commit 8c64f19d14e3488a632751f8d35900c205a93f61 Author: ModelHub XC Date: Sun May 24 09:02:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/NeuralLLaMa-3-8b-ORPO-v0.3-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a7941fd --- /dev/null +++ b/.gitattributes @@ -0,0 +1,60 @@ +*.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 +NeuralLLaMa-3-8b-ORPO-v0.3.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +NeuralLLaMa-3-8b-ORPO-v0.3.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +NeuralLLaMa-3-8b-ORPO-v0.3.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +NeuralLLaMa-3-8b-ORPO-v0.3.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +NeuralLLaMa-3-8b-ORPO-v0.3.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +NeuralLLaMa-3-8b-ORPO-v0.3.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +NeuralLLaMa-3-8b-ORPO-v0.3.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +NeuralLLaMa-3-8b-ORPO-v0.3.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +NeuralLLaMa-3-8b-ORPO-v0.3.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +NeuralLLaMa-3-8b-ORPO-v0.3.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +NeuralLLaMa-3-8b-ORPO-v0.3.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +NeuralLLaMa-3-8b-ORPO-v0.3.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +NeuralLLaMa-3-8b-ORPO-v0.3.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +NeuralLLaMa-3-8b-ORPO-v0.3.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +NeuralLLaMa-3-8b-ORPO-v0.3.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +NeuralLLaMa-3-8b-ORPO-v0.3.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +NeuralLLaMa-3-8b-ORPO-v0.3.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +NeuralLLaMa-3-8b-ORPO-v0.3.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +NeuralLLaMa-3-8b-ORPO-v0.3.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +NeuralLLaMa-3-8b-ORPO-v0.3.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +NeuralLLaMa-3-8b-ORPO-v0.3.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +NeuralLLaMa-3-8b-ORPO-v0.3.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +NeuralLLaMa-3-8b-ORPO-v0.3.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +NeuralLLaMa-3-8b-ORPO-v0.3.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/NeuralLLaMa-3-8b-ORPO-v0.3.i1-IQ1_M.gguf b/NeuralLLaMa-3-8b-ORPO-v0.3.i1-IQ1_M.gguf new file mode 100644 index 0000000..7e751f9 --- /dev/null +++ b/NeuralLLaMa-3-8b-ORPO-v0.3.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:006f2c023b999ef25d0e8150b347785af455aef513bf9dd331a6ab1649460b83 +size 2161981248 diff --git a/NeuralLLaMa-3-8b-ORPO-v0.3.i1-IQ1_S.gguf b/NeuralLLaMa-3-8b-ORPO-v0.3.i1-IQ1_S.gguf new file mode 100644 index 0000000..104b0ff --- /dev/null +++ b/NeuralLLaMa-3-8b-ORPO-v0.3.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb487caea17467e89884912ba185b96acbf4167a22c7edb7c88e90b42e2df8e6 +size 2019637056 diff --git a/NeuralLLaMa-3-8b-ORPO-v0.3.i1-IQ2_M.gguf b/NeuralLLaMa-3-8b-ORPO-v0.3.i1-IQ2_M.gguf new file mode 100644 index 0000000..53b03e7 --- /dev/null +++ b/NeuralLLaMa-3-8b-ORPO-v0.3.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c473b66d8552c1b40cd17da32aed0455789b0c727abae869e2157bbf0bd34602 +size 2948291200 diff --git a/NeuralLLaMa-3-8b-ORPO-v0.3.i1-IQ2_S.gguf b/NeuralLLaMa-3-8b-ORPO-v0.3.i1-IQ2_S.gguf new file mode 100644 index 0000000..e9cfbfe --- /dev/null +++ b/NeuralLLaMa-3-8b-ORPO-v0.3.