From 4e4c5b89a8aadee9d9f02610854a755e75726e6e Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Wed, 22 Jul 2026 04:41:10 +0800 Subject: [PATCH] =?UTF-8?q?=E5=88=9D=E5=A7=8B=E5=8C=96=E9=A1=B9=E7=9B=AE?= =?UTF-8?q?=EF=BC=8C=E7=94=B1ModelHub=20XC=E7=A4=BE=E5=8C=BA=E6=8F=90?= =?UTF-8?q?=E4=BE=9B=E6=A8=A1=E5=9E=8B?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Model: mradermacher/Qwen2.5-7B-1M-SFT-LongStory-GGUF Source: Original Platform --- .gitattributes | 47 ++++++++++++++++ Qwen2.5-7B-1M-SFT-LongStory.IQ4_XS.gguf | 3 + Qwen2.5-7B-1M-SFT-LongStory.Q2_K.gguf | 3 + Qwen2.5-7B-1M-SFT-LongStory.Q3_K_L.gguf | 3 + Qwen2.5-7B-1M-SFT-LongStory.Q3_K_M.gguf | 3 + Qwen2.5-7B-1M-SFT-LongStory.Q3_K_S.gguf | 3 + Qwen2.5-7B-1M-SFT-LongStory.Q4_K_M.gguf | 3 + Qwen2.5-7B-1M-SFT-LongStory.Q4_K_S.gguf | 3 + Qwen2.5-7B-1M-SFT-LongStory.Q5_K_M.gguf | 3 + Qwen2.5-7B-1M-SFT-LongStory.Q5_K_S.gguf | 3 + Qwen2.5-7B-1M-SFT-LongStory.Q6_K.gguf | 3 + Qwen2.5-7B-1M-SFT-LongStory.Q8_0.gguf | 3 + Qwen2.5-7B-1M-SFT-LongStory.f16.gguf | 3 + README.md | 75 +++++++++++++++++++++++++ 14 files changed, 158 insertions(+) create mode 100644 .gitattributes create mode 100644 Qwen2.5-7B-1M-SFT-LongStory.IQ4_XS.gguf create mode 100644 Qwen2.5-7B-1M-SFT-LongStory.Q2_K.gguf create mode 100644 Qwen2.5-7B-1M-SFT-LongStory.Q3_K_L.gguf create mode 100644 Qwen2.5-7B-1M-SFT-LongStory.Q3_K_M.gguf create mode 100644 Qwen2.5-7B-1M-SFT-LongStory.Q3_K_S.gguf create mode 100644 Qwen2.5-7B-1M-SFT-LongStory.Q4_K_M.gguf create mode 100644 Qwen2.5-7B-1M-SFT-LongStory.Q4_K_S.gguf create mode 100644 Qwen2.5-7B-1M-SFT-LongStory.Q5_K_M.gguf create mode 100644 Qwen2.5-7B-1M-SFT-LongStory.Q5_K_S.gguf create mode 100644 Qwen2.5-7B-1M-SFT-LongStory.Q6_K.gguf create mode 100644 Qwen2.5-7B-1M-SFT-LongStory.Q8_0.gguf create mode 100644 Qwen2.5-7B-1M-SFT-LongStory.f16.gguf create mode 100644 README.md diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..9111146 --- /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 +Qwen2.5-7B-1M-SFT-LongStory.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-1M-SFT-LongStory.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-1M-SFT-LongStory.f16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-1M-SFT-LongStory.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-1M-SFT-LongStory.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-1M-SFT-LongStory.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-1M-SFT-LongStory.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-1M-SFT-LongStory.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-1M-SFT-LongStory.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-1M-SFT-LongStory.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-1M-SFT-LongStory.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-1M-SFT-LongStory.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2.5-7B-1M-SFT-LongStory.IQ4_XS.gguf b/Qwen2.5-7B-1M-SFT-LongStory.IQ4_XS.gguf new file mode 100644 index 0000000..d792532 --- /dev/null +++ b/Qwen2.5-7B-1M-SFT-LongStory.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9038ad423c9e1853ffbca916632b40a97362f12c60c2195f41c2f2bdf8814823 +size 4250298720 diff --git a/Qwen2.5-7B-1M-SFT-LongStory.Q2_K.gguf b/Qwen2.5-7B-1M-SFT-LongStory.Q2_K.gguf new file mode 100644 index 0000000..a023373 --- /dev/null +++ b/Qwen2.5-7B-1M-SFT-LongStory.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:230004f40991c3f1117b1f712e513e7763a1f76c82868f857c7d5f50f490cc88 +size 3015940448 diff --git a/Qwen2.5-7B-1M-SFT-LongStory.Q3_K_L.gguf b/Qwen2.5-7B-1M-SFT-LongStory.Q3_K_L.gguf new file mode 100644 index 0000000..5516810 --- /dev/null +++ b/Qwen2.5-7B-1M-SFT-LongStory.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98ff1411a29fe103df159ae8092f1d9e00dd5cb6ee05eeb34369b1c5a6007431 +size 4088459616 diff --git a/Qwen2.5-7B-1M-SFT-LongStory.Q3_K_M.gguf b/Qwen2.5-7B-1M-SFT-LongStory.Q3_K_M.gguf new file mode 100644 index 0000000..3c4c5e2 --- /dev/null +++ b/Qwen2.5-7B-1M-SFT-LongStory.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e17c26a916f690c223ae741e723c0abdb8df0146a5191ed86a9829ea0c8480c +size 3808391520 diff --git a/Qwen2.5-7B-1M-SFT-LongStory.Q3_K_S.gguf b/Qwen2.5-7B-1M-SFT-LongStory.Q3_K_S.gguf new file mode 100644 index 0000000..c61ad77 --- /dev/null +++ b/Qwen2.5-7B-1M-SFT-LongStory.