commit 8cfa0f594d11dcf46ba2cdd19b457062e8857f6d Author: ModelHub XC Date: Mon May 4 18:30:13 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/PhishMe-Qwen3-8B-SFT-v2-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..8edc5d0 --- /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 +PhishMe-Qwen3-8B-SFT-v2.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +PhishMe-Qwen3-8B-SFT-v2.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +PhishMe-Qwen3-8B-SFT-v2.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +PhishMe-Qwen3-8B-SFT-v2.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +PhishMe-Qwen3-8B-SFT-v2.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +PhishMe-Qwen3-8B-SFT-v2.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +PhishMe-Qwen3-8B-SFT-v2.f16.gguf filter=lfs diff=lfs merge=lfs -text +PhishMe-Qwen3-8B-SFT-v2.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +PhishMe-Qwen3-8B-SFT-v2.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +PhishMe-Qwen3-8B-SFT-v2.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +PhishMe-Qwen3-8B-SFT-v2.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +PhishMe-Qwen3-8B-SFT-v2.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/PhishMe-Qwen3-8B-SFT-v2.IQ4_XS.gguf b/PhishMe-Qwen3-8B-SFT-v2.IQ4_XS.gguf new file mode 100644 index 0000000..5916177 --- /dev/null +++ b/PhishMe-Qwen3-8B-SFT-v2.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d0befa57c1c56b27dfffb95ecba0becdcaa1cdc860c91589d19bdaa60c08aab +size 4593297760 diff --git a/PhishMe-Qwen3-8B-SFT-v2.Q2_K.gguf b/PhishMe-Qwen3-8B-SFT-v2.Q2_K.gguf new file mode 100644 index 0000000..c8d4df3 --- /dev/null +++ b/PhishMe-Qwen3-8B-SFT-v2.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e1c3b3b9358b898860e184a08dbfb320c5b0b413c82027c7d082f169529e15f +size 3281733984 diff --git a/PhishMe-Qwen3-8B-SFT-v2.Q3_K_L.gguf b/PhishMe-Qwen3-8B-SFT-v2.Q3_K_L.gguf new file mode 100644 index 0000000..20bb987 --- /dev/null +++ b/PhishMe-Qwen3-8B-SFT-v2.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3fa5a531dd0d77f4c1542dd3408fe1b5cf9e17533ec1fa2dc3ef80ac64e9b3f +size 4431395168 diff --git a/PhishMe-Qwen3-8B-SFT-v2.Q3_K_M.gguf b/PhishMe-Qwen3-8B-SFT-v2.Q3_K_M.gguf new file mode 100644 index 0000000..a1add7b --- /dev/null +++ b/PhishMe-Qwen3-8B-SFT-v2.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72769fb2de8c13eee8cfb84e0d313fd38d27b9bf3aa743f6699066fd37df08cb +size 4124162400 diff --git a/PhishMe-Qwen3-8B-SFT-v2.Q3_K_S.gguf b/PhishMe-Qwen3-8B-SFT-v2.Q3_K_S.gguf new file mode 100644 index 0000000..ba5cd1a --- /dev/null +++ b/PhishMe-Qwen3-8B-SFT-v2.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ade5e6dea93eabe969e94e4e83fbc757f2465ad9af42456c8a0b3772f4b1b54 +size 3769612640 diff --git a/PhishMe-Qwen3-8B-SFT-v2.Q4_K_M.gguf b/PhishMe-Qwen3-8B-SFT-v2.Q4_K_M.gguf new file mode 100644 index 0000000..02c25dd --- /dev/null +++ b/PhishMe-Qwen3-8B-SFT-v2.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e077ea51ae0dca60712ca5ce4883eb0c391a136d96beaf33f41873ebc82ec67f +size 5027785056 diff --git a/PhishMe-Qwen3-8B-SFT-v2.Q4_K_S.gguf b/PhishMe-Qwen3-8B-SFT-v2.Q4_K_S.gguf new file mode 100644 index 0000000..94bf605 --- /dev/null +++ b/PhishMe-Qwen3-8B-SFT-v2.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e9b64513df8301774ca6539bbcd27900b5bfa9dc13ae4f559cc1dd529942fee +size 4802013536 diff --git a/PhishMe-Qwen3-8B-SFT-v2.Q5_K_M.gguf b/PhishMe-Qwen3-8B-SFT-v2.Q5_K_M.gguf new file mode 100644 index 0000000..32bebb1 --- /dev/null +++ b/PhishMe-Qwen3-8B-SFT-v2.