commit c997aae938f1bd140c5e3bae82f4ea26bb998719 Author: ModelHub XC Date: Wed Jul 8 01:07:12 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Tess-2.0-Llama-3-8B-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..1266baf --- /dev/null +++ b/.gitattributes @@ -0,0 +1,57 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt 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 +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz 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 +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl 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 +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* 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 +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +imatrix.dat filter=lfs diff=lfs merge=lfs -text +Tess-2.0-Llama-3-8B.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Tess-2.0-Llama-3-8B.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Tess-2.0-Llama-3-8B.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Tess-2.0-Llama-3-8B.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Tess-2.0-Llama-3-8B.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Tess-2.0-Llama-3-8B.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Tess-2.0-Llama-3-8B.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Tess-2.0-Llama-3-8B.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Tess-2.0-Llama-3-8B.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Tess-2.0-Llama-3-8B.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Tess-2.0-Llama-3-8B.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Tess-2.0-Llama-3-8B.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Tess-2.0-Llama-3-8B.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Tess-2.0-Llama-3-8B.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Tess-2.0-Llama-3-8B.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Tess-2.0-Llama-3-8B.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Tess-2.0-Llama-3-8B.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Tess-2.0-Llama-3-8B.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Tess-2.0-Llama-3-8B.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Tess-2.0-Llama-3-8B.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Tess-2.0-Llama-3-8B.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..7c4bf32 --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: migtissera/Tess-2.0-Llama-3-8B +language: +- en +library_name: transformers +license: llama3 +quantized_by: mradermacher +--- +## About + + + + + +weighted/imatrix quants of https://huggingface.co/migtissera/Tess-2.0-Llama-3-8B + + +static quants are available at https://huggingface.co/mradermacher/Tess-2.0-Llama-3-8B-GGUF +## Usage + +If you are unsure how to use GGUF files, refer to one of [TheBloke's +READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for +more details, including on how to concatenate multi-part files. + +## Provided Quants + +(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) + +| Link | Type | Size/GB | Notes | +|:-----|:-----|--------:|:------| +| [GGUF](https://huggingface.co/mradermacher/Tess-2.0-Llama-3-8B-i1-GGUF/resolve/main/Tess-2.0-Llama-3-8B.i1-IQ1_S.gguf) | i1-IQ1_S | 2.1 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Tess-2.0-Llama-3-8B-i1-GGUF/resolve/main/Tess-2.0-Llama-3-8B.i1-IQ1_M.gguf) | i1-IQ1_M | 2.3 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Tess-2.0-Llama-3-8B-i1-GGUF/resolve/main/Tess-2.0-Llama-3-8B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/Tess-2.0-Llama-3-8B-i1-GGUF/resolve/main/Tess-2.0-Llama-3-8B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Tess-2.0-Llama-3-8B-i1-GGUF/resolve/main/Tess-2.0-Llama-3-8B.i1-IQ2_S.gguf) | i1-IQ2_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Tess-2.0-Llama-3-8B-i1-GGUF/resolve/main/Tess-2.0-Llama-3-8B.i1-IQ2_M.gguf) | i1-IQ2_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Tess-2.0-Llama-3-8B-i1-GGUF/resolve/main/Tess-2.0-Llama-3-8B.i1-Q2_K.gguf) | i1-Q2_K | 3.3 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Tess-2.0-Llama-3-8B-i1-GGUF/resolve/main/Tess-2.0-Llama-3-8B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Tess-2.0-Llama-3-8B-i1-GGUF/resolve/main/Tess-2.0-Llama-3-8B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Tess-2.0-Llama-3-8B-i1-GGUF/resolve/main/Tess-2.0-Llama-3-8B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.8 