commit 61a2cc3c8cdfff567f27bf0ed778213185f605c0 Author: ModelHub XC Date: Sun Jun 14 21:16:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen2.5-3B-Instruct-abliterated-16bit-GRPO-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..476ce69 --- /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 +Qwen2.5-3B-Instruct-abliterated-16bit-GRPO.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Instruct-abliterated-16bit-GRPO.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Instruct-abliterated-16bit-GRPO.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Instruct-abliterated-16bit-GRPO.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Instruct-abliterated-16bit-GRPO.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Instruct-abliterated-16bit-GRPO.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Instruct-abliterated-16bit-GRPO.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Instruct-abliterated-16bit-GRPO.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Instruct-abliterated-16bit-GRPO.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Instruct-abliterated-16bit-GRPO.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Instruct-abliterated-16bit-GRPO.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Instruct-abliterated-16bit-GRPO.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2.5-3B-Instruct-abliterated-16bit-GRPO.IQ4_XS.gguf b/Qwen2.5-3B-Instruct-abliterated-16bit-GRPO.IQ4_XS.gguf new file mode 100644 index 0000000..169d2be --- /dev/null +++ b/Qwen2.5-3B-Instruct-abliterated-16bit-GRPO.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:095ac9bba7411e1f966faf891ddbf0598eca237b6349377d1cc5917c5a4a249a +size 1753185696 diff --git a/Qwen2.5-3B-Instruct-abliterated-16bit-GRPO.Q2_K.gguf b/Qwen2.5-3B-Instruct-abliterated-16bit-GRPO.Q2_K.gguf new file mode 100644 index 0000000..5f92607 --- /dev/null +++ b/Qwen2.5-3B-Instruct-abliterated-16bit-GRPO.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed13e39ec12693ed18c668583adea7c146e56f0e51911388ce8a52290f16a607 +size 1274756512 diff --git a/Qwen2.5-3B-Instruct-abliterated-16bit-GRPO.Q3_K_L.gguf b/Qwen2.5-3B-Instruct-abliterated-16bit-GRPO.Q3_K_L.gguf new file mode 100644 index 0000000..c445d98 --- /dev/null +++ b/Qwen2.5-3B-Instruct-abliterated-16bit-GRPO.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77c5fabe266df985bc873b76ee483d5d34155fd4d0953fcfb2cedfc6fbef0ab5 +size 1707392416 diff --git a/Qwen2.5-3B-Instruct-abliterated-16bit-GRPO.Q3_K_M.gguf b/Qwen2.5-3B-Instruct-abliterated-16bit-GRPO.Q3_K_M.gguf new file mode 100644 index 0000000..1a09230 --- /dev/null +++ b/Qwen2.5-3B-Instruct-abliterated-16bit-GRPO.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad6e1401f233df34d3c82b548818a0c28b17853d2498092ebcd6bce5533b1218 +size 1590476192 diff --git a/Qwen2.5-3B-Instruct-abliterated-16bit-GRPO.Q3_K_S.gguf b/Qwen2.5-3B-Instruct-abliterated-16bit-GRPO.Q3_K_S.gguf new file mode 100644 index 0000000..ca05e42 --- /dev/null +++ b/Qwen2.5-3B-Instruct-abliterated-16bit-GRPO.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:029954c980c733f9ee5ee30b1621b372b186eb1b7c87daab4fd834bebaf30ed9 +size 1454357920 diff --git a/Qwen2.5-3B-Instruct-abliterated-16bit-GRPO.Q4_K_M.gguf b/Qwen2.5-3B-Instruct-abliterated-16bit-GRPO.Q4_K_M.gguf new file mode 100644 index 0000000..364fdc0 --- /dev/null +++ b/Qwen2.5-3B-Instruct-abliterated-16bit-GRPO.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea5464fea6bac34b1a4afc43f52cff7e59243c4537ac87f59dddd73a15fb745f +size 1929903520 diff --git a/Qwen2.5-3B-Instruct-abliterated-16bit-GRPO.Q4_K_S.gguf b/Qwen2.5-3B-Instruct-abliterated-16bit-GRPO.Q4_K_S.gguf new file mode 100644 index 0000000..18856f4 --- /dev/null +++ b/Qwen2.5-3B-Instruct-abliterated-16bit-GRPO.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca5941f4e0dfcada8fe6eb631e229d2e66ffbb96b9bdd0c4fa9895d3aabf0c8b +size 1834384800 diff --git a/Qwen2.5-3B-Instruct-abliterated-16bit-GRPO.Q5_K_M.gguf b/Qwen2.5-3B-Instruct-abliterated-16bit-GRPO.Q5_K_M.gguf new file mode 100644 index 0000000..9dd312d --- /dev/null +++ b/Qwen2.5-3B-Instruct-abliterated-16bit-GRPO.