commit a9a4c3e599a145c36eb4fcf0b2cd0b2aa2060039 Author: ModelHub XC Date: Wed Oct 28 09:44:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/PD_gemma-3n-E4B-v2-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f0147fe --- /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 +PD_gemma-3n-E4B-v2.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +PD_gemma-3n-E4B-v2.f16.gguf filter=lfs diff=lfs merge=lfs -text +PD_gemma-3n-E4B-v2.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +PD_gemma-3n-E4B-v2.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +PD_gemma-3n-E4B-v2.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +PD_gemma-3n-E4B-v2.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +PD_gemma-3n-E4B-v2.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +PD_gemma-3n-E4B-v2.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +PD_gemma-3n-E4B-v2.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +PD_gemma-3n-E4B-v2.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +PD_gemma-3n-E4B-v2.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +PD_gemma-3n-E4B-v2.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/PD_gemma-3n-E4B-v2.IQ4_XS.gguf b/PD_gemma-3n-E4B-v2.IQ4_XS.gguf new file mode 100644 index 0000000..313e988 --- /dev/null +++ b/PD_gemma-3n-E4B-v2.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae8691c29c43e66b605b4bfdb4a039f1951ad5188c90a3b334b0ff5d3a9f9ad6 +size 3915995392 diff --git a/PD_gemma-3n-E4B-v2.Q2_K.gguf b/PD_gemma-3n-E4B-v2.Q2_K.gguf new file mode 100644 index 0000000..e1f9421 --- /dev/null +++ b/PD_gemma-3n-E4B-v2.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18008ffae3b0b108b1128f3c2f6fa5c6850ba2db38664b31d3f4292ac74af38c +size 2757318912 diff --git a/PD_gemma-3n-E4B-v2.Q3_K_L.gguf b/PD_gemma-3n-E4B-v2.Q3_K_L.gguf new file mode 100644 index 0000000..fe202eb --- /dev/null +++ b/PD_gemma-3n-E4B-v2.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:725c6aaf2f0a18fe65029af75959a1df2b5b802d9ebe1df1be0de0870b7d4db6 +size 3601996032 diff --git a/PD_gemma-3n-E4B-v2.Q3_K_M.gguf b/PD_gemma-3n-E4B-v2.Q3_K_M.gguf new file mode 100644 index 0000000..8a025bd --- /dev/null +++ b/PD_gemma-3n-E4B-v2.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d36c94e40577f92afb6fc5e06cef110fefc018e3335cab3821227bab3087ea0 +size 3440908544 diff --git a/PD_gemma-3n-E4B-v2.Q3_K_S.gguf b/PD_gemma-3n-E4B-v2.Q3_K_S.gguf new file mode 100644 index 0000000..2b22704 --- /dev/null +++ b/PD_gemma-3n-E4B-v2.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf031a2eea0d15ef7f4714b80f329502ed83959e0c3c24485176f5949d2130fa +size 3251910912 diff --git a/PD_gemma-3n-E4B-v2.Q4_K_M.gguf b/PD_gemma-3n-E4B-v2.Q4_K_M.gguf new file mode 100644 index 0000000..ce9edf8 --- /dev/null +++ b/PD_gemma-3n-E4B-v2.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f4bf1baad3c3e3e4e782619e5832b84e86029157e146a9092b77074b5a09fce +size 4237064448 diff --git a/PD_gemma-3n-E4B-v2.Q4_K_S.gguf b/PD_gemma-3n-E4B-v2.Q4_K_S.gguf new file mode 100644 index 0000000..bce7622 --- /dev/null +++ b/PD_gemma-3n-E4B-v2.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a445f49bfab058824dee44714e28bb1ec29c525e1c6ec4eea6ea1bbf8ee05642 +size 4102707456 diff --git a/PD_gemma-3n-E4B-v2.Q5_K_M.gguf b/PD_gemma-3n-E4B-v2.Q5_K_M.gguf new file mode 100644 index 0000000..44236a5 --- /dev/null +++ b/PD_gemma-3n-E4B-v2.