commit 67a168f9c967882b81107b13d31a8d2873487a8d Author: ModelHub XC Date: Thu Jun 18 02:17:13 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: bartowski/Tesslate_Tessa-T1-3B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..53d7257 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,47 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bin.* filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zstandard filter=lfs diff=lfs merge=lfs -text +*.tfevents* filter=lfs diff=lfs merge=lfs -text +*.db* filter=lfs diff=lfs merge=lfs -text +*.ark* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.gguf* filter=lfs diff=lfs merge=lfs -text +*.ggml filter=lfs diff=lfs merge=lfs -text +*.llamafile* filter=lfs diff=lfs merge=lfs -text +*.pt2 filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text \ No newline at end of file diff --git a/README.md b/README.md new file mode 100644 index 0000000..821bf81 --- /dev/null +++ b/README.md @@ -0,0 +1,180 @@ +--- +quantized_by: bartowski +pipeline_tag: text-generation +tags: +- text-generation-inference +- transformers +- qwen2 +- trl +base_model_relation: quantized +language: +- en +base_model: Tesslate/Tessa-T1-3B +license: apache-2.0 +datasets: +- Tesslate/Tessa-T1-Dataset +--- + +## Llamacpp imatrix Quantizations of Tessa-T1-3B by Tesslate + +Using llama.cpp release b4978 for quantization. + +Original model: https://huggingface.co/Tesslate/Tessa-T1-3B + +All quants made using imatrix option with dataset from [here](https://gist.github.com/bartowski1182/eb213dccb3571f863da82e99418f81e8) + +Run them in [LM Studio](https://lmstudio.ai/) + +Run them directly with [llama.cpp](https://github.com/ggerganov/llama.cpp), or any other llama.cpp based project + +## Prompt format + +``` +<|im_start|>system +{system_prompt}<|im_end|> +<|im_start|>user +{prompt}<|im_end|> +<|im_start|>assistant +``` + +## Download a file (not the whole branch) from below: + +| Filename | Quant type | File Size | Split | Description | +| -------- | ---------- | --------- | ----- | ----------- | +| [Tessa-T1-3B-bf16.gguf](https://huggingface.co/bartowski/Tesslate_Tessa-T1-3B-GGUF/blob/main/Tesslate_Tessa-T1-3B-bf16.gguf) | bf16 | 6.18GB | false | Full BF16 weights. | +| [Tessa-T1-3B-Q8_0.gguf](https://huggingface.co/bartowski/Tesslate_Tessa-T1-3B-GGUF/blob/main/Tesslate_Tessa-T1-3B-Q8_0.gguf) | Q8_0 | 3.29GB | false | Extremely high quality, generally unneeded but max available quant. | +| [Tessa-T1-3B-Q6_K_L.gguf](https://huggingface.co/bartowski/Tesslate_Tessa-T1-3B-GGUF/blob/main/Tesslate_Tessa-T1-3B-Q6_K_L.gguf) | Q6_K_L | 2.61GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. | +| [Tessa-T1-3B-Q6_K.gguf](https://huggingface.co/bartowski/Tesslate_Tessa-T1-3B-GGUF/blob/main/Tesslate_Tessa-T1-3B-Q6_K.gguf) | Q6_K | 2.54GB | false | Very high quality, near perfect, *recommended*. | +| [Tessa-T1-3B-Q5_K_L.gguf](https://huggingface.co/bartowski/Tesslate_Tessa-T1-3B-GGUF/blob/main/Tesslate_Tessa-T1-3B-Q5_K_L.gguf) | Q5_K_L | 2.30GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. | +| [Tessa-T1-3B-Q5_K_M.gguf](https://huggingface.co/bartowski/Tesslate_Tessa-T1-3B-GGUF/blob/main/Tesslate_Tessa-T1-3B-Q5_K_M.gguf) | Q5_K_M | 2.22GB | false | High quality, *recommended*. | +| [Tessa-T1-3B-Q5_K_S.gguf](https://huggingface.co/bartowski/Tesslate_Tessa-T1-3B-GGUF/blob/main/Tesslate_Tessa-T1-3B-Q5_K_S.gguf) | Q5_K_S | 2.17GB | false | High quality, *recommended*. | +| [Tessa-T1-3B-Q4_K_L.gguf](https://huggingface.co/bartowski/Tesslate_Tessa-T1-3B-GGUF/blob/main/Tesslate_Tessa-T1-3B-Q4_K_L.gguf) | Q4_K_L | 2.01GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. | +| [Tessa-T1-3B-Q4_1.gguf](https://huggingface.co/bartowski/Tesslate_Tessa-T1-3B-GGUF/blob/main/Tesslate_Tessa-T1-3B-Q4_1.gguf) | Q4_1 | 2.00GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. | +| [Tessa-T1-3B-Q4_K_M.gguf](https://huggingface.co/bartowski/Tesslate_Tessa-T1-3B-GGUF/blob/main/Tesslate_Tessa-T1-3B-Q4_K_M.gguf) | Q4_K_M | 1.93GB | false | Good quality, default size for most use cases, *recommended*. | +| [Tessa-T1-3B-Q4_K_S.gguf](https://huggingface.co/bartowski/Tesslate_Tessa-T1-3B-GGUF/blob/main/Tesslate_Tessa-T1-3B-Q4_K_S.gguf) | Q4_K_S | 1.83GB | false | Slightly lower quality with more space savings, *recommended*. | +| [Tessa-T1-3B-Q4_0.gguf](https://huggingface.co/bartowski/Tesslate_Tessa-T1-3B-GGUF/blob/main/Tesslate_Tessa-T1-3B-Q4_0.gguf) | Q4_0 | 1.83GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. | +| [Tessa-T1-3B-IQ4_NL.gguf](https://huggingface.co/bartowski/Tesslate_Tessa-T1-3B-GGUF/blob/main/Tesslate_Tessa-T1-3B-IQ4_NL.gguf) | IQ4_NL | 1.83GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. | +| [Tessa-T1-3B-Q3_K_XL.gguf](https://huggingface.co/bartowski/Tesslate_Tessa-T1-3B-GGUF/blob/main/Tesslate_Tessa-T1-3B-Q3_K_XL.gguf) | Q3_K_XL | 1.78GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. | +| [Tessa-T1-3B-IQ4_XS.gguf](https://huggingface.co/bartowski/Tesslate_Tessa-T1-3B-GGUF/blob/main/Tesslate_Tessa-T1-3B-IQ4_XS.gguf) | IQ4_XS | 1.74GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. | +| [Tessa-T1-3B-Q3_K_L.gguf](https://huggingface.co/bartowski/Tesslate_Tessa-T1-3B-GGUF/blob/main/Tesslate_Tessa-T1-3B-Q3_K_L.gguf) | Q3_K_L | 1.71GB | false | Lower quality but usable, good for low RAM availability. | +| [Tessa-T1-3B-Q3_K_M.gguf](https://huggingface.co/bartowski/Tesslate_Tessa-T1-3B-GGUF/blob/main/Tesslate_Tessa-T1-3B-Q3_K_M.gguf) | Q3_K_M | 1.59GB | false | Low quality. | +| [Tessa-T1-3B-IQ3_M.gguf](https://huggingface.co/bartowski/Tesslate_Tessa-T1-3B-GGUF/blob/main/Tesslate_Tessa-T1-3B-IQ3_M.gguf) | IQ3_M | 1.49GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. | +| [Tessa-T1-3B-Q3_K_S.gguf](https://huggingface.co/bartowski/Tesslate_Tessa-T1-3B-GGUF/blob/main/Tesslate_Tessa-T1-3B-Q3_K_S.gguf) | Q3_K_S | 1.45GB | false | Low quality, not recommended. | +| [Tessa-T1-3B-IQ3_XS.gguf](https://huggingface.co/bartowski/Tesslate_Tessa-T1-3B-GGUF/blob/main/Tesslate_Tessa-T1-3B-IQ3_XS.gguf) | IQ3_XS | 1.39GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. | +| [Tessa-T1-3B-Q2_K_L.gguf](https://huggingface.co/bartowski/Tesslate_Tessa-T1-3B-GGUF/blob/main/Tesslate_Tessa-T1-3B-Q2_K_L.gguf) | Q2_K_L | 1.35GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. | +| [Tessa-T1-3B-IQ3_XXS.gguf](https://huggingface.co/bartowski/Tesslate_Tessa-T1-3B-GGUF/blob/main/Tesslate_Tessa-T1-3B-IQ3_XXS.gguf) | IQ3_XXS | 1.28GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. | +| [Tessa-T1-3B-Q2_K.gguf](https://huggingface.co/bartowski/Tesslate_Tessa-T1-3B-GGUF/blob/main/Tesslate_Tessa-T1-3B-Q2_K.gguf) | Q2_K | 1.27GB | false | Very low quality