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01607cb0e3cfaed5dcdbcdf6a8110e9fdf8f2dd7217c14cf7c173de4fa6a43b7 +size 2224815520 diff --git a/Qwen2.5-3B-Instruct-abliterated-16bit-GRPO.Q5_K_S.gguf b/Qwen2.5-3B-Instruct-abliterated-16bit-GRPO.Q5_K_S.gguf new file mode 100644 index 0000000..d4dd2fa --- /dev/null +++ b/Qwen2.5-3B-Instruct-abliterated-16bit-GRPO.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c8bcbab29523ab11d12dc3d866bdbfda513c4ffcca7b91b451b07d13b765f0a +size 2169666976 diff --git a/Qwen2.5-3B-Instruct-abliterated-16bit-GRPO.Q6_K.gguf b/Qwen2.5-3B-Instruct-abliterated-16bit-GRPO.Q6_K.gguf new file mode 100644 index 0000000..4f0638b --- /dev/null +++ b/Qwen2.5-3B-Instruct-abliterated-16bit-GRPO.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd745e5c15e4682d712e80e4c422cfd21d895d3dd47a3f66ede9b4c9ca6a3af5 +size 2538159520 diff --git a/Qwen2.5-3B-Instruct-abliterated-16bit-GRPO.Q8_0.gguf b/Qwen2.5-3B-Instruct-abliterated-16bit-GRPO.Q8_0.gguf new file mode 100644 index 0000000..fd30521 --- /dev/null +++ b/Qwen2.5-3B-Instruct-abliterated-16bit-GRPO.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22e2c3401da181adfc0847f5122b1400cba9609c19fc06657204dcf025a15abf +size 3285476768 diff --git a/Qwen2.5-3B-Instruct-abliterated-16bit-GRPO.f16.gguf b/Qwen2.5-3B-Instruct-abliterated-16bit-GRPO.f16.gguf new file mode 100644 index 0000000..995baef --- /dev/null +++ b/Qwen2.5-3B-Instruct-abliterated-16bit-GRPO.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:974b7d3f5b81a0b1bf8908bae3141a65c427c693a8914afd7f4b58374938a4b0 +size 6178317728 diff --git a/README.md b/README.md new file mode 100644 index 0000000..2f1f64a --- /dev/null +++ b/README.md @@ -0,0 +1,76 @@ +--- +base_model: MildConcussion/Qwen2.5-3B-Instruct-abliterated-16bit-GRPO +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- qwen2 +- trl +- grpo +--- +## About + + + + + + +static quants of https://huggingface.co/MildConcussion/Qwen2.5-3B-Instruct-abliterated-16bit-GRPO + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen2.5-3B-Instruct-abliterated-16bit-GRPO-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/Qwen2.5-3B-Instruct-abliterated-16bit-GRPO-GGUF/resolve/main/Qwen2.5-3B-Instruct-abliterated-16bit-GRPO.Q2_K.gguf) | Q2_K | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-abliterated-16bit-GRPO-GGUF/resolve/main/Qwen2.5-3B-Instruct-abliterated-16bit-GRPO.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-abliterated-16bit-GRPO-GGUF/resolve/main/Qwen2.5-3B-Instruct-abliterated-16bit-GRPO.Q3_K_M.gguf) | Q3_K_M | 1.7 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-abliterated-16bit-GRPO-GGUF/resolve/main/Qwen2.5-3B-Instruct-abliterated-16bit-GRPO.Q3_K_L.gguf) | Q3_K_L | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-abliterated-16bit-GRPO-GGUF/resolve/main/Qwen2.5-3B-Instruct-abliterated-16bit-GRPO.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-abliterated-16bit-GRPO-GGUF/resolve/main/Qwen2.5-3B-Instruct-abliterated-16bit-GRPO.Q4_K_S.gguf) | Q4_K_S | 1.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-abliterated-16bit-GRPO-GGUF/resolve/main/Qwen2.5-3B-Instruct-abliterated-16bit-GRPO.Q4_K_M.gguf) | Q4_K_M | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-abliterated-16bit-GRPO-GGUF/resolve/main/Qwen2.5-3B-Instruct-abliterated-16bit-GRPO.Q5_K_S.gguf) | Q5_K_S | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-abliterated-16bit-GRPO-GGUF/resolve/main/Qwen2.5-3B-Instruct-abliterated-16bit-GRPO.Q5_K_M.gguf) | Q5_K_M | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-abliterated-16bit-GRPO-GGUF/resolve/main/Qwen2.5-3B-Instruct-abliterated-16bit-GRPO.Q6_K.gguf) | Q6_K | 2.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-abliterated-16bit-GRPO-GGUF/resolve/main/Qwen2.5-3B-Instruct-abliterated-16bit-GRPO.Q8_0.gguf) | Q8_0 | 3.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-abliterated-16bit-GRPO-GGUF/resolve/main/Qwen2.5-3B-Instruct-abliterated-16bit-GRPO.f16.gguf) | f16 | 6.3 | 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. + +