commit 4fb27adcdd81b22a8b5391c3e8970217582fdcdc Author: ModelHub XC Date: Tue Jun 16 20:38:19 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Gemma-3-4B-Fin-QA-Reasoning-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..0a542a5 --- /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 +Gemma-3-4B-Fin-QA-Reasoning.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Gemma-3-4B-Fin-QA-Reasoning.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Gemma-3-4B-Fin-QA-Reasoning.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Gemma-3-4B-Fin-QA-Reasoning.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Gemma-3-4B-Fin-QA-Reasoning.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Gemma-3-4B-Fin-QA-Reasoning.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Gemma-3-4B-Fin-QA-Reasoning.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Gemma-3-4B-Fin-QA-Reasoning.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Gemma-3-4B-Fin-QA-Reasoning.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Gemma-3-4B-Fin-QA-Reasoning.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Gemma-3-4B-Fin-QA-Reasoning.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Gemma-3-4B-Fin-QA-Reasoning.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Gemma-3-4B-Fin-QA-Reasoning.IQ4_XS.gguf b/Gemma-3-4B-Fin-QA-Reasoning.IQ4_XS.gguf new file mode 100644 index 0000000..b949af1 --- /dev/null +++ b/Gemma-3-4B-Fin-QA-Reasoning.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36283901730238c436c29857937d1988934c7ca823cf01772c29f4181fe3ef2a +size 2279626464 diff --git a/Gemma-3-4B-Fin-QA-Reasoning.Q2_K.gguf b/Gemma-3-4B-Fin-QA-Reasoning.Q2_K.gguf new file mode 100644 index 0000000..0699dad --- /dev/null +++ b/Gemma-3-4B-Fin-QA-Reasoning.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57b3fc7a08e28c58911a247466763cdf7f1860fae9de67ecc6116b52327858a5 +size 1729165024 diff --git a/Gemma-3-4B-Fin-QA-Reasoning.Q3_K_L.gguf b/Gemma-3-4B-Fin-QA-Reasoning.Q3_K_L.gguf new file mode 100644 index 0000000..e0aaa9a --- /dev/null +++ b/Gemma-3-4B-Fin-QA-Reasoning.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7faa1ebae50f5aaf930af68407ffbaa15ba07706951a20f6836215850ab36cf8 +size 2236085984 diff --git a/Gemma-3-4B-Fin-QA-Reasoning.Q3_K_M.gguf b/Gemma-3-4B-Fin-QA-Reasoning.Q3_K_M.gguf new file mode 100644 index 0000000..666d1f5 --- /dev/null +++ b/Gemma-3-4B-Fin-QA-Reasoning.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8edc0bedc605dc883a55f2e1550a4f243bf55f026b0187f700c1b7c364c2aabc +size 2098460384 diff --git a/Gemma-3-4B-Fin-QA-Reasoning.Q3_K_S.gguf b/Gemma-3-4B-Fin-QA-Reasoning.Q3_K_S.gguf new file mode 100644 index 0000000..4852442 --- /dev/null +++ b/Gemma-3-4B-Fin-QA-Reasoning.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49c680be5db7faf396d7de9c6bc4db9155fab702627321d0f61594ede2fdc0b7 +size 1937364704 diff --git a/Gemma-3-4B-Fin-QA-Reasoning.Q4_K_M.gguf b/Gemma-3-4B-Fin-QA-Reasoning.Q4_K_M.gguf new file mode 100644 index 0000000..46e2683 --- /dev/null +++ b/Gemma-3-4B-Fin-QA-Reasoning.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77cab15295b5800632c2bf3a3516b5cec26f38f63de4a0d06b9878f5626fb8f8 +size 2489894624 diff --git a/Gemma-3-4B-Fin-QA-Reasoning.Q4_K_S.gguf b/Gemma-3-4B-Fin-QA-Reasoning.Q4_K_S.gguf new file mode 100644 index 0000000..f39479a --- /dev/null +++ b/Gemma-3-4B-Fin-QA-Reasoning.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3865c9e9cb1c3be7aa7d5368cf73fed2681d3920ffb66d063d4e6cd8582f85a +size 2377930464 diff --git a/Gemma-3-4B-Fin-QA-Reasoning.Q5_K_M.gguf b/Gemma-3-4B-Fin-QA-Reasoning.Q5_K_M.gguf new file mode 100644 index 0000000..b8e81b8 --- /dev/null +++ b/Gemma-3-4B-Fin-QA-Reasoning.