commit 0f9ed7340e6d83fe345c785ce0489f0abd4c8496 Author: ModelHub XC Date: Wed Sep 9 14:32:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/NeuralLLaMa-3-8b-ORPO-v0.4-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..c53f82e --- /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 +*.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 +NeuralLLaMa-3-8b-ORPO-v0.4.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +NeuralLLaMa-3-8b-ORPO-v0.4.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +NeuralLLaMa-3-8b-ORPO-v0.4.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +NeuralLLaMa-3-8b-ORPO-v0.4.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +NeuralLLaMa-3-8b-ORPO-v0.4.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +NeuralLLaMa-3-8b-ORPO-v0.4.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +NeuralLLaMa-3-8b-ORPO-v0.4.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +NeuralLLaMa-3-8b-ORPO-v0.4.f16.gguf filter=lfs diff=lfs merge=lfs -text +NeuralLLaMa-3-8b-ORPO-v0.4.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +NeuralLLaMa-3-8b-ORPO-v0.4.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +NeuralLLaMa-3-8b-ORPO-v0.4.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +NeuralLLaMa-3-8b-ORPO-v0.4.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/NeuralLLaMa-3-8b-ORPO-v0.4.IQ4_XS.gguf b/NeuralLLaMa-3-8b-ORPO-v0.4.IQ4_XS.gguf new file mode 100644 index 0000000..347b627 --- /dev/null +++ b/NeuralLLaMa-3-8b-ORPO-v0.4.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:580280139850fa3a4b0491b32d8cfd64678064683966827e6ba57800ce7202fd +size 4484374272 diff --git a/NeuralLLaMa-3-8b-ORPO-v0.4.Q2_K.gguf b/NeuralLLaMa-3-8b-ORPO-v0.4.Q2_K.gguf new file mode 100644 index 0000000..76fff3a --- /dev/null +++ b/NeuralLLaMa-3-8b-ORPO-v0.4.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cbf161ccaf2477f484ff50ab32c0a11785f57b3ec69fc65c1b885eb14431b88c +size 3179141248 diff --git a/NeuralLLaMa-3-8b-ORPO-v0.4.Q3_K_L.gguf b/NeuralLLaMa-3-8b-ORPO-v0.4.Q3_K_L.gguf new file mode 100644 index 0000000..69fe717 --- /dev/null +++ b/NeuralLLaMa-3-8b-ORPO-v0.4.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ef36daec329e820387d9fbdfb2979ed0ddb1735bae6e3bfba250f1a97ebf53d +size 4321967040 diff --git a/NeuralLLaMa-3-8b-ORPO-v0.4.Q3_K_M.gguf b/NeuralLLaMa-3-8b-ORPO-v0.4.Q3_K_M.gguf new file mode 100644 index 0000000..febda97 --- /dev/null +++ b/NeuralLLaMa-3-8b-ORPO-v0.4.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7127e09f739b3c67930c2f8bac3a5803ef150d64f044a1df4e7af27f6f4c577 +size 4018928576 diff --git a/NeuralLLaMa-3-8b-ORPO-v0.4.Q3_K_S.gguf b/NeuralLLaMa-3-8b-ORPO-v0.4.Q3_K_S.gguf new file mode 100644 index 0000000..9d7a4ba --- /dev/null +++ b/NeuralLLaMa-3-8b-ORPO-v0.4.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5cd7df9bd5fe6a96801c2f76bb039e5130df5d3f7625d67ead12090a9876ebf3 +size 3664509888 diff --git a/NeuralLLaMa-3-8b-ORPO-v0.4.Q4_K_M.gguf b/NeuralLLaMa-3-8b-ORPO-v0.4.Q4_K_M.gguf new file mode 100644 index 0000000..ec62e56 --- /dev/null +++ b/NeuralLLaMa-3-8b-ORPO-v0.4.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf422eb1207e3a2f67630d73762b7a7d0ced9966df7a65bf11d8f5fb91abd76d +size 4920745984 diff --git a/NeuralLLaMa-3-8b-ORPO-v0.4.Q4_K_S.gguf b/NeuralLLaMa-3-8b-ORPO-v0.4.Q4_K_S.gguf new file mode 100644 index 0000000..e990652 --- /dev/null +++ b/NeuralLLaMa-3-8b-ORPO-v0.4.