commit 56e265894a1a77b6f9fc82384f9dd9846c4b1fdc Author: ModelHub XC Date: Thu Jul 16 16:28:08 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen2-0.2B-pt-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..d0af7cc --- /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 +Qwen2-0.2B-pt.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-0.2B-pt.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-0.2B-pt.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-0.2B-pt.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-0.2B-pt.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-0.2B-pt.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-0.2B-pt.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-0.2B-pt.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-0.2B-pt.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-0.2B-pt.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-0.2B-pt.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-0.2B-pt.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2-0.2B-pt.IQ4_XS.gguf b/Qwen2-0.2B-pt.IQ4_XS.gguf new file mode 100644 index 0000000..07d8b30 --- /dev/null +++ b/Qwen2-0.2B-pt.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd0ab580ea5e0e26cf0dbd851ccac5415dbcaac86816282ba1d01d9cbf0eca7e +size 124906976 diff --git a/Qwen2-0.2B-pt.Q2_K.gguf b/Qwen2-0.2B-pt.Q2_K.gguf new file mode 100644 index 0000000..66c982b --- /dev/null +++ b/Qwen2-0.2B-pt.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06b4e5d9d2c4456450ca417459ae2843c726e31a859d6d9c72a21320245cf34d +size 105405920 diff --git a/Qwen2-0.2B-pt.Q3_K_L.gguf b/Qwen2-0.2B-pt.Q3_K_L.gguf new file mode 100644 index 0000000..83efde7 --- /dev/null +++ b/Qwen2-0.2B-pt.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c00a6fafdfcd420bdf5afaff5791cb83e026604a0f4b20c83868938f0c99d257 +size 117015520 diff --git a/Qwen2-0.2B-pt.Q3_K_M.gguf b/Qwen2-0.2B-pt.Q3_K_M.gguf new file mode 100644 index 0000000..f2427dd --- /dev/null +++ b/Qwen2-0.2B-pt.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a40afb95147bf838d189672307b10c9d96ecebbb2c39067dfec8a5e9d3096ad3 +size 116204512 diff --git a/Qwen2-0.2B-pt.Q3_K_S.gguf b/Qwen2-0.2B-pt.Q3_K_S.gguf new file mode 100644 index 0000000..9abf0ca --- /dev/null +++ b/Qwen2-0.2B-pt.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19b1c29b4364720d0da316efa5acf91b59adb1b4fd42a38b0634a6c8e5d5fabe +size 114877408 diff --git a/Qwen2-0.2B-pt.Q4_K_M.gguf b/Qwen2-0.2B-pt.Q4_K_M.gguf new file mode 100644 index 0000000..42b4946 --- /dev/null +++ b/Qwen2-0.2B-pt.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:524d6ec43783df09856fbf4eafea6303b8abe00755a0ddcab412c297daa09689 +size 129851872 diff --git a/Qwen2-0.2B-pt.Q4_K_S.gguf b/Qwen2-0.2B-pt.Q4_K_S.gguf new file mode 100644 index 0000000..42815e1 --- /dev/null +++ b/Qwen2-0.2B-pt.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec936bdedddf4bee36d2546e226d70b29c63afa8de581581ec3c724cc1a69dac +size 128699872 diff --git a/Qwen2-0.2B-pt.Q5_K_M.gguf b/Qwen2-0.2B-pt.Q5_K_M.gguf new file mode 100644 index 0000000..5ba4202 --- /dev/null +++ b/Qwen2-0.2B-pt.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8df1aa4f7e577b8cc45f0918751601613605c2f69f7dcb23f11ecad911fbd3b5 +size 142078432 diff --git a/Qwen2-0.2B-pt.Q5_K_S.gguf b/Qwen2-0.2B-pt.Q5_K_S.gguf new file mode 100644 index 0000000..092eb4e --- /dev/null +++ b/Qwen2-0.2B-pt.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c5b624a284d87d714578cf37a8d832380ef6e81835395c52b5cd7ea1a5d6c60 +size 141058528 diff --git a/Qwen2-0.2B-pt.Q6_K.gguf b/Qwen2-0.2B-pt.Q6_K.gguf new file mode 100644 index 0000000..a4fe915 --- /dev/null +++ b/Qwen2-0.2B-pt.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2a9508cd1b70b1af951ab8a13d6146ddbbb44c51b546ea106d86150a0d00cd9 +size 155762656 diff --git a/Qwen2-0.2B-pt.Q8_0.gguf b/Qwen2-0.2B-pt.Q8_0.gguf new file mode 100644 index 0000000..e6b44ed --- /dev/null +++ b/Qwen2-0.2B-pt.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1bad2d2910532373667c0ba3709bbc82dac773f58f990ae2f9b198594099c5c4 +size 198204384 diff --git a/Qwen2-0.2B-pt.f16.gguf b/Qwen2-0.2B-pt.f16.gguf new file mode 100644 index 0000000..acb64a7 --- /dev/null +++ b/Qwen2-0.2B-pt.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6cb14c0d636acdf2cfc9e72bbe936df4a2cf497896f373d89690d414dc065f9b +size 367778784 diff --git a/README.md b/README.md new file mode 100644 index 0000000..257878a --- /dev/null +++ b/README.md @@ -0,0 +1,79 @@ +--- +base_model: FlameF0X/Qwen2-0.2B-pt +datasets: +- Salesforce/wikitext +- roneneldan/TinyStories +- FlameF0X/arXiv-AI-ML +- Skylion007/openwebtext +- flytech/python-codes-25k +- bookcorpus/bookcorpus +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/FlameF0X/Qwen2-0.2B-pt + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen2-0.2B-pt-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/Qwen2-0.2B-pt-GGUF/resolve/main/Qwen2-0.2B-pt.Q2_K.gguf) | Q2_K | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-0.2B-pt-GGUF/resolve/main/Qwen2-0.2B-pt.Q3_K_S.gguf) | Q3_K_S | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-0.2B-pt-GGUF/resolve/main/Qwen2-0.2B-pt.Q3_K_M.gguf) | Q3_K_M | 0.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-0.2B-pt-GGUF/resolve/main/Qwen2-0.2B-pt.Q3_K_L.gguf) | Q3_K_L | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-0.2B-pt-GGUF/resolve/main/Qwen2-0.2B-pt.IQ4_XS.gguf) | IQ4_XS | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-0.2B-pt-GGUF/resolve/main/Qwen2-0.2B-pt.Q4_K_S.gguf) | Q4_K_S | 0.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-0.2B-pt-GGUF/resolve/main/Qwen2-0.2B-pt.Q4_K_M.gguf) | Q4_K_M | 0.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-0.2B-pt-GGUF/resolve/main/Qwen2-0.2B-pt.Q5_K_S.gguf) | Q5_K_S | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-0.2B-pt-GGUF/resolve/main/Qwen2-0.2B-pt.Q5_K_M.gguf) | Q5_K_M | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-0.2B-pt-GGUF/resolve/main/Qwen2-0.2B-pt.Q6_K.gguf) | Q6_K | 0.3 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-0.2B-pt-GGUF/resolve/main/Qwen2-0.2B-pt.Q8_0.gguf) | Q8_0 | 0.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-0.2B-pt-GGUF/resolve/main/Qwen2-0.2B-pt.f16.gguf) | f16 | 0.5 | 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. + +