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6d9f10c871f2828f0d854a02fbf0d698d24c88591e0c5a5a6a0b3f354f54b6a +size 2758498944 diff --git a/NeuralLLaMa-3-8b-ORPO-v0.3.i1-IQ2_XS.gguf b/NeuralLLaMa-3-8b-ORPO-v0.3.i1-IQ2_XS.gguf new file mode 100644 index 0000000..f92c590 --- /dev/null +++ b/NeuralLLaMa-3-8b-ORPO-v0.3.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3bf99fe62b71cfdf95d9d391acae96bb8c12c67dc163854b22ef3b4ed83deab +size 2605791040 diff --git a/NeuralLLaMa-3-8b-ORPO-v0.3.i1-IQ2_XXS.gguf b/NeuralLLaMa-3-8b-ORPO-v0.3.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..0ef9314 --- /dev/null +++ b/NeuralLLaMa-3-8b-ORPO-v0.3.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f3aaa427d1d7e80afce78ab00445e07d528ece33643c70bcc6423a50c11eaa9 +size 2399221568 diff --git a/NeuralLLaMa-3-8b-ORPO-v0.3.i1-IQ3_M.gguf b/NeuralLLaMa-3-8b-ORPO-v0.3.i1-IQ3_M.gguf new file mode 100644 index 0000000..a0ffbc5 --- /dev/null +++ b/NeuralLLaMa-3-8b-ORPO-v0.3.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e5753323cb30800ae36b1e68c786314746847a6d592b3a95e279508a9350efc +size 3784834752 diff --git a/NeuralLLaMa-3-8b-ORPO-v0.3.i1-IQ3_S.gguf b/NeuralLLaMa-3-8b-ORPO-v0.3.i1-IQ3_S.gguf new file mode 100644 index 0000000..ab5a62a --- /dev/null +++ b/NeuralLLaMa-3-8b-ORPO-v0.3.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d50922536900e3e64710d3cb94533749d251b2b800b88dd51a5bc90128089692 +size 3682336448 diff --git a/NeuralLLaMa-3-8b-ORPO-v0.3.i1-IQ3_XS.gguf b/NeuralLLaMa-3-8b-ORPO-v0.3.i1-IQ3_XS.gguf new file mode 100644 index 0000000..df2fbd1 --- /dev/null +++ b/NeuralLLaMa-3-8b-ORPO-v0.3.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f8c6db7a7efa0129721a182742a5a7a058e91b092f7501b44baa2c49003d88a +size 3518758592 diff --git a/NeuralLLaMa-3-8b-ORPO-v0.3.i1-IQ3_XXS.gguf b/NeuralLLaMa-3-8b-ORPO-v0.3.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..4333393 --- /dev/null +++ b/NeuralLLaMa-3-8b-ORPO-v0.3.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72c5e1084123a0e553f26670c6d8b7107578807eee5134b7aebc1c2e0d038374 +size 3274922624 diff --git a/NeuralLLaMa-3-8b-ORPO-v0.3.i1-IQ4_NL.gguf b/NeuralLLaMa-3-8b-ORPO-v0.3.i1-IQ4_NL.gguf new file mode 100644 index 0000000..f2350e1 --- /dev/null +++ b/NeuralLLaMa-3-8b-ORPO-v0.3.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d1cbce5e05fd3b254f2ca695de52c527194aed63598b5c324114fc895865e9c +size 4678001408 diff --git a/NeuralLLaMa-3-8b-ORPO-v0.3.i1-IQ4_XS.gguf b/NeuralLLaMa-3-8b-ORPO-v0.3.i1-IQ4_XS.gguf new file mode 100644 index 0000000..dc70f69 --- /dev/null +++ b/NeuralLLaMa-3-8b-ORPO-v0.3.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff30bca67cc644f735387582b909576bf99c506e3e85d05b3ee9e9adc1e3b0a5 +size 4447674880 diff --git a/NeuralLLaMa-3-8b-ORPO-v0.3.i1-Q2_K.gguf b/NeuralLLaMa-3-8b-ORPO-v0.3.i1-Q2_K.gguf new file mode 100644 index 0000000..110cfd3 --- /dev/null +++ b/NeuralLLaMa-3-8b-ORPO-v0.3.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:573ef29ac4946c60b29369337a1c3c05f664f9c981a294fd9b82634961162412 +size 3179142016 diff --git a/NeuralLLaMa-3-8b-ORPO-v0.3.i1-Q2_K_S.gguf b/NeuralLLaMa-3-8b-ORPO-v0.3.i1-Q2_K_S.gguf new file mode 100644 index 0000000..06895c9 --- /dev/null +++ b/NeuralLLaMa-3-8b-ORPO-v0.3.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a427d1fddf30387909c005803943d2a5fc13c117a1e33123d9d9cc35d2eb5c0e +size 2988825472 diff --git a/NeuralLLaMa-3-8b-ORPO-v0.3.i1-Q3_K_L.gguf b/NeuralLLaMa-3-8b-ORPO-v0.3.i1-Q3_K_L.gguf new file mode 100644 index 0000000..187a20a --- /dev/null +++ b/NeuralLLaMa-3-8b-ORPO-v0.3.