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88d9ecf76b7f8890e813fdf842e0bd4ca2f3b394fe6ac73d3128b3e7e9909005 +size 4692680704 diff --git a/NeuralLLaMa-3-8b-ORPO-v0.4.Q5_K_M.gguf b/NeuralLLaMa-3-8b-ORPO-v0.4.Q5_K_M.gguf new file mode 100644 index 0000000..0fdf0cb --- /dev/null +++ b/NeuralLLaMa-3-8b-ORPO-v0.4.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38462aba47872e9d959c13e0f1e10b2c65057e83ee0e3995fe502cca0c698caa +size 5733000192 diff --git a/NeuralLLaMa-3-8b-ORPO-v0.4.Q5_K_S.gguf b/NeuralLLaMa-3-8b-ORPO-v0.4.Q5_K_S.gguf new file mode 100644 index 0000000..6ec13cb --- /dev/null +++ b/NeuralLLaMa-3-8b-ORPO-v0.4.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5bdb6f2d9c2455cc428bd069be79c78a138a8f7208adb3272d4ddcd219670793 +size 5599306752 diff --git a/NeuralLLaMa-3-8b-ORPO-v0.4.Q6_K.gguf b/NeuralLLaMa-3-8b-ORPO-v0.4.Q6_K.gguf new file mode 100644 index 0000000..6861fa0 --- /dev/null +++ b/NeuralLLaMa-3-8b-ORPO-v0.4.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1544a3a0a9c80101d04c99382a87f351cf5f8ca340613695845f221decb4ae6 +size 6596020288 diff --git a/NeuralLLaMa-3-8b-ORPO-v0.4.Q8_0.gguf b/NeuralLLaMa-3-8b-ORPO-v0.4.Q8_0.gguf new file mode 100644 index 0000000..06a32a3 --- /dev/null +++ b/NeuralLLaMa-3-8b-ORPO-v0.4.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c321373e70e64ad00d2944ac5cd119546d33174aa4e2f4914e7e5d699edbd86 +size 8540788672 diff --git a/NeuralLLaMa-3-8b-ORPO-v0.4.f16.gguf b/NeuralLLaMa-3-8b-ORPO-v0.4.f16.gguf new file mode 100644 index 0000000..562a07c --- /dev/null +++ b/NeuralLLaMa-3-8b-ORPO-v0.4.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a77e57d2509904e106d2b95d9edb94524a80bb00ffc84bc0dc471f93ede49a2 +size 16068924352 diff --git a/README.md b/README.md new file mode 100644 index 0000000..ef322c7 --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: Kukedlc/NeuralLLaMa-3-8b-ORPO-v0.4 +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/Kukedlc/NeuralLLaMa-3-8b-ORPO-v0.4 + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/NeuralLLaMa-3-8b-ORPO-v0.4-i1-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-v0.4-GGUF/resolve/main/NeuralLLaMa-3-8b-ORPO-v0.4.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/NeuralLLaMa-3-8b-ORPO-v0.4-GGUF/resolve/main/NeuralLLaMa-3-8b-ORPO-v0.4.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/NeuralLLaMa-3-8b-ORPO-v0.4-GGUF/resolve/main/NeuralLLaMa-3-8b-ORPO-v0.4.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/NeuralLLaMa-3-8b-ORPO-v0.4-GGUF/resolve/main/NeuralLLaMa-3-8b-ORPO-v0.4.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/NeuralLLaMa-3-8b-ORPO-v0.4-GGUF/resolve/main/NeuralLLaMa-3-8b-ORPO-v0.4.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/NeuralLLaMa-3-8b-ORPO-v0.4-GGUF/resolve/main/NeuralLLaMa-3-8b-ORPO-v0.4.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/NeuralLLaMa-3-8b-ORPO-v0.4-GGUF/resolve/main/NeuralLLaMa-3-8b-ORPO-v0.4.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/NeuralLLaMa-3-8b-ORPO-v0.4-GGUF/resolve/main/NeuralLLaMa-3-8b-ORPO-v0.4.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/NeuralLLaMa-3-8b-ORPO-v0.4-GGUF/resolve/main/NeuralLLaMa-3-8b-ORPO-v0.4.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/NeuralLLaMa-3-8b-ORPO-v0.4-GGUF/resolve/main/NeuralLLaMa-3-8b-ORPO-v0.4.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/NeuralLLaMa-3-8b-ORPO-v0.4-GGUF/resolve/main/NeuralLLaMa-3-8b-ORPO-v0.4.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/NeuralLLaMa-3-8b-ORPO-v0.4-GGUF/resolve/main/NeuralLLaMa-3-8b-ORPO-v0.4.f16.gguf) | f16 | 16.2 | 16 bpw, overkill | + +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. + +