commit 9ed392d32adc905fb9cc82497d447b34654c8f71 Author: ModelHub XC Date: Sun May 31 10:44:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen3-ST-The-Next-Generation-II-v1-256k-ctx-6B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..489e28e --- /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-ST-The-Next-Generation-II-v1-256k-ctx-6B.f16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-ST-The-Next-Generation-II-v1-256k-ctx-6B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-ST-The-Next-Generation-II-v1-256k-ctx-6B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-ST-The-Next-Generation-II-v1-256k-ctx-6B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-ST-The-Next-Generation-II-v1-256k-ctx-6B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-ST-The-Next-Generation-II-v1-256k-ctx-6B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-ST-The-Next-Generation-II-v1-256k-ctx-6B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-ST-The-Next-Generation-II-v1-256k-ctx-6B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-ST-The-Next-Generation-II-v1-256k-ctx-6B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-ST-The-Next-Generation-II-v1-256k-ctx-6B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-ST-The-Next-Generation-II-v1-256k-ctx-6B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-ST-The-Next-Generation-II-v1-256k-ctx-6B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-ST-The-Next-Generation-II-v1-256k-ctx-6B.IQ4_XS.gguf b/Qwen3-ST-The-Next-Generation-II-v1-256k-ctx-6B.IQ4_XS.gguf new file mode 100644 index 0000000..83b4225 --- /dev/null +++ b/Qwen3-ST-The-Next-Generation-II-v1-256k-ctx-6B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ae91b7c259fa06a99119f6de4993ef508eb088dddfba9d37d211ecd8dfc7964 +size 3527653024 diff --git a/Qwen3-ST-The-Next-Generation-II-v1-256k-ctx-6B.Q2_K.gguf b/Qwen3-ST-The-Next-Generation-II-v1-256k-ctx-6B.Q2_K.gguf new file mode 100644 index 0000000..0b199d1 --- /dev/null +++ b/Qwen3-ST-The-Next-Generation-II-v1-256k-ctx-6B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d136bfd52fbde2f7da823d4b7dca57a1d491568237780daae544965a1f8b175a +size 2506719904 diff --git a/Qwen3-ST-The-Next-Generation-II-v1-256k-ctx-6B.Q3_K_L.gguf b/Qwen3-ST-The-Next-Generation-II-v1-256k-ctx-6B.Q3_K_L.gguf new file mode 100644 index 0000000..75d9984 --- /dev/null +++ b/Qwen3-ST-The-Next-Generation-II-v1-256k-ctx-6B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9dac8ded1620db24b128b33a0c657a870e6b6e8648075a6c9fffbc8eb5cd7a54 +size 3417493664 diff --git a/Qwen3-ST-The-Next-Generation-II-v1-256k-ctx-6B.Q3_K_M.gguf b/Qwen3-ST-The-Next-Generation-II-v1-256k-ctx-6B.Q3_K_M.gguf new file mode 100644 index 0000000..5c8874d --- /dev/null +++ b/Qwen3-ST-The-Next-Generation-II-v1-256k-ctx-6B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c807e4151b45fd6b87f2d1668c9f67089b1aea33e64654cebfd230dd96999037 +size 3166163104 diff --git a/Qwen3-ST-The-Next-Generation-II-v1-256k-ctx-6B.Q3_K_S.gguf b/Qwen3-ST-The-Next-Generation-II-v1-256k-ctx-6B.Q3_K_S.gguf new file mode 100644 index 0000000..eed988a --- /dev/null +++ b/Qwen3-ST-The-Next-Generation-II-v1-256k-ctx-6B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1defb759ebddbf203fdd27f59e1f544728e904ab070c0215a9b2ea5d168f0da2 +size 2878511264 diff --git a/Qwen3-ST-The-Next-Generation-II-v1-256k-ctx-6B.Q4_K_M.gguf b/Qwen3-ST-The-Next-Generation-II-v1-256k-ctx-6B.Q4_K_M.gguf new file mode 100644 index 0000000..50b3cbf --- /dev/null +++ b/Qwen3-ST-The-Next-Generation-II-v1-256k-ctx-6B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e011fb2b293dab9b9fa34c517bf63208b2510cd4549a1347ce719aac53a89924 +size 3858998944 diff --git a/Qwen3-ST-The-Next-Generation-II-v1-256k-ctx-6B.Q4_K_S.gguf b/Qwen3-ST-The-Next-Generation-II-v1-256k-ctx-6B.Q4_K_S.gguf new file mode 100644 index 0000000..f0d3b76 --- /dev/null +++ b/Qwen3-ST-The-Next-Generation-II-v1-256k-ctx-6B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c4f4618608c07dfa8ea599908a959bb6987250689c6beff6b49882e564d28ac +size 3687386784 diff --git a/Qwen3-ST-The-Next-Generation-II-v1-256k-ctx-6B.Q5_K_M.gguf b/Qwen3-ST-The-Next-Generation-II-v1-256k-ctx-6B.Q5_K_M.gguf new file mode 100644 index 0000000..c6cb417 --- /dev/null +++ b/Qwen3-ST-The-Next-Generation-II-v1-256k-ctx-6B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d36a8a425071a0a57dc23ace5505244c1a98fe8716258623bb753b31d0e4b611 +size 4508583584 diff --git a/Qwen3-ST-The-Next-Generation-II-v1-256k-ctx-6B.Q5_K_S.gguf b/Qwen3-ST-The-Next-Generation-II-v1-256k-ctx-6B.Q5_K_S.gguf