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:753b17777015ba2463988fb8018e2949c8f5249a61496ee0cca9106501c73624 +size 4947998976 diff --git a/PD_gemma-3n-E4B-v2.Q5_K_S.gguf b/PD_gemma-3n-E4B-v2.Q5_K_S.gguf new file mode 100644 index 0000000..5f6ad88 --- /dev/null +++ b/PD_gemma-3n-E4B-v2.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f04ec0c54a27a5f3da859693fd159b56150748199483cc63141eb42817358207 +size 4869871872 diff --git a/PD_gemma-3n-E4B-v2.Q6_K.gguf b/PD_gemma-3n-E4B-v2.Q6_K.gguf new file mode 100644 index 0000000..769602a --- /dev/null +++ b/PD_gemma-3n-E4B-v2.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5bbb8b809cb8e53dc5633374697a137733aa7a5db929fe7fbd85cfe1509d85b9 +size 5703366912 diff --git a/PD_gemma-3n-E4B-v2.Q8_0.gguf b/PD_gemma-3n-E4B-v2.Q8_0.gguf new file mode 100644 index 0000000..53cf7f8 --- /dev/null +++ b/PD_gemma-3n-E4B-v2.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32b57f41bdd68c6781a64c06b180524ebd97662812eaf3c5c963867eb47f5a63 +size 7353293056 diff --git a/PD_gemma-3n-E4B-v2.f16.gguf b/PD_gemma-3n-E4B-v2.f16.gguf new file mode 100644 index 0000000..781cec5 --- /dev/null +++ b/PD_gemma-3n-E4B-v2.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f33011c6e4cdf921ee35777482aa4da929fcd22fefd171c038c7f3b15e8531d9 +size 13740103936 diff --git a/README.md b/README.md new file mode 100644 index 0000000..3a2436a --- /dev/null +++ b/README.md @@ -0,0 +1,78 @@ +--- +base_model: EpistemeAI/PD_gemma-3n-E4B-v2 +language: +- en +library_name: transformers +license: gemma +mradermacher: + readme_rev: 1 +no_imatrix: 'llama_model_quantize: failed to quantize: Missing importance matrix for + tensor blk.20.attn_k.weight in a very low-bit quantization' +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- gemma3n +--- +## About + + + + + + + + + +static quants of https://huggingface.co/EpistemeAI/PD_gemma-3n-E4B-v2 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#PD_gemma-3n-E4B-v2-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/PD_gemma-3n-E4B-v2-GGUF/resolve/main/PD_gemma-3n-E4B-v2.Q2_K.gguf) | Q2_K | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/PD_gemma-3n-E4B-v2-GGUF/resolve/main/PD_gemma-3n-E4B-v2.Q3_K_S.gguf) | Q3_K_S | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/PD_gemma-3n-E4B-v2-GGUF/resolve/main/PD_gemma-3n-E4B-v2.Q3_K_M.gguf) | Q3_K_M | 3.5 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/PD_gemma-3n-E4B-v2-GGUF/resolve/main/PD_gemma-3n-E4B-v2.Q3_K_L.gguf) | Q3_K_L | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/PD_gemma-3n-E4B-v2-GGUF/resolve/main/PD_gemma-3n-E4B-v2.IQ4_XS.gguf) | IQ4_XS | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/PD_gemma-3n-E4B-v2-GGUF/resolve/main/PD_gemma-3n-E4B-v2.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/PD_gemma-3n-E4B-v2-GGUF/resolve/main/PD_gemma-3n-E4B-v2.Q4_K_M.gguf) | Q4_K_M | 4.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/PD_gemma-3n-E4B-v2-GGUF/resolve/main/PD_gemma-3n-E4B-v2.Q5_K_S.gguf) | Q5_K_S | 5.0 | | +| [GGUF](https://huggingface.co/mradermacher/PD_gemma-3n-E4B-v2-GGUF/resolve/main/PD_gemma-3n-E4B-v2.Q5_K_M.gguf) | Q5_K_M | 5.0 | | +| [GGUF](https://huggingface.co/mradermacher/PD_gemma-3n-E4B-v2-GGUF/resolve/main/PD_gemma-3n-E4B-v2.Q6_K.gguf) | Q6_K | 5.8 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/PD_gemma-3n-E4B-v2-GGUF/resolve/main/PD_gemma-3n-E4B-v2.Q8_0.gguf) | Q8_0 | 7.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/PD_gemma-3n-E4B-v2-GGUF/resolve/main/PD_gemma-3n-E4B-v2.f16.gguf) | f16 | 13.8 | 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. + +