commit 325c95d9cf43f08b5623ababc79d876334c6f34f Author: ModelHub XC Date: Mon Sep 28 23:35:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/ArliAI-RPMax-v1.3-merge-llama3-8B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..06dc2b3 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,48 @@ +*.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 +ArliAI-RPMax-v1.3-merge-llama3-8B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +ArliAI-RPMax-v1.3-merge-llama3-8B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ArliAI-RPMax-v1.3-merge-llama3-8B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +ArliAI-RPMax-v1.3-merge-llama3-8B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +ArliAI-RPMax-v1.3-merge-llama3-8B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ArliAI-RPMax-v1.3-merge-llama3-8B.f16.gguf filter=lfs diff=lfs merge=lfs -text +ArliAI-RPMax-v1.3-merge-llama3-8B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ArliAI-RPMax-v1.3-merge-llama3-8B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +ArliAI-RPMax-v1.3-merge-llama3-8B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ArliAI-RPMax-v1.3-merge-llama3-8B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ArliAI-RPMax-v1.3-merge-llama3-8B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ArliAI-RPMax-v1.3-merge-llama3-8B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +ArliAI-RPMax-v1.3-merge-llama3-8B.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/ArliAI-RPMax-v1.3-merge-llama3-8B.IQ4_XS.gguf b/ArliAI-RPMax-v1.3-merge-llama3-8B.IQ4_XS.gguf new file mode 100644 index 0000000..77e0274 --- /dev/null +++ b/ArliAI-RPMax-v1.3-merge-llama3-8B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3879212ef6ec82e584f4b08235790162d5cb65d68d61ed5b64779ad30f74c649 +size 4484364704 diff --git a/ArliAI-RPMax-v1.3-merge-llama3-8B.Q2_K.gguf b/ArliAI-RPMax-v1.3-merge-llama3-8B.Q2_K.gguf new file mode 100644 index 0000000..fdfd882 --- /dev/null +++ b/ArliAI-RPMax-v1.3-merge-llama3-8B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81bf098ba9fe38cdf924374762aa3fdd83e0eb056c4c72c7c184f2c69c102b1a +size 3179133344 diff --git a/ArliAI-RPMax-v1.3-merge-llama3-8B.Q3_K_L.gguf b/ArliAI-RPMax-v1.3-merge-llama3-8B.Q3_K_L.gguf new file mode 100644 index 0000000..070f311 --- /dev/null +++ b/ArliAI-RPMax-v1.3-merge-llama3-8B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f4cb66b6bf020905b2787629f300819deb4abd26e72792ccf0cde995dcbaff0 +size 4321958304 diff --git a/ArliAI-RPMax-v1.3-merge-llama3-8B.Q3_K_M.gguf b/ArliAI-RPMax-v1.3-merge-llama3-8B.Q3_K_M.gguf new file mode 100644 index 0000000..8576ef3 --- /dev/null +++ b/ArliAI-RPMax-v1.3-merge-llama3-8B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2bd044a1625987ec3c6d5fd352ba2f788a9bd86aa93c795eda2923e260b0c885 +size 4018919840 diff --git a/ArliAI-RPMax-v1.3-merge-llama3-8B.Q3_K_S.gguf b/ArliAI-RPMax-v1.3-merge-llama3-8B.Q3_K_S.gguf new file mode 100644 index 0000000..c92852c --- /dev/null +++ b/ArliAI-RPMax-v1.3-merge-llama3-8B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:688d29a1746377fd1a4c3bc9f318a4aca813f39861e837a38cc03eaf6b570178 +size 3664501152 diff --git a/ArliAI-RPMax-v1.3-merge-llama3-8B.Q4_0_4_4.gguf b/ArliAI-RPMax-v1.3-merge-llama3-8B.Q4_0_4_4.gguf new file mode 100644 index 0000000..9bae5e9 --- /dev/null +++ b/ArliAI-RPMax-v1.3-merge-llama3-8B.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c30cff8ee2c14d97ab5e23be4ae2622f3f1cc8210567dd7d59b117116ffe60d +size 4661213600 diff --git a/ArliAI-RPMax-v1.3-merge-llama3-8B.Q4_K_M.gguf b/ArliAI-RPMax-v1.3-merge-llama3-8B.Q4_K_M.gguf new file mode 100644 index 0000000..1863f3f --- /dev/null +++ b/ArliAI-RPMax-v1.3-merge-llama3-8B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1be0f1b2a56818c811813d5bdbe2aff5ab80d05c4215533f3f8c9ff717c6cae1 +size 4920736160 diff --git a/ArliAI-RPMax-v1.3-merge-llama3-8B.Q4_K_S.gguf b/ArliAI-RPMax-v1.3-merge-llama3-8B.Q4_K_S.gguf new file mode 100644 index 0000000..04ba355 --- /dev/null +++ b/ArliAI-RPMax-v1.3-merge-llama3-8B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a39c929164880451318aace5adf81bf4dc04b7f7cf4a27073b0e1ff2f0762a69 +size 4692670880 diff --git a/ArliAI-RPMax-v1.3-merge-llama3-8B.Q5_K_M.gguf b/ArliAI-RPMax-v1.3-merge-llama3-8B.Q5_K_M.gguf new file mode 100644 index 0000000..810716b --- /dev/null +++ b/ArliAI-RPMax-v1.3-merge-llama3-8B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6917ff4f743fac37617cb22a90371594c70646bcb08e337ff787ea83399ae5e8 +size 5732989344 diff --git a/ArliAI-RPMax-v1.3-merge-llama3-8B.Q5_K_S.gguf b/ArliAI-RPMax-v1.3-merge-llama3-8B.Q5_K_S.gguf new file mode 100644 index 0000000..4acc164 --- /dev/null +++ b/ArliAI-RPMax-v1.3-merge-llama3-8B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70d3548adc4aec7e240063b1d56ff70564f5a19fa401b19c66789f11bd8ee9f4 +size 5599295904 diff --git a/ArliAI-RPMax-v1.3-merge-llama3-8B.Q6_K.gguf b/ArliAI-RPMax-v1.3-merge-llama3-8B.Q6_K.gguf new file mode 100644 index 0000000..2bcdc48 --- /dev/null +++ b/ArliAI-RPMax-v1.3-merge-llama3-8B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d7343673cc3865fad3dd205ffd99e50cc9ad0c66644941dd6e7b8f8dc2438f8 +size 6596008352 diff --git a/ArliAI-RPMax-v1.3-merge-llama3-8B.Q8_0.gguf b/ArliAI-RPMax-v1.3-merge-llama3-8B.Q8_0.gguf new file mode 100644 index 0000000..4df73f2 --- /dev/null +++ b/ArliAI-RPMax-v1.3-merge-llama3-8B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f108776c1348a93df70c4ef45549fce9acc591b02e6fc884d65fffa641a86d5d +size 8540772768 diff --git a/ArliAI-RPMax-v1.3-merge-llama3-8B.f16.gguf b/ArliAI-RPMax-v1.3-merge-llama3-8B.f16.gguf new file mode 100644 index 0000000..8741130 --- /dev/null +++ b/ArliAI-RPMax-v1.3-merge-llama3-8B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af64626d23b92ac7813641639895c52fa1f22dabb0b66bbb577506f1a2d06afe +size 16068893088 diff --git a/README.md b/README.md new file mode 100644 index 0000000..b249ae8 --- /dev/null +++ b/README.md @@ -0,0 +1,67 @@ +--- +base_model: win10/ArliAI-RPMax-v1.3-merge-llama3-8B +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/win10/ArliAI-RPMax-v1.3-merge-llama3-8B + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/ArliAI-RPMax-v1.3-merge-llama3-8B-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/ArliAI-RPMax-v1.3-merge-llama3-8B-GGUF/resolve/main/ArliAI-RPMax-v1.3-merge-llama3-8B.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/ArliAI-RPMax-v1.3-merge-llama3-8B-GGUF/resolve/main/ArliAI-RPMax-v1.3-merge-llama3-8B.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/ArliAI-RPMax-v1.3-merge-llama3-8B-GGUF/resolve/main/ArliAI-RPMax-v1.3-merge-llama3-8B.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/ArliAI-RPMax-v1.3-merge-llama3-8B-GGUF/resolve/main/ArliAI-RPMax-v1.3-merge-llama3-8B.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/ArliAI-RPMax-v1.3-merge-llama3-8B-GGUF/resolve/main/ArliAI-RPMax-v1.3-merge-llama3-8B.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/ArliAI-RPMax-v1.3-merge-llama3-8B-GGUF/resolve/main/ArliAI-RPMax-v1.3-merge-llama3-8B.Q4_0_4_4.gguf) | Q4_0_4_4 | 4.8 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/ArliAI-RPMax-v1.3-merge-llama3-8B-GGUF/resolve/main/ArliAI-RPMax-v1.3-merge-llama3-8B.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/ArliAI-RPMax-v1.3-merge-llama3-8B-GGUF/resolve/main/ArliAI-RPMax-v1.3-merge-llama3-8B.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/ArliAI-RPMax-v1.3-merge-llama3-8B-GGUF/resolve/main/ArliAI-RPMax-v1.3-merge-llama3-8B.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/ArliAI-RPMax-v1.3-merge-llama3-8B-GGUF/resolve/main/ArliAI-RPMax-v1.3-merge-llama3-8B.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/ArliAI-RPMax-v1.3-merge-llama3-8B-GGUF/resolve/main/ArliAI-RPMax-v1.3-merge-llama3-8B.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/ArliAI-RPMax-v1.3-merge-llama3-8B-GGUF/resolve/main/ArliAI-RPMax-v1.3-merge-llama3-8B.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/ArliAI-RPMax-v1.3-merge-llama3-8B-GGUF/resolve/main/ArliAI-RPMax-v1.3-merge-llama3-8B.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. + +