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a5fa3aad1b7b955f797e9ab5a4271bd1d63df26448cc649b198158017022bd4 +size 4321967808 diff --git a/NeuralLLaMa-3-8b-ORPO-v0.3.i1-Q3_K_M.gguf b/NeuralLLaMa-3-8b-ORPO-v0.3.i1-Q3_K_M.gguf new file mode 100644 index 0000000..267f0e3 --- /dev/null +++ b/NeuralLLaMa-3-8b-ORPO-v0.3.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c95e085517ba030af593fddab610e0973ac9fffb87ff18e93af7d65cf1d257d +size 4018929344 diff --git a/NeuralLLaMa-3-8b-ORPO-v0.3.i1-Q3_K_S.gguf b/NeuralLLaMa-3-8b-ORPO-v0.3.i1-Q3_K_S.gguf new file mode 100644 index 0000000..ce73521 --- /dev/null +++ b/NeuralLLaMa-3-8b-ORPO-v0.3.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6881dc6200cf98aaa4adbf25b0e111e70115fec42c73872956f21c72d00f5af2 +size 3664510656 diff --git a/NeuralLLaMa-3-8b-ORPO-v0.3.i1-Q4_0.gguf b/NeuralLLaMa-3-8b-ORPO-v0.3.i1-Q4_0.gguf new file mode 100644 index 0000000..83bfed5 --- /dev/null +++ b/NeuralLLaMa-3-8b-ORPO-v0.3.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c346984dffddeaf2b54a9cd19540028807595d1f23a10b23ef6209c75c8cc0df +size 4675904256 diff --git a/NeuralLLaMa-3-8b-ORPO-v0.3.i1-Q4_1.gguf b/NeuralLLaMa-3-8b-ORPO-v0.3.i1-Q4_1.gguf new file mode 100644 index 0000000..48037d0 --- /dev/null +++ b/NeuralLLaMa-3-8b-ORPO-v0.3.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:640dd6638cf6343a23f776198d28d78410f7a6a6a5806ac4ca86086ddc7505d8 +size 5130265856 diff --git a/NeuralLLaMa-3-8b-ORPO-v0.3.i1-Q4_K_M.gguf b/NeuralLLaMa-3-8b-ORPO-v0.3.i1-Q4_K_M.gguf new file mode 100644 index 0000000..cc0f33f --- /dev/null +++ b/NeuralLLaMa-3-8b-ORPO-v0.3.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3a77b758a8ca6cfa077c2f5eb31bfba9b309c16ed1aec5a077b71237e0c2d64 +size 4920746752 diff --git a/NeuralLLaMa-3-8b-ORPO-v0.3.i1-Q4_K_S.gguf b/NeuralLLaMa-3-8b-ORPO-v0.3.i1-Q4_K_S.gguf new file mode 100644 index 0000000..69754b3 --- /dev/null +++ b/NeuralLLaMa-3-8b-ORPO-v0.3.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:753b376516c345ded3fafd9d82ce4442d266355de7fc6085f2e966bef35ad2b4 +size 4692681472 diff --git a/NeuralLLaMa-3-8b-ORPO-v0.3.i1-Q5_K_M.gguf b/NeuralLLaMa-3-8b-ORPO-v0.3.i1-Q5_K_M.gguf new file mode 100644 index 0000000..4e3c998 --- /dev/null +++ b/NeuralLLaMa-3-8b-ORPO-v0.3.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd9bef57686b30f5cda169fe837af926628e5ed8f7b73e12f1cd5287b5faef0b +size 5733000960 diff --git a/NeuralLLaMa-3-8b-ORPO-v0.3.i1-Q5_K_S.gguf b/NeuralLLaMa-3-8b-ORPO-v0.3.i1-Q5_K_S.gguf new file mode 100644 index 0000000..f6bf0d9 --- /dev/null +++ b/NeuralLLaMa-3-8b-ORPO-v0.3.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74b5d062cd134f43cc425c5866c51e0891562e045a08fa0510567ca7411e7a64 +size 5599307520 diff --git a/NeuralLLaMa-3-8b-ORPO-v0.3.i1-Q6_K.gguf b/NeuralLLaMa-3-8b-ORPO-v0.3.i1-Q6_K.gguf new file mode 100644 index 0000000..a8fa089 --- /dev/null +++ b/NeuralLLaMa-3-8b-ORPO-v0.3.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce38be4e531fd5fe2be4e8028ba8a10ab57b2f9cb13a91577822046ed9e80b0b +size 6596021056 diff --git a/README.md b/README.md new file mode 100644 index 0000000..3bf5104 --- /dev/null +++ b/README.md @@ -0,0 +1,78 @@ +--- +base_model: Kukedlc/NeuralLLaMa-3-8b-ORPO-v0.3 +datasets: +- mlabonne/orpo-dpo-mix-40k +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/Kukedlc/NeuralLLaMa-3-8b-ORPO-v0.3 + + +static quants are available at https://huggingface.co/mradermacher/NeuralLLaMa-3-8b-ORPO-v0.3-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/NeuralLLaMa-3-8b-ORPO-v0.3-i1-GGUF/resolve/main/NeuralLLaMa-3-8b-ORPO-v0.3.i1-IQ1_S.gguf) | i1-IQ1_S | 2.1 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/NeuralLLaMa-3-8b-ORPO-v0.3-i1-GGUF/resolve/main/NeuralLLaMa-3-8b-ORPO-v0.3.i1-IQ1_M.gguf) | i1-IQ1_M | 2.3 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/NeuralLLaMa-3-8b-ORPO-v0.3-i1-GGUF/resolve/main/NeuralLLaMa-3-8b-ORPO-v0.3.