commit 5f8b28a779150abf4ec87c44a1aa02a2580a2e9d Author: ModelHub XC Date: Tue Aug 18 23:07:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/small-Qwen2ForCausalLM-2.5-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..719740c --- /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 +small-Qwen2ForCausalLM-2.5.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +small-Qwen2ForCausalLM-2.5.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +small-Qwen2ForCausalLM-2.5.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +small-Qwen2ForCausalLM-2.5.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +small-Qwen2ForCausalLM-2.5.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +small-Qwen2ForCausalLM-2.5.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +small-Qwen2ForCausalLM-2.5.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +small-Qwen2ForCausalLM-2.5.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +small-Qwen2ForCausalLM-2.5.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +small-Qwen2ForCausalLM-2.5.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +small-Qwen2ForCausalLM-2.5.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +small-Qwen2ForCausalLM-2.5.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..844d0f0 --- /dev/null +++ b/README.md @@ -0,0 +1,70 @@ +--- +base_model: trl-internal-testing/small-Qwen2ForCausalLM-2.5 +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- trl +--- +## About + + + + + + +static quants of https://huggingface.co/trl-internal-testing/small-Qwen2ForCausalLM-2.5 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#small-Qwen2ForCausalLM-2.5-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/small-Qwen2ForCausalLM-2.5-i1-GGUF +## 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/small-Qwen2ForCausalLM-2.5-GGUF/resolve/main/small-Qwen2ForCausalLM-2.5.IQ4_XS.gguf) | IQ4_XS | 0.1 | | +| [GGUF](https://huggingface.co/mradermacher/small-Qwen2ForCausalLM-2.5-GGUF/resolve/main/small-Qwen2ForCausalLM-2.5.Q2_K.gguf) | Q2_K | 0.1 | | +| [GGUF](https://huggingface.co/mradermacher/small-Qwen2ForCausalLM-2.5-GGUF/resolve/main/small-Qwen2ForCausalLM-2.5.Q3_K_S.gguf) | Q3_K_S | 0.1 | | +| [GGUF](https://huggingface.co/mradermacher/small-Qwen2ForCausalLM-2.5-GGUF/resolve/main/small-Qwen2ForCausalLM-2.5.Q3_K_M.gguf) | Q3_K_M | 0.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/small-Qwen2ForCausalLM-2.5-GGUF/resolve/main/small-Qwen2ForCausalLM-2.5.Q3_K_L.gguf) | Q3_K_L | 0.1 | | +| [GGUF](https://huggingface.co/mradermacher/small-Qwen2ForCausalLM-2.5-GGUF/resolve/main/small-Qwen2ForCausalLM-2.5.Q4_K_S.gguf) | Q4_K_S | 0.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/small-Qwen2ForCausalLM-2.5-GGUF/resolve/main/small-Qwen2ForCausalLM-2.5.Q4_K_M.gguf) | Q4_K_M | 0.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/small-Qwen2ForCausalLM-2.5-GGUF/resolve/main/small-Qwen2ForCausalLM-2.5.Q5_K_S.gguf) | Q5_K_S | 0.1 | | +| [GGUF](https://huggingface.co/mradermacher/small-Qwen2ForCausalLM-2.5-GGUF/resolve/main/small-Qwen2ForCausalLM-2.5.Q5_K_M.gguf) | Q5_K_M | 0.1 | | +| [GGUF](https://huggingface.co/mradermacher/small-Qwen2ForCausalLM-2.5-GGUF/resolve/main/small-Qwen2ForCausalLM-2.5.Q6_K.gguf) | Q6_K | 0.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/small-Qwen2ForCausalLM-2.5-GGUF/resolve/main/small-Qwen2ForCausalLM-2.5.Q8_0.gguf) | Q8_0 | 0.1 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/small-Qwen2ForCausalLM-2.5-GGUF/resolve/main/small-Qwen2ForCausalLM-2.5.f16.gguf) | f16 | 0.2 | 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. + + diff --git a/small-Qwen2ForCausalLM-2.5.IQ4_XS.gguf b/small-Qwen2ForCausalLM-2.5.IQ4_XS.gguf new file mode 100644 index 0000000..11d59f6 --- /dev/null +++ b/small-Qwen2ForCausalLM-2.5.