commit 4ff8242b1e1525ac8b1b5ae163f5cd666ab88b90 Author: ModelHub XC Date: Sat May 9 21:47:19 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Pantheon-RP-1.0-8b-Llama-3-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..b587f83 --- /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 +Pantheon-RP-1.0-8b-Llama-3.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Pantheon-RP-1.0-8b-Llama-3.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Pantheon-RP-1.0-8b-Llama-3.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Pantheon-RP-1.0-8b-Llama-3.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Pantheon-RP-1.0-8b-Llama-3.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Pantheon-RP-1.0-8b-Llama-3.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Pantheon-RP-1.0-8b-Llama-3.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Pantheon-RP-1.0-8b-Llama-3.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Pantheon-RP-1.0-8b-Llama-3.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Pantheon-RP-1.0-8b-Llama-3.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Pantheon-RP-1.0-8b-Llama-3.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Pantheon-RP-1.0-8b-Llama-3.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Pantheon-RP-1.0-8b-Llama-3.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Pantheon-RP-1.0-8b-Llama-3.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Pantheon-RP-1.0-8b-Llama-3.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Pantheon-RP-1.0-8b-Llama-3.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Pantheon-RP-1.0-8b-Llama-3.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Pantheon-RP-1.0-8b-Llama-3.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Pantheon-RP-1.0-8b-Llama-3.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Pantheon-RP-1.0-8b-Llama-3.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Pantheon-RP-1.0-8b-Llama-3.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Pantheon-RP-1.0-8b-Llama-3.i1-IQ1_M.gguf b/Pantheon-RP-1.0-8b-Llama-3.i1-IQ1_M.gguf new file mode 100644 index 0000000..b8ac6f1 --- /dev/null +++ b/Pantheon-RP-1.0-8b-Llama-3.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae6ef73174e514dcff3d6638fac499e75e93fe43f43f5b2745614189bc62603e +size 2161972096 diff --git a/Pantheon-RP-1.0-8b-Llama-3.i1-IQ1_S.gguf b/Pantheon-RP-1.0-8b-Llama-3.i1-IQ1_S.gguf new file mode 100644 index 0000000..77541f0 --- /dev/null +++ b/Pantheon-RP-1.0-8b-Llama-3.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93a4006837d8868151cd9211e53a7b0cae51862ac21489f3881ee53fca9b92e7 +size 2019627904 diff --git a/Pantheon-RP-1.0-8b-Llama-3.i1-IQ2_M.gguf b/Pantheon-RP-1.0-8b-Llama-3.i1-IQ2_M.gguf new file mode 100644 index 0000000..113531b --- /dev/null +++ b/Pantheon-RP-1.0-8b-Llama-3.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c64c327c2ca43463f12680824f1ac6067caf9a1742e28ecc0338c3d8b789aac +size 2948281216 diff --git a/Pantheon-RP-1.0-8b-Llama-3.i1-IQ2_S.gguf b/Pantheon-RP-1.0-8b-Llama-3.i1-IQ2_S.gguf new file mode 100644 index 0000000..3108dea --- /dev/null +++ b/Pantheon-RP-1.0-8b-Llama-3.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:131c29bf67384c8abc989afd7923a97bbf30f733b72eaf7c8092536612464bd8 +size 2758488960 diff --git a/Pantheon-RP-1.0-8b-Llama-3.i1-IQ2_XS.gguf b/Pantheon-RP-1.0-8b-Llama-3.i1-IQ2_XS.gguf new file mode 100644 index 0000000..c345988 --- /dev/null +++ b/Pantheon-RP-1.0-8b-Llama-3.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b55e219092d557efe03d0608d3f5eec424331d4da1c150ed065d0583cd3bfeb0 +size 2605781888 diff --git a/Pantheon-RP-1.0-8b-Llama-3.i1-IQ2_XXS.gguf b/Pantheon-RP-1.0-8b-Llama-3.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..cbfaf61 --- /dev/null +++ b/Pantheon-RP-1.0-8b-Llama-3.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b7e419c0cb415f748614350b044ec51d110b8c0cba08242ccd8265b7d6d654f +size 2399212416 diff --git a/Pantheon-RP-1.0-8b-Llama-3.i1-IQ3_M.gguf b/Pantheon-RP-1.0-8b-Llama-3.i1-IQ3_M.gguf new file mode 100644 index 0000000..7ac3b3f --- /dev/null +++ b/Pantheon-RP-1.0-8b-Llama-3.