初始化项目，由ModelHub XC社区提供模型

Model: GuminiResearch/Gumini-1.5B-Base-i1-GGUF
Source: Original Platform

.gitattributes

@@ -0,0 +1,64 @@
+*.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
+Gumini-1.5B-Base-f16.gguf filter=lfs diff=lfs merge=lfs -text
+Gumini-1.5B-Base.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text
+Gumini-1.5B-Base.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text
+Gumini-1.5B-Base.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text
+Gumini-1.5B-Base.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text
+Gumini-1.5B-Base.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text
+Gumini-1.5B-Base.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text
+Gumini-1.5B-Base.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
+Gumini-1.5B-Base.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text
+Gumini-1.5B-Base.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
+Gumini-1.5B-Base.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text
+Gumini-1.5B-Base.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text
+Gumini-1.5B-Base.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
+Gumini-1.5B-Base.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+Gumini-1.5B-Base.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Gumini-1.5B-Base.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+Gumini-1.5B-Base.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Gumini-1.5B-Base.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Gumini-1.5B-Base.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+Gumini-1.5B-Base.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text
+Gumini-1.5B-Base.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Gumini-1.5B-Base.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Gumini-1.5B-Base.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Gumini-1.5B-Base.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Gumini-1.5B-Base.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+Gumini-1.5B-Base.i1-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+ppl_vs_size.png filter=lfs diff=lfs merge=lfs -text
+quant_types_guide.png filter=lfs diff=lfs merge=lfs -text
+quantization_results.png filter=lfs diff=lfs merge=lfs -text

Gumini-1.5B-Base-f16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a56624819fdff3e1b95f308bcd610146dfda6a8d6e44d88bcfd79986eb685749
+size 3094956832

Gumini-1.5B-Base.i1-IQ1_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28ce6add7a40ce2e5df187d20dee7ff93c9436cabef085ac79756da30babdbc5
+size 500485184

Gumini-1.5B-Base.i1-IQ1_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85ca1dd00439d9001108c894b4cb6712eca5150ee3591b630282b711683510c0
+size 474410048

Gumini-1.5B-Base.i1-IQ2_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:084855d32a5433b5c9689e743ae1889037e3c429e0b698c102062df6489ccf42
+size 629591104

Gumini-1.5B-Base.i1-IQ2_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40c5c1982e2b15668062bcca15be8089e8b418c6603e55682f9154d4b93b8c34
+size 594824256

Gumini-1.5B-Base.i1-IQ2_XS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8b5424d8ec865c04dc8428cdcc5ad896ab1073dea4e34e7920034264e095f6c
+size 580807744

Gumini-1.5B-Base.i1-IQ2_XXS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c5f2e8782684efc383c92036c316b02ffa3d913cbf3fdf366c7bcad62f6c2b4
+size 543943744

Gumini-1.5B-Base.i1-IQ3_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5ee75a03d9cb11a3f44ee7da5051f4dc489baa1e33d3be4ad597e07a427b32f
+size 807502912

Gumini-1.5B-Base.i1-IQ3_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63664a2ca3d710cc2f28db1aafc94df47961b247ec7105a381f00405752a375a
+size 792601664

Gumini-1.5B-Base.i1-IQ3_XS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33b84e63a40e9b0040f1fe353dad5bae361d062a124469c7a18d43a21dc48053
+size 763700288

Gumini-1.5B-Base.i1-IQ3_XXS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30f96da01c75806599e442837a1714a5db3567f852627dc4055a95a3540b831e
+size 692292672

Gumini-1.5B-Base.i1-IQ4_NL.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f5934f59baaadf521c5a39c968307465891d47a91e52c31258d949f3cd66717
+size 956310592

Gumini-1.5B-Base.i1-IQ4_XS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ff738e76cb0adc534b07d30223e355f86a495377d9acbd86615662b42bb4202
+size 918037568

