commit 9affd5b0af97ac937dd370ee268dbb5ac0d150ad Author: ModelHub XC Date: Sat Oct 10 05:11:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Persona-Qwen2.5-3B-Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..eac46b4 --- /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 +Persona-Qwen2.5-3B-Instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Persona-Qwen2.5-3B-Instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Persona-Qwen2.5-3B-Instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Persona-Qwen2.5-3B-Instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Persona-Qwen2.5-3B-Instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Persona-Qwen2.5-3B-Instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Persona-Qwen2.5-3B-Instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Persona-Qwen2.5-3B-Instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Persona-Qwen2.5-3B-Instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Persona-Qwen2.5-3B-Instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Persona-Qwen2.5-3B-Instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Persona-Qwen2.5-3B-Instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Persona-Qwen2.5-3B-Instruct.IQ4_XS.gguf b/Persona-Qwen2.5-3B-Instruct.IQ4_XS.gguf new file mode 100644 index 0000000..fa2bfba --- /dev/null +++ b/Persona-Qwen2.5-3B-Instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12f8b6814f1e6cbf2bd57fe1d42dc125f13604b074365093dff7f3718250fba8 +size 1753185088 diff --git a/Persona-Qwen2.5-3B-Instruct.Q2_K.gguf b/Persona-Qwen2.5-3B-Instruct.Q2_K.gguf new file mode 100644 index 0000000..499d14f --- /dev/null +++ b/Persona-Qwen2.5-3B-Instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c4acc4714581c803198a688e09d9683b83241bb79ec9f7685f212da665300b5 +size 1274755904 diff --git a/Persona-Qwen2.5-3B-Instruct.Q3_K_L.gguf b/Persona-Qwen2.5-3B-Instruct.Q3_K_L.gguf new file mode 100644 index 0000000..d7280d3 --- /dev/null +++ b/Persona-Qwen2.5-3B-Instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d0a8a2d1f6497eeeb1196796ebf647bdc7180410ad8c043d4412c8e2170167e +size 1707391808 diff --git a/Persona-Qwen2.5-3B-Instruct.Q3_K_M.gguf b/Persona-Qwen2.5-3B-Instruct.Q3_K_M.gguf new file mode 100644 index 0000000..3d6f8d2 --- /dev/null +++ b/Persona-Qwen2.5-3B-Instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9a6ee462e8448d56a4907a3575ac1760d0a1fd37d837cf3276fdfb919fe0760 +size 1590475584 diff --git a/Persona-Qwen2.5-3B-Instruct.Q3_K_S.gguf b/Persona-Qwen2.5-3B-Instruct.Q3_K_S.gguf new file mode 100644 index 0000000..b2fccd3 --- /dev/null +++ b/Persona-Qwen2.5-3B-Instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1eb8a8f93c6c56811caf690af40c6bb77cc35e9216f1247596074b51365dfd6 +size 1454357312 diff --git a/Persona-Qwen2.5-3B-Instruct.Q4_K_M.gguf b/Persona-Qwen2.5-3B-Instruct.Q4_K_M.gguf new file mode 100644 index 0000000..2094605 --- /dev/null +++ b/Persona-Qwen2.5-3B-Instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97cbdbab48e9da1df18a35e4c07ee40a99f5c1ddebeb47cebe83f289e09153d5 +size 1929902912 diff --git a/Persona-Qwen2.5-3B-Instruct.Q4_K_S.gguf b/Persona-Qwen2.5-3B-Instruct.Q4_K_S.gguf new file mode 100644 index 0000000..a7b0164 --- /dev/null +++ b/Persona-Qwen2.5-3B-Instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ed41e5cbe545b96237d81dd19c75944ffa5e9c17d16d3875755be52e3afa2fd +size 1834384192 diff --git a/Persona-Qwen2.5-3B-Instruct.Q5_K_M.gguf b/Persona-Qwen2.5-3B-Instruct.Q5_K_M.gguf new file mode 100644 index 0000000..25f8efc --- /dev/null +++ b/Persona-Qwen2.5-3B-Instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d915ae3a554fcc7d3e39c40bd76aa3a370eb1bc6a30a783b7f78ba2a02cfcca4 +size 2224814912 diff --git a/Persona-Qwen2.5-3B-Instruct.Q5_K_S.gguf b/Persona-Qwen2.5-3B-Instruct.Q5_K_S.gguf new file mode 100644 index 0000000..2c26ea4 --- /dev/null +++ b/Persona-Qwen2.5-3B-Instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8374f0481de7cb323be4c133cfda48f4c188c2c055e4d462ea75158a7a83afc5 +size 2169666368 diff --git a/Persona-Qwen2.5-3B-Instruct.Q6_K.gguf b/Persona-Qwen2.5-3B-Instruct.Q6_K.gguf new file mode 100644 index 0000000..1ea04c4 --- /dev/null +++ b/Persona-Qwen2.5-3B-Instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6493f5880368ad8ddae4b377c5955a27276e88df92c0e8887cf99b9d53f6970 +size 2538158912 diff --git a/Persona-Qwen2.5-3B-Instruct.Q8_0.gguf b/Persona-Qwen2.5-3B-Instruct.Q8_0.gguf new file mode 100644 index 0000000..f21d36e --- /dev/null +++ b/Persona-Qwen2.5-3B-Instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd9ae011610844ca45a4945e0325f196e2fe4c7052bf60aa893b0d966f7826a4 +size 3285476160 diff --git a/Persona-Qwen2.5-3B-Instruct.f16.gguf b/Persona-Qwen2.5-3B-Instruct.f16.gguf new file mode 100644 index 0000000..d857397 --- /dev/null +++ b/Persona-Qwen2.5-3B-Instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7289a8d876e464e40f56ec7f2793c9a402533bcd7d2c161029fe17bb1702c55f +size 6178317120 diff --git a/README.md b/README.md new file mode 100644 index 0000000..d0b510f --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: ammaradeel/Persona-Qwen2.5-3B-Instruct +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/ammaradeel/Persona-Qwen2.5-3B-Instruct + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Persona-Qwen2.5-3B-Instruct-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Persona-Qwen2.5-3B-Instruct-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/Persona-Qwen2.5-3B-Instruct-GGUF/resolve/main/Persona-Qwen2.5-3B-Instruct.Q2_K.gguf) | Q2_K | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/Persona-Qwen2.5-3B-Instruct-GGUF/resolve/main/Persona-Qwen2.5-3B-Instruct.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Persona-Qwen2.5-3B-Instruct-GGUF/resolve/main/Persona-Qwen2.5-3B-Instruct.Q3_K_M.gguf) | Q3_K_M | 1.7 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Persona-Qwen2.5-3B-Instruct-GGUF/resolve/main/Persona-Qwen2.5-3B-Instruct.Q3_K_L.gguf) | Q3_K_L | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Persona-Qwen2.5-3B-Instruct-GGUF/resolve/main/Persona-Qwen2.5-3B-Instruct.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Persona-Qwen2.5-3B-Instruct-GGUF/resolve/main/Persona-Qwen2.5-3B-Instruct.Q4_K_S.gguf) | Q4_K_S | 1.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Persona-Qwen2.5-3B-Instruct-GGUF/resolve/main/Persona-Qwen2.5-3B-Instruct.Q4_K_M.gguf) | Q4_K_M | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Persona-Qwen2.5-3B-Instruct-GGUF/resolve/main/Persona-Qwen2.5-3B-Instruct.Q5_K_S.gguf) | Q5_K_S | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Persona-Qwen2.5-3B-Instruct-GGUF/resolve/main/Persona-Qwen2.5-3B-Instruct.Q5_K_M.gguf) | Q5_K_M | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Persona-Qwen2.5-3B-Instruct-GGUF/resolve/main/Persona-Qwen2.5-3B-Instruct.Q6_K.gguf) | Q6_K | 2.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Persona-Qwen2.5-3B-Instruct-GGUF/resolve/main/Persona-Qwen2.5-3B-Instruct.Q8_0.gguf) | Q8_0 | 3.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Persona-Qwen2.5-3B-Instruct-GGUF/resolve/main/Persona-Qwen2.5-3B-Instruct.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. + +