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3f1f12779360c6650419766483bd4690f3ff6009454fc36a878b58aa7b49509 +size 5851113824 diff --git a/PhishMe-Qwen3-8B-SFT-v2.Q5_K_S.gguf b/PhishMe-Qwen3-8B-SFT-v2.Q5_K_S.gguf new file mode 100644 index 0000000..fa6606d --- /dev/null +++ b/PhishMe-Qwen3-8B-SFT-v2.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c81301f481d3d8ae57a5775118c01d52df8e419eac7d47c0c21c79383da70310 +size 5720762720 diff --git a/PhishMe-Qwen3-8B-SFT-v2.Q6_K.gguf b/PhishMe-Qwen3-8B-SFT-v2.Q6_K.gguf new file mode 100644 index 0000000..4230e66 --- /dev/null +++ b/PhishMe-Qwen3-8B-SFT-v2.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca00ed68bc9910081ab5efa6b21f3ba2b61bffda071bbc8d751ae9e457a6774c +size 6725900640 diff --git a/PhishMe-Qwen3-8B-SFT-v2.Q8_0.gguf b/PhishMe-Qwen3-8B-SFT-v2.Q8_0.gguf new file mode 100644 index 0000000..0b2fffd --- /dev/null +++ b/PhishMe-Qwen3-8B-SFT-v2.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa59c9b06b567597bad33add8f97d83145c7dc1191718bb1c390037095e66dea +size 8709519712 diff --git a/PhishMe-Qwen3-8B-SFT-v2.f16.gguf b/PhishMe-Qwen3-8B-SFT-v2.f16.gguf new file mode 100644 index 0000000..8b3f0ea --- /dev/null +++ b/PhishMe-Qwen3-8B-SFT-v2.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53a0e15a1e2101a50b154333129439344cc26cd5b2a9f0a2246ee5b314d6b405 +size 16388045152 diff --git a/README.md b/README.md new file mode 100644 index 0000000..14e485b --- /dev/null +++ b/README.md @@ -0,0 +1,74 @@ +--- +base_model: piyawudk/PhishMe-Qwen3-8B-SFT-v2 +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- qwen3 +--- +## About + + + + + + +static quants of https://huggingface.co/piyawudk/PhishMe-Qwen3-8B-SFT-v2 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#PhishMe-Qwen3-8B-SFT-v2-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/PhishMe-Qwen3-8B-SFT-v2-GGUF/resolve/main/PhishMe-Qwen3-8B-SFT-v2.Q2_K.gguf) | Q2_K | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/PhishMe-Qwen3-8B-SFT-v2-GGUF/resolve/main/PhishMe-Qwen3-8B-SFT-v2.Q3_K_S.gguf) | Q3_K_S | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/PhishMe-Qwen3-8B-SFT-v2-GGUF/resolve/main/PhishMe-Qwen3-8B-SFT-v2.Q3_K_M.gguf) | Q3_K_M | 4.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/PhishMe-Qwen3-8B-SFT-v2-GGUF/resolve/main/PhishMe-Qwen3-8B-SFT-v2.Q3_K_L.gguf) | Q3_K_L | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/PhishMe-Qwen3-8B-SFT-v2-GGUF/resolve/main/PhishMe-Qwen3-8B-SFT-v2.IQ4_XS.gguf) | IQ4_XS | 4.7 | | +| [GGUF](https://huggingface.co/mradermacher/PhishMe-Qwen3-8B-SFT-v2-GGUF/resolve/main/PhishMe-Qwen3-8B-SFT-v2.Q4_K_S.gguf) | Q4_K_S | 4.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/PhishMe-Qwen3-8B-SFT-v2-GGUF/resolve/main/PhishMe-Qwen3-8B-SFT-v2.Q4_K_M.gguf) | Q4_K_M | 5.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/PhishMe-Qwen3-8B-SFT-v2-GGUF/resolve/main/PhishMe-Qwen3-8B-SFT-v2.Q5_K_S.gguf) | Q5_K_S | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/PhishMe-Qwen3-8B-SFT-v2-GGUF/resolve/main/PhishMe-Qwen3-8B-SFT-v2.Q5_K_M.gguf) | Q5_K_M | 6.0 | | +| [GGUF](https://huggingface.co/mradermacher/PhishMe-Qwen3-8B-SFT-v2-GGUF/resolve/main/PhishMe-Qwen3-8B-SFT-v2.Q6_K.gguf) | Q6_K | 6.8 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/PhishMe-Qwen3-8B-SFT-v2-GGUF/resolve/main/PhishMe-Qwen3-8B-SFT-v2.Q8_0.gguf) | Q8_0 | 8.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/PhishMe-Qwen3-8B-SFT-v2-GGUF/resolve/main/PhishMe-Qwen3-8B-SFT-v2.f16.gguf) | f16 | 16.5 | 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. + +