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec87dfc56be89910966140b3abbb65f177fbf336fbe36ceaeb04e0b41261e96b +size 3492368736 diff --git a/Qwen2.5-7B-1M-SFT-LongStory.Q4_K_M.gguf b/Qwen2.5-7B-1M-SFT-LongStory.Q4_K_M.gguf new file mode 100644 index 0000000..f998e52 --- /dev/null +++ b/Qwen2.5-7B-1M-SFT-LongStory.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0582a674f050c3f4c9e62464c66612c7bb02c31fbeb5947a7e0a4ee5213eac6a +size 4683073888 diff --git a/Qwen2.5-7B-1M-SFT-LongStory.Q4_K_S.gguf b/Qwen2.5-7B-1M-SFT-LongStory.Q4_K_S.gguf new file mode 100644 index 0000000..f13a676 --- /dev/null +++ b/Qwen2.5-7B-1M-SFT-LongStory.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:558109edf64ce70f2655519f0f8a1e34ad4b3ee0ce697ecb7f662f9d960620ed +size 4457769312 diff --git a/Qwen2.5-7B-1M-SFT-LongStory.Q5_K_M.gguf b/Qwen2.5-7B-1M-SFT-LongStory.Q5_K_M.gguf new file mode 100644 index 0000000..7caed12 --- /dev/null +++ b/Qwen2.5-7B-1M-SFT-LongStory.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b70eb39751f2a227138031765919a34407574da5d76fbc03d86e242e961a4355 +size 5444831584 diff --git a/Qwen2.5-7B-1M-SFT-LongStory.Q5_K_S.gguf b/Qwen2.5-7B-1M-SFT-LongStory.Q5_K_S.gguf new file mode 100644 index 0000000..7f96e49 --- /dev/null +++ b/Qwen2.5-7B-1M-SFT-LongStory.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12dbc4534314a97a2d6412b8ca02a9174523dddc394be09a165a1389618120cd +size 5315176800 diff --git a/Qwen2.5-7B-1M-SFT-LongStory.Q6_K.gguf b/Qwen2.5-7B-1M-SFT-LongStory.Q6_K.gguf new file mode 100644 index 0000000..6118158 --- /dev/null +++ b/Qwen2.5-7B-1M-SFT-LongStory.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7410f37197d97f626d80257ab2eaa5a551522b53b067f5b12f4eec25c14011a7 +size 6254199136 diff --git a/Qwen2.5-7B-1M-SFT-LongStory.Q8_0.gguf b/Qwen2.5-7B-1M-SFT-LongStory.Q8_0.gguf new file mode 100644 index 0000000..88b729f --- /dev/null +++ b/Qwen2.5-7B-1M-SFT-LongStory.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2598a3333c5f793e09ef04b5a31c9e4e57c4ecd95f5595c9d531f4bf3b3fa77 +size 8098525536 diff --git a/Qwen2.5-7B-1M-SFT-LongStory.f16.gguf b/Qwen2.5-7B-1M-SFT-LongStory.f16.gguf new file mode 100644 index 0000000..d36bd5e --- /dev/null +++ b/Qwen2.5-7B-1M-SFT-LongStory.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a3432dfecc78ca26afaf9d5149d90daa3d2f2ddfaa9d51ae70b2f11664d5dc7 +size 15237853536 diff --git a/README.md b/README.md new file mode 100644 index 0000000..eb52892 --- /dev/null +++ b/README.md @@ -0,0 +1,75 @@ +--- +base_model: agurung/Qwen2.5-7B-1M-SFT-LongStory +datasets: ncp_long_story +language: +- en +library_name: transformers +model_name: Qwen2.5-7B-1M-SFT-LongStory +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- generated_from_trainer +- ncp_long_story +- trl +- sft +--- +## About + + + + + + +static quants of https://huggingface.co/agurung/Qwen2.5-7B-1M-SFT-LongStory + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen2.5-7B-1M-SFT-LongStory-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/Qwen2.5-7B-1M-SFT-LongStory-GGUF/resolve/main/Qwen2.5-7B-1M-SFT-LongStory.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-1M-SFT-LongStory-GGUF/resolve/main/Qwen2.5-7B-1M-SFT-LongStory.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-1M-SFT-LongStory-GGUF/resolve/main/Qwen2.5-7B-1M-SFT-LongStory.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-1M-SFT-LongStory-GGUF/resolve/main/Qwen2.5-7B-1M-SFT-LongStory.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-1M-SFT-LongStory-GGUF/resolve/main/Qwen2.5-7B-1M-SFT-LongStory.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-1M-SFT-LongStory-GGUF/resolve/main/Qwen2.5-7B-1M-SFT-LongStory.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-1M-SFT-LongStory-GGUF/resolve/main/Qwen2.5-7B-1M-SFT-LongStory.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-1M-SFT-LongStory-GGUF/resolve/main/Qwen2.5-7B-1M-SFT-LongStory.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-1M-SFT-LongStory-GGUF/resolve/main/Qwen2.5-7B-1M-SFT-LongStory.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-1M-SFT-LongStory-GGUF/resolve/main/Qwen2.5-7B-1M-SFT-LongStory.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-1M-SFT-LongStory-GGUF/resolve/main/Qwen2.5-7B-1M-SFT-LongStory.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-1M-SFT-LongStory-GGUF/resolve/main/Qwen2.5-7B-1M-SFT-LongStory.f16.gguf) | f16 | 15.3 | 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. + +