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/NeuralLLaMa-3-8b-ORPO-v0.3-i1-GGUF/resolve/main/NeuralLLaMa-3-8b-ORPO-v0.3.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/NeuralLLaMa-3-8b-ORPO-v0.3-i1-GGUF/resolve/main/NeuralLLaMa-3-8b-ORPO-v0.3.i1-IQ2_S.gguf) | i1-IQ2_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/NeuralLLaMa-3-8b-ORPO-v0.3-i1-GGUF/resolve/main/NeuralLLaMa-3-8b-ORPO-v0.3.i1-IQ2_M.gguf) | i1-IQ2_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/NeuralLLaMa-3-8b-ORPO-v0.3-i1-GGUF/resolve/main/NeuralLLaMa-3-8b-ORPO-v0.3.i1-Q2_K_S.gguf) | i1-Q2_K_S | 3.1 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/NeuralLLaMa-3-8b-ORPO-v0.3-i1-GGUF/resolve/main/NeuralLLaMa-3-8b-ORPO-v0.3.i1-Q2_K.gguf) | i1-Q2_K | 3.3 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/NeuralLLaMa-3-8b-ORPO-v0.3-i1-GGUF/resolve/main/NeuralLLaMa-3-8b-ORPO-v0.3.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/NeuralLLaMa-3-8b-ORPO-v0.3-i1-GGUF/resolve/main/NeuralLLaMa-3-8b-ORPO-v0.3.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/NeuralLLaMa-3-8b-ORPO-v0.3-i1-GGUF/resolve/main/NeuralLLaMa-3-8b-ORPO-v0.3.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.8 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/NeuralLLaMa-3-8b-ORPO-v0.3-i1-GGUF/resolve/main/NeuralLLaMa-3-8b-ORPO-v0.3.i1-IQ3_S.gguf) | i1-IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/NeuralLLaMa-3-8b-ORPO-v0.3-i1-GGUF/resolve/main/NeuralLLaMa-3-8b-ORPO-v0.3.i1-IQ3_M.gguf) | i1-IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/NeuralLLaMa-3-8b-ORPO-v0.3-i1-GGUF/resolve/main/NeuralLLaMa-3-8b-ORPO-v0.3.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.1 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/NeuralLLaMa-3-8b-ORPO-v0.3-i1-GGUF/resolve/main/NeuralLLaMa-3-8b-ORPO-v0.3.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.4 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/NeuralLLaMa-3-8b-ORPO-v0.3-i1-GGUF/resolve/main/NeuralLLaMa-3-8b-ORPO-v0.3.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/NeuralLLaMa-3-8b-ORPO-v0.3-i1-GGUF/resolve/main/NeuralLLaMa-3-8b-ORPO-v0.3.i1-Q4_0.gguf) | i1-Q4_0 | 4.8 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/NeuralLLaMa-3-8b-ORPO-v0.3-i1-GGUF/resolve/main/NeuralLLaMa-3-8b-ORPO-v0.3.i1-IQ4_NL.gguf) | i1-IQ4_NL | 4.8 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/NeuralLLaMa-3-8b-ORPO-v0.3-i1-GGUF/resolve/main/NeuralLLaMa-3-8b-ORPO-v0.3.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.8 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/NeuralLLaMa-3-8b-ORPO-v0.3-i1-GGUF/resolve/main/NeuralLLaMa-3-8b-ORPO-v0.3.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/NeuralLLaMa-3-8b-ORPO-v0.3-i1-GGUF/resolve/main/NeuralLLaMa-3-8b-ORPO-v0.3.i1-Q4_1.gguf) | i1-Q4_1 | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/NeuralLLaMa-3-8b-ORPO-v0.3-i1-GGUF/resolve/main/NeuralLLaMa-3-8b-ORPO-v0.3.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/NeuralLLaMa-3-8b-ORPO-v0.3-i1-GGUF/resolve/main/NeuralLLaMa-3-8b-ORPO-v0.3.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/NeuralLLaMa-3-8b-ORPO-v0.3-i1-GGUF/resolve/main/NeuralLLaMa-3-8b-ORPO-v0.3.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..72cc695 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa6bb8e3d278d39b8d4a50f5751e3f9126ad84042910465a9837112116721424 +size 4988157