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Tess-2.0-Llama-3-8B-i1-GGUF/resolve/main/Tess-2.0-Llama-3-8B.i1-IQ3_S.gguf) | i1-IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Tess-2.0-Llama-3-8B-i1-GGUF/resolve/main/Tess-2.0-Llama-3-8B.i1-IQ3_M.gguf) | i1-IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Tess-2.0-Llama-3-8B-i1-GGUF/resolve/main/Tess-2.0-Llama-3-8B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.1 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Tess-2.0-Llama-3-8B-i1-GGUF/resolve/main/Tess-2.0-Llama-3-8B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.4 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Tess-2.0-Llama-3-8B-i1-GGUF/resolve/main/Tess-2.0-Llama-3-8B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/Tess-2.0-Llama-3-8B-i1-GGUF/resolve/main/Tess-2.0-Llama-3-8B.i1-Q4_0.gguf) | i1-Q4_0 | 4.8 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Tess-2.0-Llama-3-8B-i1-GGUF/resolve/main/Tess-2.0-Llama-3-8B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.8 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Tess-2.0-Llama-3-8B-i1-GGUF/resolve/main/Tess-2.0-Llama-3-8B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Tess-2.0-Llama-3-8B-i1-GGUF/resolve/main/Tess-2.0-Llama-3-8B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Tess-2.0-Llama-3-8B-i1-GGUF/resolve/main/Tess-2.0-Llama-3-8B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Tess-2.0-Llama-3-8B-i1-GGUF/resolve/main/Tess-2.0-Llama-3-8B.i1-Q6_K.gguf) | i1-Q6_K | 6.7 | practically like static Q6_K | + +Here is a handy graph by ikawrakow comparing some lower-quality quant +types (lower is better): + +![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) + +And here are Artefact2's thoughts on the matter: +https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 + +## FAQ / Model Request + +See https://huggingface.co/mradermacher/model_requests for some answers to +questions you might have and/or if you want some other model quantized. + +## Thanks + +I thank my company, [nethype GmbH](https://www.nethype.de/), for letting +me use its servers and providing upgrades to my workstation to enable +this work in my free time. + + diff --git a/Tess-2.0-Llama-3-8B.i1-IQ1_M.gguf b/Tess-2.0-Llama-3-8B.i1-IQ1_M.gguf new file mode 100644 index 0000000..86d7d0f --- /dev/null +++ b/Tess-2.0-Llama-3-8B.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:810d99bd10c42413d1c1bcfeef8d7b206686024ea376cf7ec3af2532d066c7f2 +size 2161972352 diff --git a/Tess-2.0-Llama-3-8B.i1-IQ1_S.gguf b/Tess-2.0-Llama-3-8B.i1-IQ1_S.gguf new file mode 100644 index 0000000..24ea6ab --- /dev/null +++ b/Tess-2.0-Llama-3-8B.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cdd88d47125c589aab4206d518d130acb70a368b2fe761858bb149cf7ec32db9 +size 2019628160 diff --git a/Tess-2.0-Llama-3-8B.i1-IQ2_M.gguf b/Tess-2.0-Llama-3-8B.i1-IQ2_M.gguf new file mode 100644 index 0000000..84006f0 --- /dev/null +++ b/Tess-2.0-Llama-3-8B.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e9b749f6f0b9dc24e302d550cf31ad8792e6ce5b8fe58d3a0b3688cc46d3551 +size 2948281472 diff --git a/Tess-2.0-Llama-3-8B.i1-IQ2_S.gguf b/Tess-2.0-Llama-3-8B.i1-IQ2_S.gguf new file mode 100644 index 0000000..d6af6d5 --- /dev/null +++ b/Tess-2.0-Llama-3-8B.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c673777a1ecb93e9ca9e6a4df9655af69351e6ec3923e7021b1f92447212345 +size 2758489216 diff --git a/Tess-2.0-Llama-3-8B.i1-IQ2_XS.gguf b/Tess-2.0-Llama-3-8B.i1-IQ2_XS.gguf new file mode 100644 index 0000000..c3865ad --- /dev/null +++ b/Tess-2.0-Llama-3-8B.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55090b4872384ece7058e74b2f76bb455ae38cc51c53120e5b1df99a89a413a2 +size 2605782144 diff --git a/Tess-2.0-Llama-3-8B.i1-IQ2_XXS.gguf b/Tess-2.0-Llama-3-8B.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..024d537 --- /dev/null +++ b/Tess-2.0-Llama-3-8B.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91f688567074559480d8b4489cfcd3da83f9654f773074c58d8983c7496104e7 +size 2399212672 diff --git a/Tess-2.0-Llama-3-8B.i1-IQ3_M.gguf b/Tess-2.0-Llama-3-8B.i1-IQ3_M.gguf new file mode 100644 index 0000000..c66b772 --- /dev/null +++ b/Tess-2.0-Llama-3-8B.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d4465de268cd37790950632c35ebf1f2984147afa2f6dd4e417fa86b7e33256 +size 3784823936 diff --git a/Tess-2.0-Llama-3-8B.i1-IQ3_S.gguf b/Tess-2.0-Llama-3-8B.i1-IQ3_S.gguf new file mode 100644 index 0000000..2a95974 --- /dev/null +++ b/Tess-2.0-Llama-3-8B.