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17a47e221448f9784201d829f3edc3abff9e7be798e124e205b15eb205200a3e +size 37547072 diff --git a/small-Qwen2ForCausalLM-2.5.Q2_K.gguf b/small-Qwen2ForCausalLM-2.5.Q2_K.gguf new file mode 100644 index 0000000..878a17e --- /dev/null +++ b/small-Qwen2ForCausalLM-2.5.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ce12b8cd69815a09151ea78fe6c7a39c91897deb57852afb9a9bb2c8cc7267f +size 37547072 diff --git a/small-Qwen2ForCausalLM-2.5.Q3_K_L.gguf b/small-Qwen2ForCausalLM-2.5.Q3_K_L.gguf new file mode 100644 index 0000000..d87a001 --- /dev/null +++ b/small-Qwen2ForCausalLM-2.5.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b45d3b83e5615219e95d771167cea432b3c632b10e51ce06a0b98494130d43b9 +size 37557824 diff --git a/small-Qwen2ForCausalLM-2.5.Q3_K_M.gguf b/small-Qwen2ForCausalLM-2.5.Q3_K_M.gguf new file mode 100644 index 0000000..ac00134 --- /dev/null +++ b/small-Qwen2ForCausalLM-2.5.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d0a0d9d0d648a338516acf1530143af10637b8f7dfc7401a2452bac4bf4d311 +size 37555264 diff --git a/small-Qwen2ForCausalLM-2.5.Q3_K_S.gguf b/small-Qwen2ForCausalLM-2.5.Q3_K_S.gguf new file mode 100644 index 0000000..7fd2f3a --- /dev/null +++ b/small-Qwen2ForCausalLM-2.5.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4cd3a1d7f3ca6edbcd3bc509d137b3622519050e179812da625c687ad18cfdac +size 37547072 diff --git a/small-Qwen2ForCausalLM-2.5.Q4_K_M.gguf b/small-Qwen2ForCausalLM-2.5.Q4_K_M.gguf new file mode 100644 index 0000000..8a81d92 --- /dev/null +++ b/small-Qwen2ForCausalLM-2.5.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4654ed76c7a27b1fd73e2f769539d600b3ad4f10c45ff296389d0f98d29af361 +size 39993664 diff --git a/small-Qwen2ForCausalLM-2.5.Q4_K_S.gguf b/small-Qwen2ForCausalLM-2.5.Q4_K_S.gguf new file mode 100644 index 0000000..4ee2a0a --- /dev/null +++ b/small-Qwen2ForCausalLM-2.5.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d30d646fda650a40710c3deeba67f7ecb2226f8cdfdd990fe7744f534d1d12d3 +size 39990080 diff --git a/small-Qwen2ForCausalLM-2.5.Q5_K_M.gguf b/small-Qwen2ForCausalLM-2.5.Q5_K_M.gguf new file mode 100644 index 0000000..ba2140a --- /dev/null +++ b/small-Qwen2ForCausalLM-2.5.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e786e92f912af3d659eea2a5bdc2b39bb2258bfccc8a1fa743a615127516932b +size 41213888 diff --git a/small-Qwen2ForCausalLM-2.5.Q5_K_S.gguf b/small-Qwen2ForCausalLM-2.5.Q5_K_S.gguf new file mode 100644 index 0000000..b8ce53d --- /dev/null +++ b/small-Qwen2ForCausalLM-2.5.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b465637566459e3148d4bf6b1f4f7ce0d7b79db840e09c5e5a81aa5c3d93d26 +size 41210048 diff --git a/small-Qwen2ForCausalLM-2.5.Q6_K.gguf b/small-Qwen2ForCausalLM-2.5.Q6_K.gguf new file mode 100644 index 0000000..f631cd4 --- /dev/null +++ b/small-Qwen2ForCausalLM-2.5.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7a77dc20de2e3c3b20e23de87fab516eafb7f6af1a2202fdc9feab8e2a4c84f +size 47315072 diff --git a/small-Qwen2ForCausalLM-2.5.Q8_0.gguf b/small-Qwen2ForCausalLM-2.5.Q8_0.gguf new file mode 100644 index 0000000..94a78ff --- /dev/null +++ b/small-Qwen2ForCausalLM-2.5.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59fef460ac9093d999c8cddc985f4f75d4b50df2589646bc2e4fb6dc1062f76e +size 47315072 diff --git a/small-Qwen2ForCausalLM-2.5.f16.gguf b/small-Qwen2ForCausalLM-2.5.f16.gguf new file mode 100644 index 0000000..2f58945 --- /dev/null +++ b/small-Qwen2ForCausalLM-2.5.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0fae807f52c2156b745ce38761fce609ebd87a3ce9b510702bda205af9632423 +size 83829824