commit b805dc452fb6b58e4c633ca27066736dbc2499a3 Author: ModelHub XC Date: Thu Jun 11 14:34:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/llama-3-8B-RP-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..63a910d --- /dev/null +++ b/.gitattributes @@ -0,0 +1,49 @@ +*.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 +llama-3-8B-RP.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8B-RP.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8B-RP.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8B-RP.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8B-RP.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8B-RP.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8B-RP.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8B-RP.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8B-RP.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8B-RP.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8B-RP.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8B-RP.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8B-RP.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8B-RP.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..febcd8c --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: Dogge/llama-3-8B-RP +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- trl +- sft +--- +## About + + + + + +static quants of https://huggingface.co/Dogge/llama-3-8B-RP + + +weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. +## 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/llama-3-8B-RP-GGUF/resolve/main/llama-3-8B-RP.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8B-RP-GGUF/resolve/main/llama-3-8B-RP.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8B-RP-GGUF/resolve/main/llama-3-8B-RP.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8B-RP-GGUF/resolve/main/llama-3-8B-RP.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8B-RP-GGUF/resolve/main/llama-3-8B-RP.IQ3_M.gguf) | IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8B-RP-GGUF/resolve/main/llama-3-8B-RP.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8B-RP-GGUF/resolve/main/llama-3-8B-RP.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8B-RP-GGUF/resolve/main/llama-3-8B-RP.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8B-RP-GGUF/resolve/main/llama-3-8B-RP.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8B-RP-GGUF/resolve/main/llama-3-8B-RP.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8B-RP-GGUF/resolve/main/llama-3-8B-RP.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8B-RP-GGUF/resolve/main/llama-3-8B-RP.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8B-RP-GGUF/resolve/main/llama-3-8B-RP.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8B-RP-GGUF/resolve/main/llama-3-8B-RP.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | + +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/llama-3-8B-RP.IQ3_M.gguf b/llama-3-8B-RP.IQ3_M.gguf new file mode 100644 index 0000000..a11d14d --- /dev/null +++ b/llama-3-8B-RP.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ae27384faeb14c7d8a7bc67f14a35beb6b5b6f296ae556b35ee47d8414a3a98 +size 3785336064 diff --git a/llama-3-8B-RP.IQ3_S.gguf b/llama-3-8B-RP.IQ3_S.gguf new file mode 100644 index 0000000..e3cf35b --- /dev/null +++ b/llama-3-8B-RP.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e1a6dfe546c9b4a96f71e72e09fd3d2e0a57ab25bd30b1a3d9b1f3c657d7188 +size 3682837760 diff --git a/llama-3-8B-RP.IQ3_XS.gguf b/llama-3-8B-RP.IQ3_XS.gguf new file mode 100644 index 0000000..9ccc778 --- /dev/null +++ b/llama-3-8B-RP.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:266f10c0d1df9ed1160d7b47e4b5fd9287a339a0aeb065d341ee5b6f63e130f0 +size 3519259904 diff --git a/llama-3-8B-RP.IQ4_XS.gguf b/llama-3-8B-RP.IQ4_XS.gguf new file mode 100644 index 0000000..0c0e63c --- /dev/null +++ b/llama-3-8B-RP.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58ada64c0799ca69b3afd205bceb35d13279545cc56709561f40acf27942ddc1 +size 4484875520 diff --git a/llama-3-8B-RP.Q2_K.gguf b/llama-3-8B-RP.Q2_K.gguf new file mode 100644 index 0000000..569fc54 --- /dev/null +++ b/llama-3-8B-RP.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69c00b2be22dc1a474f082ae6528c1637e765fffa295534189dfda1c56fdd802 +size 3179644160 diff --git a/llama-3-8B-RP.Q3_K_L.gguf b/llama-3-8B-RP.Q3_K_L.gguf new file mode 100644 index 0000000..4fa8837 --- /dev/null +++ b/llama-3-8B-RP.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff5e923bf9df53fdc8dfab44fc0044bdc8dc8fc7cb87678942931b06a7da23fc +size 4322469120 diff --git a/llama-3-8B-RP.Q3_K_M.gguf b/llama-3-8B-RP.Q3_K_M.gguf new file mode 100644 index 0000000..7dc91b5 --- /dev/null +++ b/llama-3-8B-RP.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b6c5323d075697c63f5226229a19b86e314a8b090e8e26a58fc429cfcbd5725 +size 4019430656 diff --git a/llama-3-8B-RP.Q3_K_S.gguf b/llama-3-8B-RP.Q3_K_S.gguf new file mode 100644 index 0000000..6035159 --- /dev/null +++ b/llama-3-8B-RP.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:416d82dd366022b203ccd9f84f5f4fe025e90b004ccb0ddefed175bf2f7680ce +size 3665011968 diff --git a/llama-3-8B-RP.Q4_K_M.gguf b/llama-3-8B-RP.Q4_K_M.gguf new file mode 100644 index 0000000..33b4163 --- /dev/null +++ b/llama-3-8B-RP.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9be4dc3f2eed3bca630b2ac5adfb56942d4cdec4c56211ca015c2f80314589b +size 4921246976 diff --git a/llama-3-8B-RP.Q4_K_S.gguf b/llama-3-8B-RP.Q4_K_S.gguf new file mode 100644 index 0000000..048c019 --- /dev/null +++ b/llama-3-8B-RP.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32535c1a8ac2db0b6bcd0d3684a0b76451301a2a6d1d48a3f1742982efde340d +size 4693181696 diff --git a/llama-3-8B-RP.Q5_K_M.gguf b/llama-3-8B-RP.Q5_K_M.gguf new file mode 100644 index 0000000..b40da80 --- /dev/null +++ b/llama-3-8B-RP.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d11994319d11eb10fb5cbd49443e9d37dcc12937a3670fd2c7b355c2ae558de8 +size 5733500160 diff --git a/llama-3-8B-RP.Q5_K_S.gguf b/llama-3-8B-RP.Q5_K_S.gguf new file mode 100644 index 0000000..58e74f3 --- /dev/null +++ b/llama-3-8B-RP.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f84b98e18feed413dd2d6831d587be163d8fff2218ea0104115b7a0f21a61d2 +size 5599806720 diff --git a/llama-3-8B-RP.Q6_K.gguf b/llama-3-8B-RP.Q6_K.gguf new file mode 100644 index 0000000..52e4a63 --- /dev/null +++ b/llama-3-8B-RP.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b975e0d13d5c928a05af9689e39b9c57787782092b6529845c2c5e42530bb61 +size 6596519168 diff --git a/llama-3-8B-RP.Q8_0.gguf b/llama-3-8B-RP.Q8_0.gguf new file mode 100644 index 0000000..0b1bef1 --- /dev/null +++ b/llama-3-8B-RP.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38491f8ee359e4f297786bd593a3302a9067c0348dd3193e47bda5f6466834b2 +size 8541283584