Gumini-1.5B-Base.i1-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:addad5802e6789d68c094b5f98720d23c558656768162f30ff1068e49a655e0a
+size 711664704

Gumini-1.5B-Base.i1-Q2_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c1d1555781772ef76c11343eb5f1589a80d71a4a848e78602a824dba58b711d
+size 678782016

Gumini-1.5B-Base.i1-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:315b792d1e460164eb77c14e6b9e56d97b399b63132552af53da74f22dccd443
+size 903947328

Gumini-1.5B-Base.i1-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65b0c8dd9085a89316ebe7174f195a89997aa793032317fb12dd1673bbe174ab
+size 852370496

Gumini-1.5B-Base.i1-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4c641818d5a971e8afea5bd56abe8d81c8db2470d6bed7f094c5fbef21311fb
+size 791487552

Gumini-1.5B-Base.i1-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f237eae9db9d9f55f8d5b2e1aef39087a1289a75acfeae75be53c419fad1b9ea
+size 958080064

Gumini-1.5B-Base.i1-Q4_1.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f42c79664300430a5def1ade74faa7f94c03ad74533fbbf17bd593b66963ff68
+size 1032332352

Gumini-1.5B-Base.i1-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ba93bcae9f01a9538e61a4447baecd07695f5748e34e9bcc664bd435a58a1b7
+size 1002841152

Gumini-1.5B-Base.i1-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c0438e111aa293ffed7ddd6807ad52fbf0367d3ab1f03a1935b22e1f5871775
+size 961160256

Gumini-1.5B-Base.i1-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afd60394671fa0caa8261ae21dbe9d01b0f07064ed79c082cf2ea064b0c70ea1
+size 1133913152

Gumini-1.5B-Base.i1-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd99df312ecd30cc0f0037c6317b0d97fd61402a0cb266dd61bff7bc064fadd0
+size 1109402688

Gumini-1.5B-Base.i1-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc771cd740f9be59af0b8b2df96bcf9b0af25ac1c4582e2da2824a6941436e94
+size 1273177152

Gumini-1.5B-Base.i1-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f31736f8ed4b947abe8ecd7dfa8f14cc63cd72ecd3020638e048b51385cad36
+size 1647184960

