commit 23301192998f19fc0774614bb37c9db6c77b3df6 Author: ModelHub XC Date: Thu Apr 23 18:57:03 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/RAG-RP-Journal-GenZ-Flow-Grokked-4B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..542eef8 --- /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 +RAG-RP-Journal-GenZ-Flow-Grokked-4B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +RAG-RP-Journal-GenZ-Flow-Grokked-4B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +RAG-RP-Journal-GenZ-Flow-Grokked-4B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +RAG-RP-Journal-GenZ-Flow-Grokked-4B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +RAG-RP-Journal-GenZ-Flow-Grokked-4B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +RAG-RP-Journal-GenZ-Flow-Grokked-4B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +RAG-RP-Journal-GenZ-Flow-Grokked-4B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +RAG-RP-Journal-GenZ-Flow-Grokked-4B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +RAG-RP-Journal-GenZ-Flow-Grokked-4B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +RAG-RP-Journal-GenZ-Flow-Grokked-4B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +RAG-RP-Journal-GenZ-Flow-Grokked-4B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +RAG-RP-Journal-GenZ-Flow-Grokked-4B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/RAG-RP-Journal-GenZ-Flow-Grokked-4B.IQ4_XS.gguf b/RAG-RP-Journal-GenZ-Flow-Grokked-4B.IQ4_XS.gguf new file mode 100644 index 0000000..1239781 --- /dev/null +++ b/RAG-RP-Journal-GenZ-Flow-Grokked-4B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96ec12d152f785722aaf7728daa5509f9bc3e715963c6d98890376f5ea1edb87 +size 2490800736 diff --git a/RAG-RP-Journal-GenZ-Flow-Grokked-4B.Q2_K.gguf b/RAG-RP-Journal-GenZ-Flow-Grokked-4B.Q2_K.gguf new file mode 100644 index 0000000..70be3e0 --- /dev/null +++ b/RAG-RP-Journal-GenZ-Flow-Grokked-4B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d127145d7c16732741172e9b4156f4f7632e90136826ffea7d8fca13753d474 +size 1806604896 diff --git a/RAG-RP-Journal-GenZ-Flow-Grokked-4B.Q3_K_L.gguf b/RAG-RP-Journal-GenZ-Flow-Grokked-4B.Q3_K_L.gguf new file mode 100644 index 0000000..f79f771 --- /dev/null +++ b/RAG-RP-Journal-GenZ-Flow-Grokked-4B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5dbfd50940b5da7e681666bdb4b3579c048762015e92f90bac235d399e062ce8 +size 2451479136 diff --git a/RAG-RP-Journal-GenZ-Flow-Grokked-4B.Q3_K_M.gguf b/RAG-RP-Journal-GenZ-Flow-Grokked-4B.Q3_K_M.gguf new file mode 100644 index 0000000..a06c07c --- /dev/null +++ b/RAG-RP-Journal-GenZ-Flow-Grokked-4B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2c0de487ac84ec85052650d21a1862c984351d85fe833645a4846002d101ad6 +size 2269813344 diff --git a/RAG-RP-Journal-GenZ-Flow-Grokked-4B.Q3_K_S.gguf b/RAG-RP-Journal-GenZ-Flow-Grokked-4B.Q3_K_S.gguf new file mode 100644 index 0000000..d6eb44c --- /dev/null +++ b/RAG-RP-Journal-GenZ-Flow-Grokked-4B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:027cbcc2a5e88237123cfac23520cce547835bdb23cbca6f0b41af4cdda7f1f8 +size 2062195296 diff --git a/RAG-RP-Journal-GenZ-Flow-Grokked-4B.Q4_K_M.gguf b/RAG-RP-Journal-GenZ-Flow-Grokked-4B.Q4_K_M.gguf new file mode 100644 index 0000000..19da96e --- /dev/null +++ b/RAG-RP-Journal-GenZ-Flow-Grokked-4B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:966a8be948c8a2b6e63db28f7c512685cd2d969720f6bc2eadece4a4f736dfb5 +size 2742950496 diff --git a/RAG-RP-Journal-GenZ-Flow-Grokked-4B.Q4_K_S.gguf b/RAG-RP-Journal-GenZ-Flow-Grokked-4B.Q4_K_S.gguf new file mode 100644 index 0000000..35bfb8b --- /dev/null +++ b/RAG-RP-Journal-GenZ-Flow-Grokked-4B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00d7777eddb8c15e9e31fa080c4dc401c6e3fd8edb6f0145be71ad447b159eb6 +size 2614270560 diff --git a/RAG-RP-Journal-GenZ-Flow-Grokked-4B.Q5_K_M.gguf b/RAG-RP-Journal-GenZ-Flow-Grokked-4B.Q5_K_M.gguf new file mode 100644 index 0000000..4928f36 --- /dev/null +++ b/RAG-RP-Journal-GenZ-Flow-Grokked-4B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c3fb5bbd5cf65281f753ee79ecfacf7c46d8a2b23a9f971d037c887e90dcef3 +size 3175488096 diff --git a/RAG-RP-Journal-GenZ-Flow-Grokked-4B.Q5_K_S.gguf b/RAG-RP-Journal-GenZ-Flow-Grokked-4B.Q5_K_S.gguf new file mode 100644 index 0000000..e8c2ae4 --- /dev/null +++ b/RAG-RP-Journal-GenZ-Flow-Grokked-4B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8c1fadc7c6a27ca63d7c411ef7ebe465b40a7a35213519d31e78e81e42ed0d7 +size 3100285536 diff --git a/RAG-RP-Journal-GenZ-Flow-Grokked-4B.Q6_K.gguf b/RAG-RP-Journal-GenZ-Flow-Grokked-4B.Q6_K.gguf new file mode 100644 index 0000000..e7fd916 --- /dev/null +++ b/RAG-RP-Journal-GenZ-Flow-Grokked-4B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9697ae17a359132fd0d3ed0c17d2db6c601d77acbb144f82546da76eded59283 +size 3635059296 diff --git a/RAG-RP-Journal-GenZ-Flow-Grokked-4B.Q8_0.gguf b/RAG-RP-Journal-GenZ-Flow-Grokked-4B.Q8_0.gguf new file mode 100644 index 0000000..ad0f5b8 --- /dev/null +++ b/RAG-RP-Journal-GenZ-Flow-Grokked-4B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07837b76217b7a0d1c5d886c0cce6e9e2ebeebd8b6dacebd7bd49e5d1b0e1bd9 +size 4705657440 diff --git a/RAG-RP-Journal-GenZ-Flow-Grokked-4B.f16.gguf b/RAG-RP-Journal-GenZ-Flow-Grokked-4B.f16.gguf new file mode 100644 index 0000000..785bcc2 --- /dev/null +++ b/RAG-RP-Journal-GenZ-Flow-Grokked-4B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3bf756df136ea829ebc86dabf67a3f9c054b5aa85047792270abf2e4bec981fe +size 8849908320 diff --git a/README.md b/README.md new file mode 100644 index 0000000..f8e530a --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: TroyDoesAI/RAG-RP-Journal-GenZ-Flow-Grokked-4B +language: +- en +library_name: transformers +license: artistic-2.0 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/TroyDoesAI/RAG-RP-Journal-GenZ-Flow-Grokked-4B + + +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/RAG-RP-Journal-GenZ-Flow-Grokked-4B-GGUF/resolve/main/RAG-RP-Journal-GenZ-Flow-Grokked-4B.Q2_K.gguf) | Q2_K | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/RAG-RP-Journal-GenZ-Flow-Grokked-4B-GGUF/resolve/main/RAG-RP-Journal-GenZ-Flow-Grokked-4B.Q3_K_S.gguf) | Q3_K_S | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/RAG-RP-Journal-GenZ-Flow-Grokked-4B-GGUF/resolve/main/RAG-RP-Journal-GenZ-Flow-Grokked-4B.Q3_K_M.gguf) | Q3_K_M | 2.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/RAG-RP-Journal-GenZ-Flow-Grokked-4B-GGUF/resolve/main/RAG-RP-Journal-GenZ-Flow-Grokked-4B.Q3_K_L.gguf) | Q3_K_L | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/RAG-RP-Journal-GenZ-Flow-Grokked-4B-GGUF/resolve/main/RAG-RP-Journal-GenZ-Flow-Grokked-4B.IQ4_XS.gguf) | IQ4_XS | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/RAG-RP-Journal-GenZ-Flow-Grokked-4B-GGUF/resolve/main/RAG-RP-Journal-GenZ-Flow-Grokked-4B.Q4_K_S.gguf) | Q4_K_S | 2.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/RAG-RP-Journal-GenZ-Flow-Grokked-4B-GGUF/resolve/main/RAG-RP-Journal-GenZ-Flow-Grokked-4B.Q4_K_M.gguf) | Q4_K_M | 2.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/RAG-RP-Journal-GenZ-Flow-Grokked-4B-GGUF/resolve/main/RAG-RP-Journal-GenZ-Flow-Grokked-4B.Q5_K_S.gguf) | Q5_K_S | 3.2 | | +| [GGUF](https://huggingface.co/mradermacher/RAG-RP-Journal-GenZ-Flow-Grokked-4B-GGUF/resolve/main/RAG-RP-Journal-GenZ-Flow-Grokked-4B.Q5_K_M.gguf) | Q5_K_M | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/RAG-RP-Journal-GenZ-Flow-Grokked-4B-GGUF/resolve/main/RAG-RP-Journal-GenZ-Flow-Grokked-4B.Q6_K.gguf) | Q6_K | 3.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/RAG-RP-Journal-GenZ-Flow-Grokked-4B-GGUF/resolve/main/RAG-RP-Journal-GenZ-Flow-Grokked-4B.Q8_0.gguf) | Q8_0 | 4.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/RAG-RP-Journal-GenZ-Flow-Grokked-4B-GGUF/resolve/main/RAG-RP-Journal-GenZ-Flow-Grokked-4B.f16.gguf) | f16 | 8.9 | 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. + +