new file mode 100644 index 0000000..c18e6c5 --- /dev/null +++ b/Qwen3-ST-The-Next-Generation-II-v1-256k-ctx-6B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5393f80f21ff69d5bf6ba3e5c6620d46bccf8f758e2336e5ebe5e901a0c34a1c +size 4409880224 diff --git a/Qwen3-ST-The-Next-Generation-II-v1-256k-ctx-6B.Q6_K.gguf b/Qwen3-ST-The-Next-Generation-II-v1-256k-ctx-6B.Q6_K.gguf new file mode 100644 index 0000000..6e36d86 --- /dev/null +++ b/Qwen3-ST-The-Next-Generation-II-v1-256k-ctx-6B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96648f7112a7f9630be59084be1fee377b7c3eceadb1be2408cd60158664c60f +size 5198767264 diff --git a/Qwen3-ST-The-Next-Generation-II-v1-256k-ctx-6B.Q8_0.gguf b/Qwen3-ST-The-Next-Generation-II-v1-256k-ctx-6B.Q8_0.gguf new file mode 100644 index 0000000..c44ac02 --- /dev/null +++ b/Qwen3-ST-The-Next-Generation-II-v1-256k-ctx-6B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:062bbd9aea6ab2b282bac9d8089adc0e6e60a0b2f598f1e076e5ae4606ead784 +size 6731526304 diff --git a/Qwen3-ST-The-Next-Generation-II-v1-256k-ctx-6B.f16.gguf b/Qwen3-ST-The-Next-Generation-II-v1-256k-ctx-6B.f16.gguf new file mode 100644 index 0000000..c1bfe6c --- /dev/null +++ b/Qwen3-ST-The-Next-Generation-II-v1-256k-ctx-6B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f7b4c26edc766d8f0a67c9beb7073a5aabfbf5c899e94885be569b82ad1e199 +size 12664787104 diff --git a/README.md b/README.md new file mode 100644 index 0000000..5c5424c --- /dev/null +++ b/README.md @@ -0,0 +1,100 @@ +--- +base_model: DavidAU/Qwen3-ST-The-Next-Generation-II-v1-256k-ctx-6B +datasets: +- progs2002/star-trek-tng-scripts +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- programming +- code generation +- code +- coding +- coder +- chat +- code +- chat +- brainstorm +- qwen +- qwen3 +- qwencoder +- brainstorm 20x +- creative +- all uses cases +- Jan-V1 +- float32 +- horror +- science fiction +- fantasy +- Star Trek +- finetune +- thinking +- reasoning +- unsloth +--- +## About + + + + + + + + + +static quants of https://huggingface.co/DavidAU/Qwen3-ST-The-Next-Generation-II-v1-256k-ctx-6B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-ST-The-Next-Generation-II-v1-256k-ctx-6B-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Qwen3-ST-The-Next-Generation-II-v1-256k-ctx-6B-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-ST-The-Next-Generation-II-v1-256k-ctx-6B-GGUF/resolve/main/Qwen3-ST-The-Next-Generation-II-v1-256k-ctx-6B.Q2_K.gguf) | Q2_K | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-ST-The-Next-Generation-II-v1-256k-ctx-6B-GGUF/resolve/main/Qwen3-ST-The-Next-Generation-II-v1-256k-ctx-6B.Q3_K_S.gguf) | Q3_K_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-ST-The-Next-Generation-II-v1-256k-ctx-6B-GGUF/resolve/main/Qwen3-ST-The-Next-Generation-II-v1-256k-ctx-6B.Q3_K_M.gguf) | Q3_K_M | 3.3 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-ST-The-Next-Generation-II-v1-256k-ctx-6B-GGUF/resolve/main/Qwen3-ST-The-Next-Generation-II-v1-256k-ctx-6B.Q3_K_L.gguf) | Q3_K_L | 3.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-ST-The-Next-Generation-II-v1-256k-ctx-6B-GGUF/resolve/main/Qwen3-ST-The-Next-Generation-II-v1-256k-ctx-6B.IQ4_XS.gguf) | IQ4_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-ST-The-Next-Generation-II-v1-256k-ctx-6B-GGUF/resolve/main/Qwen3-ST-The-Next-Generation-II-v1-256k-ctx-6B.Q4_K_S.gguf) | Q4_K_S | 3.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-ST-The-Next-Generation-II-v1-256k-ctx-6B-GGUF/resolve/main/Qwen3-ST-The-Next-Generation-II-v1-256k-ctx-6B.Q4_K_M.gguf) | Q4_K_M | 4.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-ST-The-Next-Generation-II-v1-256k-ctx-6B-GGUF/resolve/main/Qwen3-ST-The-Next-Generation-II-v1-256k-ctx-6B.Q5_K_S.gguf) | Q5_K_S | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-ST-The-Next-Generation-II-v1-256k-ctx-6B-GGUF/resolve/main/Qwen3-ST-The-Next-Generation-II-v1-256k-ctx-6B.Q5_K_M.gguf) | Q5_K_M | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-ST-The-Next-Generation-II-v1-256k-ctx-6B-GGUF/resolve/main/Qwen3-ST-The-Next-Generation-II-v1-256k-ctx-6B.Q6_K.gguf) | Q6_K | 5.3 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-ST-The-Next-Generation-II-v1-256k-ctx-6B-GGUF/resolve/main/Qwen3-ST-The-Next-Generation-II-v1-256k-ctx-6B.Q8_0.gguf) | Q8_0 | 6.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-ST-The-Next-Generation-II-v1-256k-ctx-6B-GGUF/resolve/main/Qwen3-ST-The-Next-Generation-II-v1-256k-ctx-6B.f16.gguf) | f16 | 12.8 | 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. + +