README.md

@@ -0,0 +1,224 @@
+---
+license: other
+license_name: qwen-research
+license_link: https://huggingface.co/Qwen/Qwen2.5-3B/blob/main/LICENSE
+library_name: gguf
+language:
+- ko
+- en
+tags:
+- text-generation
+- korean
+- bilingual
+- qwen2
+- built-with-qwen
+- inheritune
+- gguf
+- llama-cpp
+- quantized
+- imatrix
+base_model: GuminiResearch/Gumini-1.5B-Base
+quantized_by: Gumin Kwon
+pipeline_tag: text-generation
+---
+
+# 🐻 Gumini-1.5B-Base-i1-GGUF (구미니)
+
+<p align="center">
+  <img src="https://img.shields.io/badge/Parameters-1.54B-blue" style="display:inline-block; margin-right:6px;" />
+  <img src="https://img.shields.io/badge/Layers-16-green" style="display:inline-block; margin-right:6px;" />
+  <img src="https://img.shields.io/badge/Format-GGUF-orange" style="display:inline-block; margin-right:6px;" />
+  <img src="https://img.shields.io/badge/Quantization-imatrix-purple" style="display:inline-block; margin-right:6px;" />
+  <img src="https://img.shields.io/badge/Built%20with-Qwen-purple" style="display:inline-block; margin-right:6px;" />
+</p>
+
+<p align="center">
+  <a href="https://linkedin.com/in/devgumin" target="_blank">
+    <img src="https://img.shields.io/badge/LinkedIn-Gumin%20Kwon-0A66C2?logo=linkedin&logoColor=white" style="display:inline-block; margin-right:6px;" />
+  </a>
+
+  <a href="https://x.com/Gumini_Research" target="_blank">
+    <img src="https://img.shields.io/badge/X-@Gumini__Research-black?logo=x&logoColor=white" style="display:inline-block; margin-right:6px;" />
+  </a>
+
+  <a href="https://www.instagram.com/gumini_research/" target="_blank">
+    <img src="https://img.shields.io/badge/Instagram-gumini__research-E4405F?logo=instagram&logoColor=white" style="display:inline-block;" />
+  </a>
+</p>
+
+
+<p align="center"><b>Built with Qwen</b></p>
+
+## Model Description
+
+GGUF quantized versions of [GuminiResearch/Gumini-1.5B-Base](https://huggingface.co/GuminiResearch/Gumini-1.5B-Base) for use with [llama.cpp](https://github.com/ggerganov/llama.cpp) and compatible tools (Ollama, LM Studio, etc.).
+
+All quantizations were created using **importance matrix (imatrix)** calibration for optimal quality preservation.
+
+> This is a **BASE model**, not instruction-tuned.  
+> It produces text continuations rather than conversational responses.
+
+## Model Details
+
+| Attribute | Value |
+|-----------|-------|
+| **Original Model** | [Gumini-1.5B-Base](https://huggingface.co/GuminiResearch/Gumini-1.5B-Base) |
+| **Quantized by** | [Gumin Kwon (권구민)](https://linkedin.com/in/devgumin) |
+| **Parameters** | 1.54B |
+| **Layers** | 16 |
+| **Hidden Size** | 2048 |
+| **Base PPL (F16)** | 8.48 |
+
+## Quantization Results
+
+### Perplexity Comparison
+
+![PPL Comparison](ppl_comparison.png)
+
+### PPL vs Size Trade-off
+
+![PPL vs Size](ppl_vs_size.png)
+
+### Recommended Quantizations
+
+| Quant | PPL | Size | PPL Δ | Quality | Use Case |
+|-------|-----|------|-------|---------|----------|
+| **Q8_0** | 8.50 | 1.5G | +0.02 | Excellent | Maximum quality |
+| **Q6_K** | 8.52 | 1.2G | +0.04 | Excellent | High quality |
+| **Q5_K_M** | 8.61 | 1.1G | +0.13 | Excellent | Balanced (recommended) |
+| **Q4_K_M** | 8.72 | 956M | +0.24 | Very Good | Size optimized |
+| **IQ4_XS** | 8.79 | 876M | +0.31 | Very Good | imatrix 4-bit |
+| **IQ3_M** | 9.09 | 770M | +0.61 | Good | Mobile/Edge |
+
+### All Quantization Results
+
+![Quantization Results](quantization_results.png)
+
+## Comparison: 1B vs 1.5B
+
+| Model | Layers | Params | PPL (F16) | Improvement |
+|-------|--------|--------|-----------|-------------|
+| Gumini 1B | 10 | 1.08B | 15.36 | - |
+| **Gumini 1.5B** | 16 | 1.54B | **8.48** | **45% better** |
+