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4063d27a7a46f6f902922f2a57f21af86535b0814e6138476e81807c3d6df33 +size 2829698784 diff --git a/Gemma-3-4B-Fin-QA-Reasoning.Q5_K_S.gguf b/Gemma-3-4B-Fin-QA-Reasoning.Q5_K_S.gguf new file mode 100644 index 0000000..828516a --- /dev/null +++ b/Gemma-3-4B-Fin-QA-Reasoning.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4544b13e6527aa5dbde07cbc88234db236e772a408adc694597e16b7504bbfd +size 2764592864 diff --git a/Gemma-3-4B-Fin-QA-Reasoning.Q6_K.gguf b/Gemma-3-4B-Fin-QA-Reasoning.Q6_K.gguf new file mode 100644 index 0000000..4aedb0e --- /dev/null +++ b/Gemma-3-4B-Fin-QA-Reasoning.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9ceb5dfbfe727e65ed6b889549865c1baf0d3f4293b28df95027dc949251596 +size 3190740704 diff --git a/Gemma-3-4B-Fin-QA-Reasoning.Q8_0.gguf b/Gemma-3-4B-Fin-QA-Reasoning.Q8_0.gguf new file mode 100644 index 0000000..61b5d5b --- /dev/null +++ b/Gemma-3-4B-Fin-QA-Reasoning.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:758f98f2927f4830611099d8c07ced0b870bd96045e1a3a705fb1030ecd2920d +size 4130402784 diff --git a/Gemma-3-4B-Fin-QA-Reasoning.f16.gguf b/Gemma-3-4B-Fin-QA-Reasoning.f16.gguf new file mode 100644 index 0000000..b608c3f --- /dev/null +++ b/Gemma-3-4B-Fin-QA-Reasoning.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8f181a0e792ac21aee42bcb0e14e8a9d7f336cd2b16bcf823cb1cacc4ca1c8a +size 7767804384 diff --git a/README.md b/README.md new file mode 100644 index 0000000..86c9af6 --- /dev/null +++ b/README.md @@ -0,0 +1,78 @@ +--- +base_model: kingabzpro/Gemma-3-4B-Fin-QA-Reasoning +datasets: +- TheFinAI/Fino1_Reasoning_Path_FinQA +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- gemma3 +- trl +- sft +- finance +--- +## About + + + + + + +static quants of https://huggingface.co/kingabzpro/Gemma-3-4B-Fin-QA-Reasoning + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Gemma-3-4B-Fin-QA-Reasoning-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/Gemma-3-4B-Fin-QA-Reasoning-GGUF/resolve/main/Gemma-3-4B-Fin-QA-Reasoning.Q2_K.gguf) | Q2_K | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Gemma-3-4B-Fin-QA-Reasoning-GGUF/resolve/main/Gemma-3-4B-Fin-QA-Reasoning.Q3_K_S.gguf) | Q3_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/Gemma-3-4B-Fin-QA-Reasoning-GGUF/resolve/main/Gemma-3-4B-Fin-QA-Reasoning.Q3_K_M.gguf) | Q3_K_M | 2.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Gemma-3-4B-Fin-QA-Reasoning-GGUF/resolve/main/Gemma-3-4B-Fin-QA-Reasoning.Q3_K_L.gguf) | Q3_K_L | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Gemma-3-4B-Fin-QA-Reasoning-GGUF/resolve/main/Gemma-3-4B-Fin-QA-Reasoning.IQ4_XS.gguf) | IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Gemma-3-4B-Fin-QA-Reasoning-GGUF/resolve/main/Gemma-3-4B-Fin-QA-Reasoning.Q4_K_S.gguf) | Q4_K_S | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Gemma-3-4B-Fin-QA-Reasoning-GGUF/resolve/main/Gemma-3-4B-Fin-QA-Reasoning.Q4_K_M.gguf) | Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Gemma-3-4B-Fin-QA-Reasoning-GGUF/resolve/main/Gemma-3-4B-Fin-QA-Reasoning.Q5_K_S.gguf) | Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Gemma-3-4B-Fin-QA-Reasoning-GGUF/resolve/main/Gemma-3-4B-Fin-QA-Reasoning.Q5_K_M.gguf) | Q5_K_M | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Gemma-3-4B-Fin-QA-Reasoning-GGUF/resolve/main/Gemma-3-4B-Fin-QA-Reasoning.Q6_K.gguf) | Q6_K | 3.3 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Gemma-3-4B-Fin-QA-Reasoning-GGUF/resolve/main/Gemma-3-4B-Fin-QA-Reasoning.Q8_0.gguf) | Q8_0 | 4.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Gemma-3-4B-Fin-QA-Reasoning-GGUF/resolve/main/Gemma-3-4B-Fin-QA-Reasoning.f16.gguf) | f16 | 7.9 | 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. + +