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89164f1e227ac4c0321a955c725c1bc2eae2234c821a250467abbddd5618471d +size 3784823680 diff --git a/Pantheon-RP-1.0-8b-Llama-3.i1-IQ3_S.gguf b/Pantheon-RP-1.0-8b-Llama-3.i1-IQ3_S.gguf new file mode 100644 index 0000000..5cea130 --- /dev/null +++ b/Pantheon-RP-1.0-8b-Llama-3.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83fca4f267a9ae994e0db280a8f31c091c2b25d5c3077b66b94d8fac042d2750 +size 3682325376 diff --git a/Pantheon-RP-1.0-8b-Llama-3.i1-IQ3_XS.gguf b/Pantheon-RP-1.0-8b-Llama-3.i1-IQ3_XS.gguf new file mode 100644 index 0000000..d873aaf --- /dev/null +++ b/Pantheon-RP-1.0-8b-Llama-3.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b574993bf90d38da7374a6e8a942fce03805b9effc676044a7619b35f4a00a00 +size 3518747520 diff --git a/Pantheon-RP-1.0-8b-Llama-3.i1-IQ3_XXS.gguf b/Pantheon-RP-1.0-8b-Llama-3.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..863c25c --- /dev/null +++ b/Pantheon-RP-1.0-8b-Llama-3.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b10beac4ea63b30f15bc6966c63d6a5f0bd88c8ae73108eeda65f0a34f17851f +size 3274912640 diff --git a/Pantheon-RP-1.0-8b-Llama-3.i1-IQ4_XS.gguf b/Pantheon-RP-1.0-8b-Llama-3.i1-IQ4_XS.gguf new file mode 100644 index 0000000..bb21c2b --- /dev/null +++ b/Pantheon-RP-1.0-8b-Llama-3.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c767ff229f7e33386455bd48bdf051d4e1aefe77e35fa233bcdb50759933b74 +size 4447662976 diff --git a/Pantheon-RP-1.0-8b-Llama-3.i1-Q2_K.gguf b/Pantheon-RP-1.0-8b-Llama-3.i1-Q2_K.gguf new file mode 100644 index 0000000..050e2ec --- /dev/null +++ b/Pantheon-RP-1.0-8b-Llama-3.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c29566feb548e9f4675d90d69285fbb66f95b066a905a071b6c1fd94b80fcf1e +size 3179131776 diff --git a/Pantheon-RP-1.0-8b-Llama-3.i1-Q3_K_L.gguf b/Pantheon-RP-1.0-8b-Llama-3.i1-Q3_K_L.gguf new file mode 100644 index 0000000..26cdeac --- /dev/null +++ b/Pantheon-RP-1.0-8b-Llama-3.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52282d51fd5bfa812f800d12517a70bc32b26e9e6829426849bc3d4adea5a4a9 +size 4321956736 diff --git a/Pantheon-RP-1.0-8b-Llama-3.i1-Q3_K_M.gguf b/Pantheon-RP-1.0-8b-Llama-3.i1-Q3_K_M.gguf new file mode 100644 index 0000000..e659da4 --- /dev/null +++ b/Pantheon-RP-1.0-8b-Llama-3.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45d3ef128b2640f942e2e652db6bdf18a94e45caa8ec2e51547aab306c9ef09e +size 4018918272 diff --git a/Pantheon-RP-1.0-8b-Llama-3.i1-Q3_K_S.gguf b/Pantheon-RP-1.0-8b-Llama-3.i1-Q3_K_S.gguf new file mode 100644 index 0000000..6d5455a --- /dev/null +++ b/Pantheon-RP-1.0-8b-Llama-3.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5754b1d26cba0db35d0af8b5afa064757b8e301c23f47b54eb49d2653c26df6 +size 3664499584 diff --git a/Pantheon-RP-1.0-8b-Llama-3.i1-Q4_0.gguf b/Pantheon-RP-1.0-8b-Llama-3.i1-Q4_0.gguf new file mode 100644 index 0000000..a144744 --- /dev/null +++ b/Pantheon-RP-1.0-8b-Llama-3.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a300de7a40bad8ae356f3acd632af06a780d36931894924e1523f42ae7dbb782 +size 4675892096 diff --git a/Pantheon-RP-1.0-8b-Llama-3.i1-Q4_K_M.gguf b/Pantheon-RP-1.0-8b-Llama-3.i1-Q4_K_M.gguf new file mode 100644 index 0000000..679a951 --- /dev/null +++ b/Pantheon-RP-1.0-8b-Llama-3.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7bc350fa834481b109e6c81c038aa6fc31ee93f95fb8835dd218bb16f713fb4 +size 4920734592 diff --git a/Pantheon-RP-1.0-8b-Llama-3.i1-Q4_K_S.gguf b/Pantheon-RP-1.0-8b-Llama-3.i1-Q4_K_S.gguf new file mode 100644 index 0000000..f0addc2 --- /dev/null +++ b/Pantheon-RP-1.0-8b-Llama-3.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4f8acc73de0344bb52cc6e52a1f29aa98f0a243787254eaacf4e5b340a071cf +size 4692669312 diff --git a/Pantheon-RP-1.0-8b-Llama-3.i1-Q5_K_M.gguf b/Pantheon-RP-1.0-8b-Llama-3.i1-Q5_K_M.gguf new file mode 100644 index 0000000..1d03756 --- /dev/null +++ b/Pantheon-RP-1.0-8b-Llama-3.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf52082afa5c2f489feb4570fc15562ebdcb5066ff874ec7449d020c33def4e0 +size 5732987776 diff --git a/Pantheon-RP-1.0-8b-Llama-3.i1-Q5_K_S.gguf b/Pantheon-RP-1.0-8b-Llama-3.i1-Q5_K_S.gguf new file mode 100644 index 0000000..1356162 --- /dev/null +++ b/Pantheon-RP-1.0-8b-Llama-3.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad022a7cbb485c33fc9e4afb2b79cf501e4c68343f693fd96aae327fa33f6177 +size 5599294336 diff --git a/Pantheon-RP-1.0-8b-Llama-3.i1-Q6_K.gguf b/Pantheon-RP-1.0-8b-Llama-3.i1-Q6_K.gguf new file mode 100644 index 0000000..efaa978 --- /dev/null +++ b/Pantheon-RP-1.0-8b-Llama-3.