commit 588b3ba6fa8e793e2209edae9824244df14a0ee4 Author: ModelHub XC Date: Sun Apr 26 22:28:34 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen2.5-gfn-sft-3b-250k-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..7986e74 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,48 @@ +*.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-gfn-sft-3b-250k.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-gfn-sft-3b-250k.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-gfn-sft-3b-250k.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-gfn-sft-3b-250k.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-gfn-sft-3b-250k.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-gfn-sft-3b-250k.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-gfn-sft-3b-250k.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-gfn-sft-3b-250k.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-gfn-sft-3b-250k.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-gfn-sft-3b-250k.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-gfn-sft-3b-250k.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-gfn-sft-3b-250k.f16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-gfn-sft-3b-250k.mmproj-fp16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2.5-gfn-sft-3b-250k.IQ4_XS.gguf b/Qwen2.5-gfn-sft-3b-250k.IQ4_XS.gguf new file mode 100644 index 0000000..cc53aae --- /dev/null +++ b/Qwen2.5-gfn-sft-3b-250k.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed3f888d8335d338db6d947495428cb72b0ef4fcb1513ce0579dbf2daaa59bf4 +size 1753183680 diff --git a/Qwen2.5-gfn-sft-3b-250k.Q2_K.gguf b/Qwen2.5-gfn-sft-3b-250k.Q2_K.gguf new file mode 100644 index 0000000..c2f5d32 --- /dev/null +++ b/Qwen2.5-gfn-sft-3b-250k.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c8b0f7030819a2f23245e0f161c9062b44b354239129d70f5eda61c4f8c5118 +size 1274754496 diff --git a/Qwen2.5-gfn-sft-3b-250k.Q3_K_L.gguf b/Qwen2.5-gfn-sft-3b-250k.Q3_K_L.gguf new file mode 100644 index 0000000..1c3e26a --- /dev/null +++ b/Qwen2.5-gfn-sft-3b-250k.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ccbfceb6bf88bd73320f3925a87f57a9b412053471fc68be13f7a5282742dd9 +size 1707390400 diff --git a/Qwen2.5-gfn-sft-3b-250k.Q3_K_M.gguf b/Qwen2.5-gfn-sft-3b-250k.Q3_K_M.gguf new file mode 100644 index 0000000..d0df087 --- /dev/null +++ b/Qwen2.5-gfn-sft-3b-250k.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e4441b3627a342efc78b4551123a410278ecc0a6adb3b8d652d711e10758b3b +size 1590474176 diff --git a/Qwen2.5-gfn-sft-3b-250k.Q3_K_S.gguf b/Qwen2.5-gfn-sft-3b-250k.Q3_K_S.gguf new file mode 100644 index 0000000..26383d7 --- /dev/null +++ b/Qwen2.5-gfn-sft-3b-250k.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:692e833b3bb9dd6827a463e68ee2527e68112f0036ac345c04a29e1b686f0c1a +size 1454355904 diff --git a/Qwen2.5-gfn-sft-3b-250k.Q4_K_M.gguf b/Qwen2.5-gfn-sft-3b-250k.Q4_K_M.gguf new file mode 100644 index 0000000..2705aa9 --- /dev/null +++ b/Qwen2.5-gfn-sft-3b-250k.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c8585ca8518df60e08c2543958411d359d80340e6391219ac313496d55ce35d +size 1929901504 diff --git a/Qwen2.5-gfn-sft-3b-250k.Q4_K_S.gguf b/Qwen2.5-gfn-sft-3b-250k.Q4_K_S.gguf new file mode 100644 index 0000000..72f78a9 --- /dev/null +++ b/Qwen2.5-gfn-sft-3b-250k.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4dbfb4a639963fc362b5d9ef41c96e5ef1e9aab1190d287cf774d7145a9aee79 +size 1834382784 diff --git a/Qwen2.5-gfn-sft-3b-250k.Q5_K_M.gguf b/Qwen2.5-gfn-sft-3b-250k.Q5_K_M.gguf new file mode 100644 index 0000000..1c7c69a --- /dev/null +++ b/Qwen2.5-gfn-sft-3b-250k.