commit 2ae3c864736c9ef89f1abe2e74f44d11f191b902 Author: ModelHub XC Date: Mon Jul 6 01:45:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen-0.5B-SFT-2-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..ac8a8f8 --- /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-0.5B-SFT-2.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-0.5B-SFT-2.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-0.5B-SFT-2.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-0.5B-SFT-2.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-0.5B-SFT-2.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-0.5B-SFT-2.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-0.5B-SFT-2.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-0.5B-SFT-2.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-0.5B-SFT-2.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-0.5B-SFT-2.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-0.5B-SFT-2.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-0.5B-SFT-2.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen-0.5B-SFT-2.IQ4_XS.gguf b/Qwen-0.5B-SFT-2.IQ4_XS.gguf new file mode 100644 index 0000000..afd105f --- /dev/null +++ b/Qwen-0.5B-SFT-2.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1c16ff743e3342e618969ac5c9898606cbff1369ae356e6c21cb1ef2c88e74c +size 351443168 diff --git a/Qwen-0.5B-SFT-2.Q2_K.gguf b/Qwen-0.5B-SFT-2.Q2_K.gguf new file mode 100644 index 0000000..707b8bd --- /dev/null +++ b/Qwen-0.5B-SFT-2.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66969480797cfec308fdcaac4fe6a8e0c224972012274271c6f04600b8256cc3 +size 338605280 diff --git a/Qwen-0.5B-SFT-2.Q3_K_L.gguf b/Qwen-0.5B-SFT-2.Q3_K_L.gguf new file mode 100644 index 0000000..a63763f --- /dev/null +++ b/Qwen-0.5B-SFT-2.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b548601d86a2d359fb167e1602fba2ac2223166387a4e877d4bc14c1eca05c06 +size 369356000 diff --git a/Qwen-0.5B-SFT-2.Q3_K_M.gguf b/Qwen-0.5B-SFT-2.Q3_K_M.gguf new file mode 100644 index 0000000..31fef95 --- /dev/null +++ b/Qwen-0.5B-SFT-2.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0a59401ddd3740b08906acead372d9c7e1f957bf50b49d1d4ec1d48ff2fd652 +size 355464416 diff --git a/Qwen-0.5B-SFT-2.Q3_K_S.gguf b/Qwen-0.5B-SFT-2.Q3_K_S.gguf new file mode 100644 index 0000000..4b7eb6a --- /dev/null +++ b/Qwen-0.5B-SFT-2.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea295cb847376301fbb0eedd8fdfeb12a6875e81bd855ca1eb708bf1f19ddd5b +size 338261216 diff --git a/Qwen-0.5B-SFT-2.Q4_K_M.gguf b/Qwen-0.5B-SFT-2.Q4_K_M.gguf new file mode 100644 index 0000000..993c562 --- /dev/null +++ b/Qwen-0.5B-SFT-2.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb9bebe002dfcfb085cf6741eb88c5cfa923a34d21271ec9510659e515bb75ea +size 397805792 diff --git a/Qwen-0.5B-SFT-2.Q4_K_S.gguf b/Qwen-0.5B-SFT-2.Q4_K_S.gguf new file mode 100644 index 0000000..3000e92 --- /dev/null +++ b/Qwen-0.5B-SFT-2.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a34f71e59be10a705802af1493bc7349f195510b0af2f995cbbe01f74c7b5bac +size 385469664 diff --git a/Qwen-0.5B-SFT-2.Q5_K_M.gguf b/Qwen-0.5B-SFT-2.Q5_K_M.gguf new file mode 100644 index 0000000..74b35cc --- /dev/null +++ b/Qwen-0.5B-SFT-2.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e02849c2183ab16e105f75192890057272c02e61ce4bdc534ab1d5160da573b8 +size 420083936 diff --git a/Qwen-0.5B-SFT-2.Q5_K_S.gguf b/Qwen-0.5B-SFT-2.Q5_K_S.gguf new file mode 100644 index 0000000..81e5303 --- /dev/null +++ b/Qwen-0.5B-SFT-2.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:878983245393c9395eed5587aeb0a309e90b54532e4c621d9d578e77e1827607 +size 412708064 diff --git a/Qwen-0.5B-SFT-2.Q6_K.gguf b/Qwen-0.5B-SFT-2.Q6_K.gguf new file mode 100644 index 0000000..369b025 --- /dev/null +++ b/Qwen-0.5B-SFT-2.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:440788a686811a0c8b10b83312313a6b52a10557fac587ffc2e12b76ebe18994 +size 505734368 diff --git a/Qwen-0.5B-SFT-2.Q8_0.gguf b/Qwen-0.5B-SFT-2.Q8_0.gguf new file mode 100644 index 0000000..d49e4d7 --- /dev/null +++ b/Qwen-0.5B-SFT-2.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52edd9eecdb90588e15ff767797f6b594badea1a0722e4eb8a9938e997a2c0ec +size 531066080 diff --git a/Qwen-0.5B-SFT-2.f16.gguf b/Qwen-0.5B-SFT-2.f16.gguf new file mode 100644 index 0000000..caa9cff --- /dev/null +++ b/Qwen-0.5B-SFT-2.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20362413cd97cb5d5f85de3017d7bd3fa7fa836ae4a2ff67d578dfdd2a1791f3 +size 994154720 diff --git a/README.md b/README.md new file mode 100644 index 0000000..0ef8856 --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: Ayush-Singh/Qwen-0.5B-SFT-2 +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- trl +- sft +--- +## About + + + + + + +static quants of https://huggingface.co/Ayush-Singh/Qwen-0.5B-SFT-2 + + +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-0.5B-SFT-2-GGUF/resolve/main/Qwen-0.5B-SFT-2.Q3_K_S.gguf) | Q3_K_S | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-0.5B-SFT-2-GGUF/resolve/main/Qwen-0.5B-SFT-2.Q2_K.gguf) | Q2_K | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-0.5B-SFT-2-GGUF/resolve/main/Qwen-0.5B-SFT-2.IQ4_XS.gguf) | IQ4_XS | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-0.5B-SFT-2-GGUF/resolve/main/Qwen-0.5B-SFT-2.Q3_K_M.gguf) | Q3_K_M | 0.5 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen-0.5B-SFT-2-GGUF/resolve/main/Qwen-0.5B-SFT-2.Q3_K_L.gguf) | Q3_K_L | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-0.5B-SFT-2-GGUF/resolve/main/Qwen-0.5B-SFT-2.Q4_K_S.gguf) | Q4_K_S | 0.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen-0.5B-SFT-2-GGUF/resolve/main/Qwen-0.5B-SFT-2.Q4_K_M.gguf) | Q4_K_M | 0.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen-0.5B-SFT-2-GGUF/resolve/main/Qwen-0.5B-SFT-2.Q5_K_S.gguf) | Q5_K_S | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-0.5B-SFT-2-GGUF/resolve/main/Qwen-0.5B-SFT-2.Q5_K_M.gguf) | Q5_K_M | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-0.5B-SFT-2-GGUF/resolve/main/Qwen-0.5B-SFT-2.Q6_K.gguf) | Q6_K | 0.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen-0.5B-SFT-2-GGUF/resolve/main/Qwen-0.5B-SFT-2.Q8_0.gguf) | Q8_0 | 0.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen-0.5B-SFT-2-GGUF/resolve/main/Qwen-0.5B-SFT-2.f16.gguf) | f16 | 1.1 | 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. + +