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d969c614de22c8fdec4bf6ba3c972ae5e6ed5fdd3cb63852a28297fe09538d94 +size 3682325632 diff --git a/Tess-2.0-Llama-3-8B.i1-IQ3_XS.gguf b/Tess-2.0-Llama-3-8B.i1-IQ3_XS.gguf new file mode 100644 index 0000000..f4cf52d --- /dev/null +++ b/Tess-2.0-Llama-3-8B.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f93c18017dcb2de57b9da73587192de478078d3f8f1765a286b3a2a6923faf5e +size 3518747776 diff --git a/Tess-2.0-Llama-3-8B.i1-IQ3_XXS.gguf b/Tess-2.0-Llama-3-8B.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..45fa908 --- /dev/null +++ b/Tess-2.0-Llama-3-8B.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:159945babd376072659eb2ee2d65cace6530ee43f2c33c8679e3a699ac35f384 +size 3274912896 diff --git a/Tess-2.0-Llama-3-8B.i1-IQ4_XS.gguf b/Tess-2.0-Llama-3-8B.i1-IQ4_XS.gguf new file mode 100644 index 0000000..1714f0e --- /dev/null +++ b/Tess-2.0-Llama-3-8B.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55e2ab7f36b5e72f3ddbee2f67b2fdc8eb971609b668754c85edfb807a471d63 +size 4447663232 diff --git a/Tess-2.0-Llama-3-8B.i1-Q2_K.gguf b/Tess-2.0-Llama-3-8B.i1-Q2_K.gguf new file mode 100644 index 0000000..bce1d33 --- /dev/null +++ b/Tess-2.0-Llama-3-8B.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d2953e488459282b831b9fc1e3b4353790b2c9d24e63a106fc3c0611d036caf +size 3179132032 diff --git a/Tess-2.0-Llama-3-8B.i1-Q3_K_L.gguf b/Tess-2.0-Llama-3-8B.i1-Q3_K_L.gguf new file mode 100644 index 0000000..6bd3464 --- /dev/null +++ b/Tess-2.0-Llama-3-8B.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c53a3778ddb6213db4a53efbd18b438329b889815b3c0af5eb95854c7b92d07e +size 4321956992 diff --git a/Tess-2.0-Llama-3-8B.i1-Q3_K_M.gguf b/Tess-2.0-Llama-3-8B.i1-Q3_K_M.gguf new file mode 100644 index 0000000..98b51cb --- /dev/null +++ b/Tess-2.0-Llama-3-8B.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a07817e356cb7fc067e7d5b8cc3fa682e81176eec969ec7fc847ee3045acbef9 +size 4018918528 diff --git a/Tess-2.0-Llama-3-8B.i1-Q3_K_S.gguf b/Tess-2.0-Llama-3-8B.i1-Q3_K_S.gguf new file mode 100644 index 0000000..0490320 --- /dev/null +++ b/Tess-2.0-Llama-3-8B.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:732a4a7f84b9146af3a2fa1c1ad87170d7d51c93c51beaca4a9a055ec96c6679 +size 3664499840 diff --git a/Tess-2.0-Llama-3-8B.i1-Q4_0.gguf b/Tess-2.0-Llama-3-8B.i1-Q4_0.gguf new file mode 100644 index 0000000..db9a4d1 --- /dev/null +++ b/Tess-2.0-Llama-3-8B.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8846a40cc58cf45a62a2fdea827aa2297c7edd407c9931410ceb7a3782bd868 +size 4675892352 diff --git a/Tess-2.0-Llama-3-8B.i1-Q4_K_M.gguf b/Tess-2.0-Llama-3-8B.i1-Q4_K_M.gguf new file mode 100644 index 0000000..3c679e6 --- /dev/null +++ b/Tess-2.0-Llama-3-8B.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b71422313cc57501d6a8d07ceeb8fed50731b0d1398e9466b4e87b981dcd97a9 +size 4920734848 diff --git a/Tess-2.0-Llama-3-8B.i1-Q4_K_S.gguf b/Tess-2.0-Llama-3-8B.i1-Q4_K_S.gguf new file mode 100644 index 0000000..4007e55 --- /dev/null +++ b/Tess-2.0-Llama-3-8B.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0e415e0e672b25e58d4c3511a764c12e727a9796d12b9134a127faef7697935 +size 4692669568 diff --git a/Tess-2.0-Llama-3-8B.i1-Q5_K_M.gguf b/Tess-2.0-Llama-3-8B.i1-Q5_K_M.gguf new file mode 100644 index 0000000..f0b2428 --- /dev/null +++ b/Tess-2.0-Llama-3-8B.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fbebc80873d5973d3940b0252724e4635ad62860152c833da23c1849db618799 +size 5732988032 diff --git a/Tess-2.0-Llama-3-8B.i1-Q5_K_S.gguf b/Tess-2.0-Llama-3-8B.i1-Q5_K_S.gguf new file mode 100644 index 0000000..3fe4a0f --- /dev/null +++ b/Tess-2.0-Llama-3-8B.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d2b680173343a7cc5dc410364ce84fa2ca30ccea34242513c2bd30715a10d66a +size 5599294592 diff --git a/Tess-2.0-Llama-3-8B.i1-Q6_K.gguf b/Tess-2.0-Llama-3-8B.i1-Q6_K.gguf new file mode 100644 index 0000000..4c80968 --- /dev/null +++ b/Tess-2.0-Llama-3-8B.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b111768cf469c4ede668efdfc9dd4d97c7681aea3713c40135f5b48b312463a4 +size 6596007040 diff --git a/imatrix.dat b/imatrix.dat new file mode 100644 index 0000000..1afd504 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d9427159c07dc84c39ac21d26dcff9fd352b7feab977fad467ec883ba09caea +size 4988159