commit 0a9dde91e9203855877ffe6060e14c83d60a9bca Author: ModelHub XC Date: Wed Jul 22 06:52:10 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen2.5-7B-s1K-SFT-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..91123a4 --- /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-s1K-SFT.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-s1K-SFT.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-s1K-SFT.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-s1K-SFT.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-s1K-SFT.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-s1K-SFT.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-s1K-SFT.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-s1K-SFT.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-s1K-SFT.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-s1K-SFT.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-s1K-SFT.f16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-s1K-SFT.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2.5-7B-s1K-SFT.IQ4_XS.gguf b/Qwen2.5-7B-s1K-SFT.IQ4_XS.gguf new file mode 100644 index 0000000..0d4ea35 --- /dev/null +++ b/Qwen2.5-7B-s1K-SFT.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10a69b44ca7b8dee6bf9dd90a0a9b51a1433b879650802509851045556f17846 +size 4250299296 diff --git a/Qwen2.5-7B-s1K-SFT.Q2_K.gguf b/Qwen2.5-7B-s1K-SFT.Q2_K.gguf new file mode 100644 index 0000000..5cd1502 --- /dev/null +++ b/Qwen2.5-7B-s1K-SFT.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c21b04f52103dcba7984a0c31cb63224edf2bbede4609745381b70ef105e5f9 +size 3015941024 diff --git a/Qwen2.5-7B-s1K-SFT.Q3_K_L.gguf b/Qwen2.5-7B-s1K-SFT.Q3_K_L.gguf new file mode 100644 index 0000000..361a3e3 --- /dev/null +++ b/Qwen2.5-7B-s1K-SFT.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ccb34a5d80ed223488a47f79f8b9f3d3690c50e566feb1fc981d9c249a4b72f +size 4088460192 diff --git a/Qwen2.5-7B-s1K-SFT.Q3_K_M.gguf b/Qwen2.5-7B-s1K-SFT.Q3_K_M.gguf new file mode 100644 index 0000000..472c4c1 --- /dev/null +++ b/Qwen2.5-7B-s1K-SFT.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0c83a1273a2115d4991d7e8803734ad6354f79f73ae30167abb81a1e261934a +size 3808392096 diff --git a/Qwen2.5-7B-s1K-SFT.Q3_K_S.gguf b/Qwen2.5-7B-s1K-SFT.Q3_K_S.gguf new file mode 100644 index 0000000..8b69327 --- /dev/null +++ b/Qwen2.5-7B-s1K-SFT.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a12b02c8d9e454b287ff65ec2fc6bb4b8adbc7dac94c7ca4800f14e5982b307 +size 3492369312 diff --git a/Qwen2.5-7B-s1K-SFT.Q4_K_M.gguf b/Qwen2.5-7B-s1K-SFT.Q4_K_M.gguf new file mode 100644 index 0000000..93acad6 --- /dev/null +++ b/Qwen2.5-7B-s1K-SFT.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f9b9f0b8c8c993b57b4c5f8d3652c1c6b0676fb41978f2637e520715d6f505a +size 4683074464 diff --git a/Qwen2.5-7B-s1K-SFT.Q4_K_S.gguf b/Qwen2.5-7B-s1K-SFT.Q4_K_S.gguf new file mode 100644 index 0000000..7c2f6fa --- /dev/null +++ b/Qwen2.5-7B-s1K-SFT.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:caf5ef659b6a40b0d3d31e102f47e7b763e0c3ff003afaabdf819ecdace76f5f +size 4457769888 diff --git a/Qwen2.5-7B-s1K-SFT.Q5_K_M.gguf b/Qwen2.5-7B-s1K-SFT.Q5_K_M.gguf new file mode 100644 index 0000000..ab0cc12 --- /dev/null +++ b/Qwen2.5-7B-s1K-SFT.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d44b7f0764ba2a2f9ae06796efb9e9a0ec94005d50b41706dd3bed7a3e35600 +size 5444832160 diff --git a/Qwen2.5-7B-s1K-SFT.Q5_K_S.gguf b/Qwen2.5-7B-s1K-SFT.Q5_K_S.gguf new file mode 100644 index 0000000..29597ad --- /dev/null +++ b/Qwen2.5-7B-s1K-SFT.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d29922ff3262311305c55433199fc4cf54ee9c9b06602db86c852b881e5aa80c +size 5315177376 diff --git a/Qwen2.5-7B-s1K-SFT.Q6_K.gguf b/Qwen2.5-7B-s1K-SFT.Q6_K.gguf new file mode 100644 index 0000000..403bac8 --- /dev/null +++ b/Qwen2.5-7B-s1K-SFT.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:84801f0be9f549658b66a750cea68b7ba44b0ec8724eda6e01d60cf2d7efdb60 +size 6254199712 diff --git a/Qwen2.5-7B-s1K-SFT.Q8_0.gguf b/Qwen2.5-7B-s1K-SFT.Q8_0.gguf new file mode 100644 index 0000000..54fc141 --- /dev/null +++ b/Qwen2.5-7B-s1K-SFT.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31e90f91287349c3f9812a885071538db8e1db98e7335fb6e26edc3a8e4ba039 +size 8098526112 diff --git a/Qwen2.5-7B-s1K-SFT.f16.gguf b/Qwen2.5-7B-s1K-SFT.f16.gguf new file mode 100644 index 0000000..a59757e --- /dev/null +++ b/Qwen2.5-7B-s1K-SFT.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cdc521df96181c087a1bd930cde0bc03d452982b94d7f56c2af2fd73a8476da4 +size 15237854112 diff --git a/README.md b/README.md new file mode 100644 index 0000000..899edf9 --- /dev/null +++ b/README.md @@ -0,0 +1,75 @@ +--- +base_model: januverma/Qwen2.5-7B-s1K-SFT +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- qwen2 +- trl +--- +## About + + + + + + +static quants of https://huggingface.co/januverma/Qwen2.5-7B-s1K-SFT + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen2.5-7B-s1K-SFT-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-s1K-SFT-GGUF/resolve/main/Qwen2.5-7B-s1K-SFT.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-s1K-SFT-GGUF/resolve/main/Qwen2.5-7B-s1K-SFT.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-s1K-SFT-GGUF/resolve/main/Qwen2.5-7B-s1K-SFT.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-s1K-SFT-GGUF/resolve/main/Qwen2.5-7B-s1K-SFT.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-s1K-SFT-GGUF/resolve/main/Qwen2.5-7B-s1K-SFT.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-s1K-SFT-GGUF/resolve/main/Qwen2.5-7B-s1K-SFT.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-s1K-SFT-GGUF/resolve/main/Qwen2.5-7B-s1K-SFT.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-s1K-SFT-GGUF/resolve/main/Qwen2.5-7B-s1K-SFT.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-s1K-SFT-GGUF/resolve/main/Qwen2.5-7B-s1K-SFT.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-s1K-SFT-GGUF/resolve/main/Qwen2.5-7B-s1K-SFT.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-s1K-SFT-GGUF/resolve/main/Qwen2.5-7B-s1K-SFT.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-s1K-SFT-GGUF/resolve/main/Qwen2.5-7B-s1K-SFT.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. + +