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e0443e1302e27a18c8042bc9b3fce7604cee4d0716d3ac2ae317a58a3532c3c +size 2224813504 diff --git a/Qwen2.5-gfn-sft-3b-250k.Q5_K_S.gguf b/Qwen2.5-gfn-sft-3b-250k.Q5_K_S.gguf new file mode 100644 index 0000000..730e5f5 --- /dev/null +++ b/Qwen2.5-gfn-sft-3b-250k.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7de33750ccb7fb0263045bf58dc00dd518f4488b943263a91093c51d4d1872d +size 2169664960 diff --git a/Qwen2.5-gfn-sft-3b-250k.Q6_K.gguf b/Qwen2.5-gfn-sft-3b-250k.Q6_K.gguf new file mode 100644 index 0000000..6b2c260 --- /dev/null +++ b/Qwen2.5-gfn-sft-3b-250k.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb9bcc718cc3be98f2071081bfa97887edb91fdd0904e32d231adda4c77ec3cc +size 2538157504 diff --git a/Qwen2.5-gfn-sft-3b-250k.Q8_0.gguf b/Qwen2.5-gfn-sft-3b-250k.Q8_0.gguf new file mode 100644 index 0000000..b130fb8 --- /dev/null +++ b/Qwen2.5-gfn-sft-3b-250k.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c041476706d1d52e251c25bca0086f6da7e23adb290401457fdd48324203cd62 +size 3285474752 diff --git a/Qwen2.5-gfn-sft-3b-250k.f16.gguf b/Qwen2.5-gfn-sft-3b-250k.f16.gguf new file mode 100644 index 0000000..b6fcbdb --- /dev/null +++ b/Qwen2.5-gfn-sft-3b-250k.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:567ebca25f4ad08a4ef3dd18e858d0962967c05930dd61fe6f5c6a8859f675bb +size 6178315712 diff --git a/Qwen2.5-gfn-sft-3b-250k.mmproj-fp16.gguf b/Qwen2.5-gfn-sft-3b-250k.mmproj-fp16.gguf new file mode 100644 index 0000000..b96f69d --- /dev/null +++ b/Qwen2.5-gfn-sft-3b-250k.mmproj-fp16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb7d5e099424fe4707455ad59d2b95daf5dc8325a6318fd2f705ad145d3bd83b +size 1338428544 diff --git a/README.md b/README.md new file mode 100644 index 0000000..e5351fa --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: ZachSun/Qwen2.5-gfn-sft-3b-250k +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/ZachSun/Qwen2.5-gfn-sft-3b-250k + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen2.5-gfn-sft-3b-250k-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-gfn-sft-3b-250k-GGUF/resolve/main/Qwen2.5-gfn-sft-3b-250k.Q2_K.gguf) | Q2_K | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-gfn-sft-3b-250k-GGUF/resolve/main/Qwen2.5-gfn-sft-3b-250k.mmproj-fp16.gguf) | mmproj-fp16 | 1.4 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-gfn-sft-3b-250k-GGUF/resolve/main/Qwen2.5-gfn-sft-3b-250k.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-gfn-sft-3b-250k-GGUF/resolve/main/Qwen2.5-gfn-sft-3b-250k.Q3_K_M.gguf) | Q3_K_M | 1.7 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-gfn-sft-3b-250k-GGUF/resolve/main/Qwen2.5-gfn-sft-3b-250k.Q3_K_L.gguf) | Q3_K_L | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-gfn-sft-3b-250k-GGUF/resolve/main/Qwen2.5-gfn-sft-3b-250k.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-gfn-sft-3b-250k-GGUF/resolve/main/Qwen2.5-gfn-sft-3b-250k.Q4_K_S.gguf) | Q4_K_S | 1.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-gfn-sft-3b-250k-GGUF/resolve/main/Qwen2.5-gfn-sft-3b-250k.Q4_K_M.gguf) | Q4_K_M | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-gfn-sft-3b-250k-GGUF/resolve/main/Qwen2.5-gfn-sft-3b-250k.Q5_K_S.gguf) | Q5_K_S | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-gfn-sft-3b-250k-GGUF/resolve/main/Qwen2.5-gfn-sft-3b-250k.Q5_K_M.gguf) | Q5_K_M | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-gfn-sft-3b-250k-GGUF/resolve/main/Qwen2.5-gfn-sft-3b-250k.Q6_K.gguf) | Q6_K | 2.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-gfn-sft-3b-250k-GGUF/resolve/main/Qwen2.5-gfn-sft-3b-250k.Q8_0.gguf) | Q8_0 | 3.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-gfn-sft-3b-250k-GGUF/resolve/main/Qwen2.5-gfn-sft-3b-250k.f16.gguf) | f16 | 6.3 | 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. + +