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5eb3508149d92fc8686f84270d71ebef6f896a769ff633f82ca04e1d3bf54dbf +size 6596006784 diff --git a/README.md b/README.md new file mode 100644 index 0000000..f2e3c3f --- /dev/null +++ b/README.md @@ -0,0 +1,80 @@ +--- +base_model: Gryphe/Pantheon-RP-1.0-8b-Llama-3 +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- Llama-3 +- instruct +- finetune +- chatml +- axolotl +- roleplay +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/Gryphe/Pantheon-RP-1.0-8b-Llama-3 + + +static quants are available at https://huggingface.co/mradermacher/Pantheon-RP-1.0-8b-Llama-3-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/Pantheon-RP-1.0-8b-Llama-3-i1-GGUF/resolve/main/Pantheon-RP-1.0-8b-Llama-3.i1-IQ1_S.gguf) | i1-IQ1_S | 2.1 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Pantheon-RP-1.0-8b-Llama-3-i1-GGUF/resolve/main/Pantheon-RP-1.0-8b-Llama-3.i1-IQ1_M.gguf) | i1-IQ1_M | 2.3 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Pantheon-RP-1.0-8b-Llama-3-i1-GGUF/resolve/main/Pantheon-RP-1.0-8b-Llama-3.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/Pantheon-RP-1.0-8b-Llama-3-i1-GGUF/resolve/main/Pantheon-RP-1.0-8b-Llama-3.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Pantheon-RP-1.0-8b-Llama-3-i1-GGUF/resolve/main/Pantheon-RP-1.0-8b-Llama-3.i1-IQ2_S.gguf) | i1-IQ2_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Pantheon-RP-1.0-8b-Llama-3-i1-GGUF/resolve/main/Pantheon-RP-1.0-8b-Llama-3.i1-IQ2_M.gguf) | i1-IQ2_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Pantheon-RP-1.0-8b-Llama-3-i1-GGUF/resolve/main/Pantheon-RP-1.0-8b-Llama-3.i1-Q2_K.gguf) | i1-Q2_K | 3.3 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Pantheon-RP-1.0-8b-Llama-3-i1-GGUF/resolve/main/Pantheon-RP-1.0-8b-Llama-3.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Pantheon-RP-1.0-8b-Llama-3-i1-GGUF/resolve/main/Pantheon-RP-1.0-8b-Llama-3.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Pantheon-RP-1.0-8b-Llama-3-i1-GGUF/resolve/main/Pantheon-RP-1.0-8b-Llama-3.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.8 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Pantheon-RP-1.0-8b-Llama-3-i1-GGUF/resolve/main/Pantheon-RP-1.0-8b-Llama-3.i1-IQ3_S.gguf) | i1-IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Pantheon-RP-1.0-8b-Llama-3-i1-GGUF/resolve/main/Pantheon-RP-1.0-8b-Llama-3.i1-IQ3_M.gguf) | i1-IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Pantheon-RP-1.0-8b-Llama-3-i1-GGUF/resolve/main/Pantheon-RP-1.0-8b-Llama-3.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.1 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Pantheon-RP-1.0-8b-Llama-3-i1-GGUF/resolve/main/Pantheon-RP-1.0-8b-Llama-3.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.4 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Pantheon-RP-1.0-8b-Llama-3-i1-GGUF/resolve/main/Pantheon-RP-1.0-8b-Llama-3.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/Pantheon-RP-1.0-8b-Llama-3-i1-GGUF/resolve/main/Pantheon-RP-1.0-8b-Llama-3.i1-Q4_0.gguf) | i1-Q4_0 | 4.8 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Pantheon-RP-1.0-8b-Llama-3-i1-GGUF/resolve/main/Pantheon-RP-1.0-8b-Llama-3.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.8 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Pantheon-RP-1.0-8b-Llama-3-i1-GGUF/resolve/main/Pantheon-RP-1.0-8b-Llama-3.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Pantheon-RP-1.0-8b-Llama-3-i1-GGUF/resolve/main/Pantheon-RP-1.0-8b-Llama-3.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Pantheon-RP-1.0-8b-Llama-3-i1-GGUF/resolve/main/Pantheon-RP-1.0-8b-Llama-3.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Pantheon-RP-1.0-8b-Llama-3-i1-GGUF/resolve/main/Pantheon-RP-1.0-8b-Llama-3.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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. + + diff --git a/imatrix.dat b/imatrix.dat new file mode 100644 index 0000000..48bf08e --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2d16dc5b27bbb0c07a027c1a706aa0d6a4aa70b24ca0482368f1d68d64ee69e +size 4988143