commit 891fba58fad159018ab1e445bbfd7be9b1abc2c7 Author: ModelHub XC Date: Sat Apr 11 23:17:00 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen3-0.6B-Prompt-Gen-v0.1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..1380430 --- /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 +Qwen3-0.6B-Prompt-Gen-v0.1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Prompt-Gen-v0.1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Prompt-Gen-v0.1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Prompt-Gen-v0.1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Prompt-Gen-v0.1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Prompt-Gen-v0.1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Prompt-Gen-v0.1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Prompt-Gen-v0.1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Prompt-Gen-v0.1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Prompt-Gen-v0.1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Prompt-Gen-v0.1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Prompt-Gen-v0.1.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-0.6B-Prompt-Gen-v0.1.IQ4_XS.gguf b/Qwen3-0.6B-Prompt-Gen-v0.1.IQ4_XS.gguf new file mode 100644 index 0000000..25dcad9 --- /dev/null +++ b/Qwen3-0.6B-Prompt-Gen-v0.1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c05246d9ae40d1f9a31f596739e411eab777ac1e2126212125142e73bbc55b5 +size 369274912 diff --git a/Qwen3-0.6B-Prompt-Gen-v0.1.Q2_K.gguf b/Qwen3-0.6B-Prompt-Gen-v0.1.Q2_K.gguf new file mode 100644 index 0000000..bb9d935 --- /dev/null +++ b/Qwen3-0.6B-Prompt-Gen-v0.1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:315555807e2c5f05da1d712da4a4487ae1cd1387aa450cb882a45b2a02940a42 +size 296235040 diff --git a/Qwen3-0.6B-Prompt-Gen-v0.1.Q3_K_L.gguf b/Qwen3-0.6B-Prompt-Gen-v0.1.Q3_K_L.gguf new file mode 100644 index 0000000..3421aff --- /dev/null +++ b/Qwen3-0.6B-Prompt-Gen-v0.1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7943222f058bda1e2e13b2cd8c7320da7b5d48f328fe3f823eefaadc8fd8d4f2 +size 368488480 diff --git a/Qwen3-0.6B-Prompt-Gen-v0.1.Q3_K_M.gguf b/Qwen3-0.6B-Prompt-Gen-v0.1.Q3_K_M.gguf new file mode 100644 index 0000000..d21f7d3 --- /dev/null +++ b/Qwen3-0.6B-Prompt-Gen-v0.1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df1c2649fc3769d66d83b07d6735b38332bb8d8b5fcb45f42830e34a4926e858 +size 347123744 diff --git a/Qwen3-0.6B-Prompt-Gen-v0.1.Q3_K_S.gguf b/Qwen3-0.6B-Prompt-Gen-v0.1.Q3_K_S.gguf new file mode 100644 index 0000000..ff4be5f --- /dev/null +++ b/Qwen3-0.6B-Prompt-Gen-v0.1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1259ddfbd61d4b1abc013e3e485b4f05de3ae55cf191808790aa5d7afae1fc3 +size 323072032 diff --git a/Qwen3-0.6B-Prompt-Gen-v0.1.Q4_K_M.gguf b/Qwen3-0.6B-Prompt-Gen-v0.1.Q4_K_M.gguf new file mode 100644 index 0000000..8727f31 --- /dev/null +++ b/Qwen3-0.6B-Prompt-Gen-v0.1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:237b083b0f5a4a31ecad0a52ce996db2cc3926257b6fea8e00460b351c1cba62 +size 396701728 diff --git a/Qwen3-0.6B-Prompt-Gen-v0.1.Q4_K_S.gguf b/Qwen3-0.6B-Prompt-Gen-v0.1.Q4_K_S.gguf new file mode 100644 index 0000000..ffe209b --- /dev/null +++ b/Qwen3-0.6B-Prompt-Gen-v0.1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ab14010f2289419171d72cf4302e3c98269d16e4633a57ab50b8c827021fca1 +size 383266848 diff --git a/Qwen3-0.6B-Prompt-Gen-v0.1.Q5_K_M.gguf b/Qwen3-0.6B-Prompt-Gen-v0.1.Q5_K_M.gguf new file mode 100644 index 0000000..9c7d0ac --- /dev/null +++ b/Qwen3-0.6B-Prompt-Gen-v0.1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50b93d59596e3adfbe12d402307ddbfe7348b6c38bfc9bd676d7a5ddd777dddd +size 444411936 diff --git a/Qwen3-0.6B-Prompt-Gen-v0.1.Q5_K_S.gguf b/Qwen3-0.6B-Prompt-Gen-v0.1.Q5_K_S.gguf new file mode 100644 index 0000000..13d9c9c --- /dev/null +++ b/Qwen3-0.6B-Prompt-Gen-v0.1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8973575791a59648a605010d802cca40c9c3f9b934864e333aa3d1b2b2a70249 +size 436613152 diff --git a/Qwen3-0.6B-Prompt-Gen-v0.1.Q6_K.gguf b/Qwen3-0.6B-Prompt-Gen-v0.1.Q6_K.gguf new file mode 100644 index 0000000..5f0a1ec --- /dev/null +++ b/Qwen3-0.6B-Prompt-Gen-v0.1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cce492e8992981ab7292807e5e7085ffc0ecbae30fc370817cdcff805a2c46c3 +size 495104032 diff --git a/Qwen3-0.6B-Prompt-Gen-v0.1.Q8_0.gguf b/Qwen3-0.6B-Prompt-Gen-v0.1.Q8_0.gguf new file mode 100644 index 0000000..a3648bf --- /dev/null +++ b/Qwen3-0.6B-Prompt-Gen-v0.1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6103133ee62389759e0a597f62f609f07bbc281eb540658ef7c40579377cb69d +size 639444000 diff --git a/Qwen3-0.6B-Prompt-Gen-v0.1.f16.gguf b/Qwen3-0.6B-Prompt-Gen-v0.1.f16.gguf new file mode 100644 index 0000000..6a56719 --- /dev/null +++ b/Qwen3-0.6B-Prompt-Gen-v0.1.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4897941d1bed8b4dbad667ce5dc16e39a292009425063990163f456501c8294f +size 1198179360 diff --git a/README.md b/README.md new file mode 100644 index 0000000..b9a02d5 --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: SakikoLab/Qwen3-0.6B-Prompt-Gen-v0.1 +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/SakikoLab/Qwen3-0.6B-Prompt-Gen-v0.1 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-0.6B-Prompt-Gen-v0.1-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Qwen3-0.6B-Prompt-Gen-v0.1-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/Qwen3-0.6B-Prompt-Gen-v0.1-GGUF/resolve/main/Qwen3-0.6B-Prompt-Gen-v0.1.Q2_K.gguf) | Q2_K | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Prompt-Gen-v0.1-GGUF/resolve/main/Qwen3-0.6B-Prompt-Gen-v0.1.Q3_K_S.gguf) | Q3_K_S | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Prompt-Gen-v0.1-GGUF/resolve/main/Qwen3-0.6B-Prompt-Gen-v0.1.Q3_K_M.gguf) | Q3_K_M | 0.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Prompt-Gen-v0.1-GGUF/resolve/main/Qwen3-0.6B-Prompt-Gen-v0.1.Q3_K_L.gguf) | Q3_K_L | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Prompt-Gen-v0.1-GGUF/resolve/main/Qwen3-0.6B-Prompt-Gen-v0.1.IQ4_XS.gguf) | IQ4_XS | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Prompt-Gen-v0.1-GGUF/resolve/main/Qwen3-0.6B-Prompt-Gen-v0.1.Q4_K_S.gguf) | Q4_K_S | 0.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Prompt-Gen-v0.1-GGUF/resolve/main/Qwen3-0.6B-Prompt-Gen-v0.1.Q4_K_M.gguf) | Q4_K_M | 0.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Prompt-Gen-v0.1-GGUF/resolve/main/Qwen3-0.6B-Prompt-Gen-v0.1.Q5_K_S.gguf) | Q5_K_S | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Prompt-Gen-v0.1-GGUF/resolve/main/Qwen3-0.6B-Prompt-Gen-v0.1.Q5_K_M.gguf) | Q5_K_M | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Prompt-Gen-v0.1-GGUF/resolve/main/Qwen3-0.6B-Prompt-Gen-v0.1.Q6_K.gguf) | Q6_K | 0.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Prompt-Gen-v0.1-GGUF/resolve/main/Qwen3-0.6B-Prompt-Gen-v0.1.Q8_0.gguf) | Q8_0 | 0.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Prompt-Gen-v0.1-GGUF/resolve/main/Qwen3-0.6B-Prompt-Gen-v0.1.f16.gguf) | f16 | 1.3 | 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. + +