6_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:928b8e7e068046fb67f7c924afff5a2b6138ac38ef680593a92cda11159b1004 +size 7811278304 diff --git a/google_txgemma-9b-chat-Q8_0.gguf b/google_txgemma-9b-chat-Q8_0.gguf new file mode 100644 index 0000000..9dfe1ab --- /dev/null +++ b/google_txgemma-9b-chat-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80f8aca4548b073469aa8dc366289d87f8f0cb538f646897fe0e376b6e47b324 +size 9827149280 diff --git a/google_txgemma-9b-chat-bf16.gguf b/google_txgemma-9b-chat-bf16.gguf new file mode 100644 index 0000000..9b5efcb --- /dev/null +++ b/google_txgemma-9b-chat-bf16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4f70a09188cd9d6fe02d0b385b6a1b4fa527bbeb90afee262e245e70c32b1f2 +size 18490680512 diff --git a/google_txgemma-9b-chat.imatrix b/google_txgemma-9b-chat.imatrix new file mode 100644 index 0000000..9925747 --- /dev/null +++ b/google_txgemma-9b-chat.imatrix @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b478f58d2d7983d6a73ce7ae5950bd197483043e5cb9105ec39b061c4af0ca6e +size 6116900