commit 8f5cf028aeda1d27ea1e69b1aa76d35f81daafcd Author: ModelHub XC Date: Tue Jul 21 14:00:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen-3b-RL-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..1bef652 --- /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 +Qwen-3b-RL.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-3b-RL.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-3b-RL.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-3b-RL.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-3b-RL.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-3b-RL.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-3b-RL.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-3b-RL.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-3b-RL.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-3b-RL.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-3b-RL.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-3b-RL.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen-3b-RL.IQ4_XS.gguf b/Qwen-3b-RL.IQ4_XS.gguf new file mode 100644 index 0000000..93dd47b --- /dev/null +++ b/Qwen-3b-RL.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ed0886f206f92f1f85c8ee4d45538de06cacb1d7f3110f031c49b8ec10ddc9c +size 1753185632 diff --git a/Qwen-3b-RL.Q2_K.gguf b/Qwen-3b-RL.Q2_K.gguf new file mode 100644 index 0000000..7883064 --- /dev/null +++ b/Qwen-3b-RL.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9656d42ac7aa8bb98065c57207000ba1ebc9ca20324ea9c600f32e0b70fef4e4 +size 1274756448 diff --git a/Qwen-3b-RL.Q3_K_L.gguf b/Qwen-3b-RL.Q3_K_L.gguf new file mode 100644 index 0000000..9ef8929 --- /dev/null +++ b/Qwen-3b-RL.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:007b45710791c1f18629b4e04419f1d9ed318bb6df24d9e661e2719d9190c6c9 +size 1707392352 diff --git a/Qwen-3b-RL.Q3_K_M.gguf b/Qwen-3b-RL.Q3_K_M.gguf new file mode 100644 index 0000000..d4c0b27 --- /dev/null +++ b/Qwen-3b-RL.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:925b19fc89909b898fd9076e0c16d07d32dff5d20ad9c950c2d064dfbeda6bc4 +size 1590476128 diff --git a/Qwen-3b-RL.Q3_K_S.gguf b/Qwen-3b-RL.Q3_K_S.gguf new file mode 100644 index 0000000..b96e086 --- /dev/null +++ b/Qwen-3b-RL.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6c61fb40b4512d7f1e52f96bcb2bf968b0b0b8552bd74e6d54bdbdcf56b2290 +size 1454357856 diff --git a/Qwen-3b-RL.Q4_K_M.gguf b/Qwen-3b-RL.Q4_K_M.gguf new file mode 100644 index 0000000..9e97f6e --- /dev/null +++ b/Qwen-3b-RL.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:836859b60aa09c1d80ee0e07d8d083826a82b58f085b77145c8a03915ab1d4ea +size 1929903456 diff --git a/Qwen-3b-RL.Q4_K_S.gguf b/Qwen-3b-RL.Q4_K_S.gguf new file mode 100644 index 0000000..a67687f --- /dev/null +++ b/Qwen-3b-RL.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc2c2d46a6da5fa6b10a8702389cb7bc2d1231884fcabcef37ef3d0549d61afa +size 1834384736 diff --git a/Qwen-3b-RL.Q5_K_M.gguf b/Qwen-3b-RL.Q5_K_M.gguf new file mode 100644 index 0000000..0209933 --- /dev/null +++ b/Qwen-3b-RL.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a517e6c74f03aaf2da00eb8852340629eab503c890a8e6ffee69fb0db44f2c2 +size 2224815456 diff --git a/Qwen-3b-RL.Q5_K_S.gguf b/Qwen-3b-RL.Q5_K_S.gguf new file mode 100644 index 0000000..04acfab --- /dev/null +++ b/Qwen-3b-RL.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36322d5b240a380782347d8205bf45cdcd12e5530f7ca658563e95f465d97a5d +size 2169666912 diff --git a/Qwen-3b-RL.Q6_K.gguf b/Qwen-3b-RL.Q6_K.gguf new file mode 100644 index 0000000..bb12624 --- /dev/null +++ b/Qwen-3b-RL.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0d5922e415adff673e96f8403771fd73667c2aacb251653c51ad87798a318d5 +size 2538159456 diff --git a/Qwen-3b-RL.Q8_0.gguf b/Qwen-3b-RL.Q8_0.gguf new file mode 100644 index 0000000..4218666 --- /dev/null +++ b/Qwen-3b-RL.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b64ad51017e36718522e523aa7105c633595c942480580c2de6bf51de16505d +size 3285476704 diff --git a/Qwen-3b-RL.f16.gguf b/Qwen-3b-RL.f16.gguf new file mode 100644 index 0000000..6c77dda --- /dev/null +++ b/Qwen-3b-RL.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f8e42521fcd53541dfd21e25ba115d83642f48c74abf4816de8b6072db6c253 +size 6178317664 diff --git a/README.md b/README.md new file mode 100644 index 0000000..23319f2 --- /dev/null +++ b/README.md @@ -0,0 +1,63 @@ +--- +base_model: icemoon28/Qwen-3b-RL +language: +- en +library_name: transformers +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/icemoon28/Qwen-3b-RL + + +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/Qwen-3b-RL-GGUF/resolve/main/Qwen-3b-RL.Q2_K.gguf) | Q2_K | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-3b-RL-GGUF/resolve/main/Qwen-3b-RL.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-3b-RL-GGUF/resolve/main/Qwen-3b-RL.Q3_K_M.gguf) | Q3_K_M | 1.7 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen-3b-RL-GGUF/resolve/main/Qwen-3b-RL.Q3_K_L.gguf) | Q3_K_L | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-3b-RL-GGUF/resolve/main/Qwen-3b-RL.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-3b-RL-GGUF/resolve/main/Qwen-3b-RL.Q4_K_S.gguf) | Q4_K_S | 1.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen-3b-RL-GGUF/resolve/main/Qwen-3b-RL.Q4_K_M.gguf) | Q4_K_M | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen-3b-RL-GGUF/resolve/main/Qwen-3b-RL.Q5_K_S.gguf) | Q5_K_S | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-3b-RL-GGUF/resolve/main/Qwen-3b-RL.Q5_K_M.gguf) | Q5_K_M | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-3b-RL-GGUF/resolve/main/Qwen-3b-RL.Q6_K.gguf) | Q6_K | 2.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen-3b-RL-GGUF/resolve/main/Qwen-3b-RL.Q8_0.gguf) | Q8_0 | 3.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen-3b-RL-GGUF/resolve/main/Qwen-3b-RL.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. + +