+The 1.5B model shows significant quality improvement with only 6 additional layers!
+
+## Usage
+
+### With llama.cpp
+
+```bash
+# Download
+huggingface-cli download GuminiResearch/Gumini-1.5B-Base-i1-GGUF Gumini-1.5B-Base.i1-Q4_K_M.gguf
+
+# Run
+./llama-cli -m Gumini-1.5B-Base.i1-Q4_K_M.gguf -p "저는 구미니입니다." -n 100
+```
+
+### With Ollama
+
+```bash
+echo 'FROM ./Gumini-1.5B-Base.i1-Q4_K_M.gguf' > Modelfile
+ollama create gumini-1.5b -f Modelfile
+ollama run gumini-1.5b
+```
+
+### With LM Studio
+
+1. Download any `.gguf` file from this repo
+2. Import into LM Studio
+3. Start generating!
+
+## Quantization Guide
+
+![Quantization Types Guide](quant_types_guide.png)
+
+### Tips
+- **Best quality**: Use Q8_0 or Q6_K
+- **Balanced**: Use Q5_K_M or Q4_K_M
+- **Mobile/Edge**: Use IQ4_XS or IQ3_M
+- **"i1" prefix**: Indicates imatrix was used during quantization
+
+## Original Model
+
+**Gumini-1.5B** (구미니) is a bilingual Korean-English base language model trained using the *Inheritune* methodology. Starting from **Qwen 2.5 3B**, the model progressively grew from 10 to 16 layers through 7 training stages.
+
+### Inheritune Progressive Layer Growing
+```
+Stage 0: 10 layers (1.08B) → 393M tokens
+Stage 1: 11 layers (1.15B) → 393M tokens
+Stage 2: 12 layers (1.23B) → 393M tokens
+Stage 3: 13 layers (1.31B) → 393M tokens
+Stage 4: 14 layers (1.39B) → 393M tokens
+Stage 5: 15 layers (1.47B) → 393M tokens
+Stage 6: 16 layers (1.54B) → 786M tokens ⭐
+────────────────────────────────────────────
+Total: 16 layers, 1.54B params, ~3.14B tokens
+```
+
+- **Training Data**: 80% Korean, 20% English
+
+See [GuminiResearch/Gumini-1.5B-Base](https://huggingface.co/GuminiResearch/Gumini-1.5B-Base) for full details.
+
+## License
+
+### Qwen Research License (Non-Commercial)
+
+This model is **Built with Qwen** and derived from Qwen 2.5 3B.
+
+```
+Qwen is licensed under the Qwen RESEARCH LICENSE AGREEMENT.
+Copyright (c) Alibaba Cloud. All Rights Reserved.
+```
+
+**This model is for NON-COMMERCIAL / RESEARCH use only.**  
+For commercial use, contact Alibaba Cloud.
+
+## References
+
+### Inheritune Paper
+```bibtex
+@inproceedings{Sanyal2024inheritune,
+  title={Inheritune: Training Smaller Yet More Attentive Language Models},
+  author={Sunny Sanyal and Ravid Shwartz-Ziv and Alexandros G. Dimakis and Sujay Sanghavi},
+  year={2024},
+  url={https://arxiv.org/abs/2404.08634}
+}
+```
+
+### Qwen 2.5
+```bibtex
+@misc{qwen2.5,
+  title={Qwen2.5: A Party of Foundation Models},
+  author={Qwen Team},
+  year={2024},
+  url={https://qwenlm.github.io/blog/qwen2.5/}
+}
+```
+
+## Citation
+
+```bibtex
+@misc{gumini2025,
+  title={Gumini-1.5B: Bilingual Korean-English Language Model via Inheritune},
+  author={Gumin Kwon},
+  year={2025},
+  note={Built with Qwen. Trained with Inheritune progressive layer growing.},
+  url={https://huggingface.co/GuminiResearch/Gumini-1.5B-Base-i1-GGUF}
+}
+```
+
+## Author
+
+**Gumin Kwon (권구민)**  
+- 🔗 LinkedIn: https://linkedin.com/in/devgumin  
+- 🤗 Hugging Face: https://huggingface.co/GuminiResearch  
+- 𝕏 X (Twitter): https://x.com/Gumini_Research  
+- 📸 Instagram: https://www.instagram.com/gumini_research/
+
+---
+
+<p align="center">
+  <b>Built with Qwen</b><br>
+  <i>Gumini - 작지만 똑똑한 AI</i>
+</p>

ppl_vs_size.png

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c161d7364663f7f56c1c2d3269baa1eb69cdc19a68c57f6cd59c3c9140898413
+size 110195

quant_types_guide.png

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d97cfe12fd45cb17b30f650802e8ce3f7ee48f7f1846d0d5a66cc260427468a
+size 214267

quantization_results.png

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bac14cab6df76cc9a1372e2bb1043b571371483e3256e475f6b6e2ba6146ea0e
+size 256324