but surprisingly usable. | +| [Tessa-T1-3B-IQ2_M.gguf](https://huggingface.co/bartowski/Tesslate_Tessa-T1-3B-GGUF/blob/main/Tesslate_Tessa-T1-3B-IQ2_M.gguf) | IQ2_M | 1.14GB | false | Relatively low quality, uses SOTA techniques to be surprisingly usable. | + +## Embed/output weights + +Some of these quants (Q3_K_XL, Q4_K_L etc) are the standard quantization method with the embeddings and output weights quantized to Q8_0 instead of what they would normally default to. + +## Downloading using huggingface-cli + +
+ Click to view download instructions + +First, make sure you have hugginface-cli installed: + +``` +pip install -U "huggingface_hub[cli]" +``` + +Then, you can target the specific file you want: + +``` +huggingface-cli download bartowski/Tesslate_Tessa-T1-3B-GGUF --include "Tesslate_Tessa-T1-3B-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/Tesslate_Tessa-T1-3B-GGUF --include "Tesslate_Tessa-T1-3B-Q8_0/*" --local-dir ./ +``` + +You can either specify a new local-dir (Tesslate_Tessa-T1-3B-Q8_0) or download them all in place (./) + +
+ +## ARM/AVX information + +Previously, you would download Q4_0_4_4/4_8/8_8, and these would have their weights interleaved in memory in order to improve performance on ARM and AVX machines by loading up more data in one pass. + +Now, however, there is something called "online repacking" for weights. details in [this PR](https://github.com/ggerganov/llama.cpp/pull/9921). If you use Q4_0 and your hardware would benefit from repacking weights, it will do it automatically on the fly. + +As of llama.cpp build [b4282](https://github.com/ggerganov/llama.cpp/releases/tag/b4282) you will not be able to run the Q4_0_X_X files and will instead need to use Q4_0. + +Additionally, if you want to get slightly better quality for , you can use IQ4_NL thanks to [this PR](https://github.com/ggerganov/llama.cpp/pull/10541) which will also repack the weights for ARM, though only the 4_4 for now. The loading time may be slower but it will result in an overall speed incrase. + +
+ Click to view Q4_0_X_X information (deprecated + +I'm keeping this section to show the potential theoretical uplift in performance from using the Q4_0 with online repacking. + +
+ Click to view benchmarks on an AVX2 system (EPYC7702) + +| model | size | params | backend | threads | test | t/s | % (vs Q4_0) | +| ------------------------------ | ---------: | ---------: | ---------- | ------: | ------------: | -------------------: |-------------: | +| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | pp512 | 204.03 ± 1.03 | 100% | +| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | pp1024 | 282.92 ± 0.19 | 100% | +| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | pp2048 | 259.49 ± 0.44 | 100% | +| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | tg128 | 39.12 ± 0.27 | 100% | +| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | tg256 | 39.31 ± 0.69 | 100% | +| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | tg512 | 40.52 ± 0.03 | 100% | +| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | pp512 | 301.02 ± 1.74 | 147% | +| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | pp1024 | 287.23 ± 0.20 | 101% | +| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | pp2048 | 262.77 ± 1.81 | 101% | +| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | tg128 | 18.80 ± 0.99 | 48% | +| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | tg256 | 24.46 ± 3.04 | 83% | +| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | tg512 | 36.32 ± 3.59 | 90% | +| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | pp512 | 271.71 ± 3.53 | 133% | +| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | pp1024 | 279.86 ± 45.63 | 100% | +| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | pp2048 | 320.77 ± 5.00 | 124% | +| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | tg128 | 43.51 ± 0.05 | 111% | +| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | tg256 | 43.35 ± 0.09 | 110% | +| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | tg512 | 42.60 ± 0.31 | 105% | + +Q4_0_8_8 offers a nice bump to prompt processing and a small bump to text generation + +
+ +
+ +## Which file should I choose? + +
+ Click here for details + +A great write up with charts showing various performances is provided by Artefact2 [here](https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9) + +The first thing to figure out is how big a model you can run. To do this, you'll need to figure out how much RAM and/or VRAM you have. + +If you want your model running as FAST as possible, you'll want to fit the whole thing on your GPU's VRAM. Aim for a quant with a file size 1-2GB smaller than your GPU's total VRAM. + +If you want the absolute maximum quality, add both your system RAM and your GPU's VRAM together, then similarly grab a quant with a file size 1-2GB Smaller than that total. + +Next, you'll need to decide if you want to use an 'I-quant' or a 'K-quant'. + +If you don't want to think too much, grab one of the K-quants. These are in format 'QX_K_X', like Q5_K_M. + +If you want to get more into the weeds, you can check out this extremely useful feature chart: + +[llama.cpp feature matrix](https://github.com/ggerganov/llama.cpp/wiki/Feature-matrix) + +But basically, if you're aiming for below Q4, and you're running cuBLAS (Nvidia) or rocBLAS (AMD), you should look towards the I-quants. These are in format IQX_X, like IQ3_M. These are newer and offer better performance for their size. + +These I-quants can also be used on CPU, but will be slower than their K-quant equivalent, so speed vs performance is a tradeoff you'll have to decide. + +
+ +## Credits + +Thank you kalomaze and Dampf for assistance in creating the imatrix calibration dataset. + +Thank you ZeroWw for the inspiration to experiment with embed/output. + +Thank you to LM Studio for sponsoring my work. + +Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski diff --git a/Tesslate_Tessa-T1-3B-IQ2_M.gguf b/Tesslate_Tessa-T1-3B-IQ2_M.gguf new file mode 100644 index 0000000..363491c --- /dev/null +++ b/Tesslate_Tessa-T1-3B-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3821c0311cc202a35334e79b69a9f3fd8e2e7b3e3caea955fc62fe25af19775b +size 1140516128 diff --git a/Tesslate_Tessa-T1-3B-IQ3_M.gguf b/Tesslate_Tessa-T1-3B-IQ3_M.gguf new file mode 100644 index 0000000..85090d1 --- /dev/null +++ b/Tesslate_Tessa-T1-3B-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0734c58268a4e15e8b3fff83ddc171426380de2cf6c2a0372acdc30eeafb6ae +size 1488895264 diff --git a/Tesslate_Tessa-T1-3B-IQ3_XS.gguf b/Tesslate_Tessa-T1-3B-IQ3_XS.gguf new file mode 100644 index 0000000..4ee6c04 --- /dev/null +++ b/Tesslate_Tessa-T1-3B-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f55bc79f19ad07062e75af5ccab35019637afe73518445c11ae27c1847a5135 +size 1391836448 diff --git a/Tesslate_Tessa-T1-3B-IQ3_XXS.gguf b/Tesslate_Tessa-T1-3B-IQ3_XXS.gguf new file mode 100644 index 0000000..2e09d68 --- /dev/null +++ b/Tesslate_Tessa-T1-3B-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9cb89f436f6326f9a16529ffd6be113c2facf8c27fd5813c5ded9b0eb0b78c0 +size 1282827552 diff --git a/Tesslate_Tessa-T1-3B-IQ4_NL.gguf b/Tesslate_Tessa-T1-3B-IQ4_NL.gguf new file mode 100644 index 0000000..4e88529 --- /dev/null +++ b/Tesslate_Tessa-T1-3B-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95c9c3aeba3e432efb12c6a797b4427c7bc833b802f9bab41aa85ab7c6b0ffec +size 1825209632 diff --git a/Tesslate_Tessa-T1-3B-IQ4_XS.gguf b/Tesslate_Tessa-T1-3B-IQ4_XS.gguf new file mode 100644 index 0000000..ccfcddd --- /dev/null +++ b/Tesslate_Tessa-T1-3B-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c43d2631289055f36fcc50e3e754dd50def43078c6a955138ff824f83b65eb44 +size 1739095328 diff --git a/Tesslate_Tessa-T1-3B-Q2_K.gguf b/Tesslate_Tessa-T1-3B-Q2_K.gguf new file mode 100644 index 0000000..4fb020e --- /dev/null +++ b/Tesslate_Tessa-T1-3B-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a9349af11734fe7d0d9fbef98acaf4c70079c39602d5306725ae81b8eecb42b +size 1274756384 diff --git a/Tesslate_Tessa-T1-3B-Q2_K_L.gguf b/Tesslate_Tessa-T1-3B-Q2_K_L.gguf new file mode 100644 index 0000000..d3ba208 --- /dev/null +++ b/Tesslate_Tessa-T1-3B-Q2_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0a5ee2c255720cb3b1b2ef339ddc3ebd6365806a394f7f141ed7938110a25fb +size 1350116640 diff --git a/Tesslate_Tessa-T1-3B-Q3_K_L.gguf b/Tesslate_Tessa-T1-3B-Q3_K_L.gguf new file mode 100644 index 0000000..ed33e27 --- /dev/null +++ b/Tesslate_Tessa-T1-3B-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:799ce0391400f36a991e44e8bf7fc78cd633b149af2baf42e05c59a1550c6356 +size 1707392288 diff --git a/Tesslate_Tessa-T1-3B-Q3_K_M.gguf b/Tesslate_Tessa-T1-3B-Q3_K_M.gguf new file mode 100644 index 0000000..c5cf88b --- /dev/null +++ b/Tesslate_Tessa-T1-3B-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd79ebe0a8ddce6ef438e6ebbf9006813b04e4443df5ac3b88666c9e664d485f +size 1590476064 diff --git a/Tesslate_Tessa-T1-3B-Q3_K_S.gguf b/Tesslate_Tessa-T1-3B-Q3_K_S.gguf new file mode 100644 index 0000000..6755972 --- /dev/null +++ b/Tesslate_Tessa-T1-3B-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aba24104e2efe60919c9e06370dad7ac322dd32ccd91bf91313e32f8a0786921 +size 1454357792 diff --git a/Tesslate_Tessa-T1-3B-Q3_K_XL.gguf b/Tesslate_Tessa-T1-3B-Q3_K_XL.gguf new file mode 100644 index 0000000..a7c946f --- /dev/null +++ b/Tesslate_Tessa-T1-3B-Q3_K_XL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f256b08a29d440296ee6fabf53e50729ba4245ad3cde613cd7e78ae4f66fbc6 +size 1782752544 diff --git a/Tesslate_Tessa-T1-3B-Q4_0.gguf b/Tesslate_Tessa-T1-3B-Q4_0.gguf new file mode 100644 index 0000000..a6ebb65 --- /dev/null +++ b/Tesslate_Tessa-T1-3B-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b818bad4d84b8acf3945e417767439a9d71f642a681548a8be87ce305585c700 +size 1828486432 diff --git a/Tesslate_Tessa-T1-3B-Q4_1.gguf b/Tesslate_Tessa-T1-3B-Q4_1.gguf new file mode 100644 index 0000000..7ab7769 --- /dev/null +++ b/Tesslate_Tessa-T1-3B-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ccf7e89b814f63d3c5b81797e5088438a0977f64824a0d4489c3a15f799321a6 +size 1996258592 diff --git a/Tesslate_Tessa-T1-3B-Q4_K_L.gguf b/Tesslate_Tessa-T1-3B-Q4_K_L.gguf new file mode 100644 index 0000000..fc3a8e7 --- /dev/null +++ b/Tesslate_Tessa-T1-3B-Q4_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e3a1d2f8d9fb2f3f0ff683c6ac50ecf4cb3fd6bdd596566779ae3ef90531326 +size 2005263648 diff --git a/Tesslate_Tessa-T1-3B-Q4_K_M.gguf b/Tesslate_Tessa-T1-3B-Q4_K_M.gguf new file mode 100644 index 0000000..53f20c8 --- /dev/null +++ b/Tesslate_Tessa-T1-3B-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6b9d31d78d36094cab2725a7df318f8f3556990df736a21998c952d9a6ee0bf +size 1929903392 diff --git a/Tesslate_Tessa-T1-3B-Q4_K_S.gguf b/Tesslate_Tessa-T1-3B-Q4_K_S.gguf new file mode 100644 index 0000000..8b053ee --- /dev/null +++ b/Tesslate_Tessa-T1-3B-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5eff9e723ebc7f996c2754138d4902ce47ecef1cc557a6cbbc48e2e7ba9771df +size 1834384672 diff --git a/Tesslate_Tessa-T1-3B-Q5_K_L.gguf b/Tesslate_Tessa-T1-3B-Q5_K_L.gguf new file mode 100644 index 0000000..6eabe89 --- /dev/null +++ b/Tesslate_Tessa-T1-3B-Q5_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9237a6022a747381587c50639843a75038ccf921ff7e28c6e3049e5c616bb2e0 +size 2300175648 diff --git a/Tesslate_Tessa-T1-3B-Q5_K_M.gguf b/Tesslate_Tessa-T1-3B-Q5_K_M.gguf new file mode 100644 index 0000000..b8d66e3 --- /dev/null +++ b/Tesslate_Tessa-T1-3B-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:706f0d7bcec8bf931ebf03f2924c988b179b826a75e83f3cfeffeabf0df74bf7 +size 2224815392 diff --git a/Tesslate_Tessa-T1-3B-Q5_K_S.gguf b/Tesslate_Tessa-T1-3B-Q5_K_S.gguf new file mode 100644 index 0000000..3bf02f0 --- /dev/null +++ b/Tesslate_Tessa-T1-3B-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91565cfd18aca612bf9f535f5b09d50ac2510a9e50148f305b75c0cb75a819b1 +size 2169666848 diff --git a/Tesslate_Tessa-T1-3B-Q6_K.gguf b/Tesslate_Tessa-T1-3B-Q6_K.gguf new file mode 100644 index 0000000..799c67f --- /dev/null +++ b/Tesslate_Tessa-T1-3B-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8fbd65f36d04272d8a8dcf2659603a73824e009780fc0ded761801f66245fc47 +size 2538159392 diff --git a/Tesslate_Tessa-T1-3B-Q6_K_L.gguf b/Tesslate_Tessa-T1-3B-Q6_K_L.gguf new file mode 100644 index 0000000..e55b329 --- /dev/null +++ b/Tesslate_Tessa-T1-3B-Q6_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06e1f9f1b03f0344b332104e82f7049acec1309ee8050aa873cbad835d3e9d2b +size 2613519648 diff --git a/Tesslate_Tessa-T1-3B-Q8_0.gguf b/Tesslate_Tessa-T1-3B-Q8_0.gguf new file mode 100644 index 0000000..987505c --- /dev/null +++ b/Tesslate_Tessa-T1-3B-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a912e0f7493d33a6a14b3a627b583d9eb6dc9f4725abddd9fe05f0808127dce +size 3285476640 diff --git a/Tesslate_Tessa-T1-3B-bf16.gguf b/Tesslate_Tessa-T1-3B-bf16.gguf new file mode 100644 index 0000000..a799349 --- /dev/null +++ b/Tesslate_Tessa-T1-3B-bf16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99c228d5c0de195c523d9c718ce2b7f3d84b7d9f9816fa9a950bd64e1ccebeb7 +size 6178317312 diff --git a/Tesslate_Tessa-T1-3B.imatrix b/Tesslate_Tessa-T1-3B.imatrix new file mode 100644 index 0000000..1dfa15b Binary files /dev/null and b/Tesslate_Tessa-T1-3B.imatrix differ 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