commit 21cf5a8a8950aeb576e7a24b0d3f1e0b587e0779 Author: ModelHub XC Date: Wed Apr 15 11:13:05 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Mlem-4B-RL-Thinking-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..e87a23f --- /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 +Mlem-4B-RL-Thinking.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Mlem-4B-RL-Thinking.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Mlem-4B-RL-Thinking.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Mlem-4B-RL-Thinking.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Mlem-4B-RL-Thinking.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Mlem-4B-RL-Thinking.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Mlem-4B-RL-Thinking.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Mlem-4B-RL-Thinking.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Mlem-4B-RL-Thinking.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Mlem-4B-RL-Thinking.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Mlem-4B-RL-Thinking.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Mlem-4B-RL-Thinking.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Mlem-4B-RL-Thinking.IQ4_XS.gguf b/Mlem-4B-RL-Thinking.IQ4_XS.gguf new file mode 100644 index 0000000..64a6211 --- /dev/null +++ b/Mlem-4B-RL-Thinking.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:abaace252b682ae5714c709e4c2e48f8eef8cca874fc3f98753d3fcc611d9555 +size 2286316224 diff --git a/Mlem-4B-RL-Thinking.Q2_K.gguf b/Mlem-4B-RL-Thinking.Q2_K.gguf new file mode 100644 index 0000000..b77da3a --- /dev/null +++ b/Mlem-4B-RL-Thinking.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05c8a027d47ed2145343bbc7236a9008a561fb3c7851c21ad99a8c81c2111b9f +size 1669499584 diff --git a/Mlem-4B-RL-Thinking.Q3_K_L.gguf b/Mlem-4B-RL-Thinking.Q3_K_L.gguf new file mode 100644 index 0000000..b02f743 --- /dev/null +++ b/Mlem-4B-RL-Thinking.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90aab68d76f2d1efdf49a89cab64c4f93a16af12cc991c61976a582ac1c0a5dc +size 2239785664 diff --git a/Mlem-4B-RL-Thinking.Q3_K_M.gguf b/Mlem-4B-RL-Thinking.Q3_K_M.gguf new file mode 100644 index 0000000..cb30da4 --- /dev/null +++ b/Mlem-4B-RL-Thinking.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00db3f0f576d9db459b26c50d2cb5fd110ab4569dcdb7c76a07c79e2d550564e +size 2075617984 diff --git a/Mlem-4B-RL-Thinking.Q3_K_S.gguf b/Mlem-4B-RL-Thinking.Q3_K_S.gguf new file mode 100644 index 0000000..4544b79 --- /dev/null +++ b/Mlem-4B-RL-Thinking.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d566231f783bdbdf792de85bfbedf3f16ab30a1768981302b1375baae76b2b8f +size 1886997184 diff --git a/Mlem-4B-RL-Thinking.Q4_K_M.gguf b/Mlem-4B-RL-Thinking.Q4_K_M.gguf new file mode 100644 index 0000000..3296d7f --- /dev/null +++ b/Mlem-4B-RL-Thinking.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c16785aa5834f7e0f0d3e8ce1ada9231a49f69095a2c72983dab09fe1adb648 +size 2497280704 diff --git a/Mlem-4B-RL-Thinking.Q4_K_S.gguf b/Mlem-4B-RL-Thinking.Q4_K_S.gguf new file mode 100644 index 0000000..bb5641f --- /dev/null +++ b/Mlem-4B-RL-Thinking.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:159fb58e2b52d35c2a9dc278d567cee23e24459cec446eabb5c57b827d87f302 +size 2383309504 diff --git a/Mlem-4B-RL-Thinking.Q5_K_M.gguf b/Mlem-4B-RL-Thinking.Q5_K_M.gguf new file mode 100644 index 0000000..dfa3597 --- /dev/null +++ b/Mlem-4B-RL-Thinking.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c7cf4b0d18b6488218325c54ec3a2041027b57e9818a8e535aa619455994a15 +size 2889513664 diff --git a/Mlem-4B-RL-Thinking.Q5_K_S.gguf b/Mlem-4B-RL-Thinking.Q5_K_S.gguf new file mode 100644 index 0000000..40882bd --- /dev/null +++ b/Mlem-4B-RL-Thinking.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13ee281bc481ec3fd1b15e66e4f927ced5eeed96b7b16b60cdb827b20b2d8bc8 +size 2823711424 diff --git a/Mlem-4B-RL-Thinking.Q6_K.gguf b/Mlem-4B-RL-Thinking.Q6_K.gguf new file mode 100644 index 0000000..bc9662a --- /dev/null +++ b/Mlem-4B-RL-Thinking.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28bfc3f03a9d26ae8ff7c8c6156e1cdf7d727610a0b11e33f6e3380fb185c0c3 +size 3306261184 diff --git a/Mlem-4B-RL-Thinking.Q8_0.gguf b/Mlem-4B-RL-Thinking.Q8_0.gguf new file mode 100644 index 0000000..2a5fc92 --- /dev/null +++ b/Mlem-4B-RL-Thinking.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03901c7ba8648c6602713181cd55466ba8028a626703b650f1a6c456ed72dbb6 +size 4280405184 diff --git a/Mlem-4B-RL-Thinking.f16.gguf b/Mlem-4B-RL-Thinking.f16.gguf new file mode 100644 index 0000000..6529cea --- /dev/null +++ b/Mlem-4B-RL-Thinking.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0de25d266c78b1c8b287cd716f4b0456f3577bf1b75119795f105fca736373ab +size 8051285184 diff --git a/README.md b/README.md new file mode 100644 index 0000000..e965460 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: Rexhaif/Mlem-4B-RL-Thinking +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/Rexhaif/Mlem-4B-RL-Thinking + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Mlem-4B-RL-Thinking-GGUF).*** + +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/Mlem-4B-RL-Thinking-GGUF/resolve/main/Mlem-4B-RL-Thinking.Q2_K.gguf) | Q2_K | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Mlem-4B-RL-Thinking-GGUF/resolve/main/Mlem-4B-RL-Thinking.Q3_K_S.gguf) | Q3_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/Mlem-4B-RL-Thinking-GGUF/resolve/main/Mlem-4B-RL-Thinking.Q3_K_M.gguf) | Q3_K_M | 2.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Mlem-4B-RL-Thinking-GGUF/resolve/main/Mlem-4B-RL-Thinking.Q3_K_L.gguf) | Q3_K_L | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Mlem-4B-RL-Thinking-GGUF/resolve/main/Mlem-4B-RL-Thinking.IQ4_XS.gguf) | IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Mlem-4B-RL-Thinking-GGUF/resolve/main/Mlem-4B-RL-Thinking.Q4_K_S.gguf) | Q4_K_S | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Mlem-4B-RL-Thinking-GGUF/resolve/main/Mlem-4B-RL-Thinking.Q4_K_M.gguf) | Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Mlem-4B-RL-Thinking-GGUF/resolve/main/Mlem-4B-RL-Thinking.Q5_K_S.gguf) | Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Mlem-4B-RL-Thinking-GGUF/resolve/main/Mlem-4B-RL-Thinking.Q5_K_M.gguf) | Q5_K_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Mlem-4B-RL-Thinking-GGUF/resolve/main/Mlem-4B-RL-Thinking.Q6_K.gguf) | Q6_K | 3.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Mlem-4B-RL-Thinking-GGUF/resolve/main/Mlem-4B-RL-Thinking.Q8_0.gguf) | Q8_0 | 4.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Mlem-4B-RL-Thinking-GGUF/resolve/main/Mlem-4B-RL-Thinking.f16.gguf) | f16 | 8.2 | 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. + +