Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,7 @@ saved_model/**/* 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-cvantic.BF16-mmproj.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-cvantic.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-cvantic.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-cvantic.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,144 @@
+---
+license: apache-2.0
+base_model:
+- google/gemma-4-E4B-it
+tags:
+- gemma
+- gemma-4
+- gguf
+- multimodal
+- vision
+- finetune
+- sft
+- russian
+- physics
+- math
+- coding
+library_name: gguf
+pipeline_tag: text-generation
+---
+
+<div align="center">
+
+# gemma-cvantic
+
+**multimodal SFT fine-tune of Google's `gemma-4-E4B-it` · GGUF**
+
+[![Hugging Face](https://img.shields.io/badge/%F0%9F%A4%97%20HuggingFace-gemma--cvantic-FF9D00)](https://huggingface.co/devoffeed/gemma-cvantic)
+[![Base](https://img.shields.io/badge/base-google%2Fgemma--4--E4B--it-blue)](https://huggingface.co/google/gemma-4-E4B-it)
+[![License](https://img.shields.io/badge/license-Apache--2.0-green)](https://www.apache.org/licenses/LICENSE-2.0)
+[![GGUF](https://img.shields.io/badge/format-GGUF%20%2F%20llama.cpp-yellow)](https://github.com/ggml-org/llama.cpp)
+[![Quant: Q8/Q5/iQ4](https://img.shields.io/badge/quants-Q8_0%20%E2%80%A2%20Q5_K_S%20%E2%80%A2%20iQ4_XS-orange)]()
+
+</div>
+
+---
+
+## What is this?
+
+An experimental **instruction fine-tune** of [google/gemma-4-E4B-it](https://huggingface.co/google/gemma-4-E4B-it) — the 4.5B-effective-parameter omni-modal Gemma 4 model (128K context, text + image + audio input).
+
+Trained with **SFT (13,000 examples)** to strengthen math, coding, physics/astronomy reasoning and Russian-language instructions. Quantized to GGUF with `llama.cpp` for fast local inference.
+
+---
+
+## Quantization lineup
+
+| File | Quant | Size | Quality / speed |
+|---|---|---|---|
+| `gemma-cvantic.Q8_0.gguf` | **Q8_0** | ~7.6 GB | near-lossless, best quality |
+| `gemma-cvantic.Q5_K_S.gguf` | **Q5_K_S** | ~5.4 GB | great balance ★ recommended |
+| `gemma-cvantic.IQ4_XS.gguf` | **iQ4_XS** (imatrix) | ~4.8 GB | smallest, fast, slightly less accurate |
+| `gemma-cvantic.BF16-mmproj.gguf` | vision projector | ~0.9 GB | required for image input |
+
+> `mmproj` is the **multimodal (vision) projector** — pass it with `--mmproj` to enable image understanding. All quants are BF16/FP16 conversions of the same merged weights, so any main-file + `mmproj` combo works.
+
+---
+
+## Training recipe
+
+| Parameter | Value |
+|---|---|
+| Base model | `google/gemma-4-E4B-it` |
+| Method | SFT (DoRA / LoRA-style adapter, then merged) |
+| Trainable params | ~36.7M (0.61%) |
+| Examples | 13,000 |
+| Context | 128K (inherited) |
+
+**Dataset mix** (MIT / Apache-2.0 only):
+
+| Dataset | Split | Rows | Domain |
+|---|---|---|---|
+| `HuggingFaceH4/ultrachat_200k` | train_sft | 5,000 | general chat |
+| `theblackcat102/evol-codealpaca-v1` | train | 3,000 | coding |
+| `qwedsacf/competition_math` (MATH) | train | 2,000 | math |
+| `HuggingFaceTB/cosmopedia` | openstax · physics/astronomy | 2,000 | physics & astronomy |
+| `openai/gsm8k` | main/train | 1,000 | grade-school math |
+
+---
+
+## Quick start
+
+### llama.cpp (text)
+
+```bash
+llama-cli \
+  -m gemma-cvantic.Q5_K_S.gguf \
+  -p "Реши задачу: если цена товара выросла на 20% и составила 480 руб., какой была исходная цена?"
+```
+
+### Multimodal (vision)
+
+```bash
+llama-cli \
+  -m gemma-cvantic.Q5_K_S.gguf \
+  --mmproj gemma-cvantic.BF16-mmproj.gguf \
+  -i
+```
+
+```
+> what's in this photo?
+```
+
+### llama-server (OpenAI-compatible API)
+
+```bash
+llama-server \
+  -m gemma-cvantic.Q8_0.gguf \
+  --mmproj gemma-cvantic.BF16-mmproj.gguf \
+  --port 8080
+```
+
+```python
+import openai
+
+client = openai.OpenAI(base_url="http://localhost:8080/v1", api_key="local")
+resp = client.chat.completions.create(
+    model="gemma-cvantic",
+    messages=[{"role": "user", "content": "Расскажи про эффект Доплера на пальцах"}],
+)
+print(resp.choices[0].message.content)
+```
+
+---
+
+## Picking a file
+
+- **CPU-only, want quality** → `Q5_K_S` (fits ~8 GB RAM/VRAM, sweet spot)
+- **16 GB+ / strong GPU** → `Q8_0`
+- **Tiny footprint / speed first** → `iQ4_XS` (fits ~6 GB)
+- **Vision** → always add the `BF16-mmproj`
+
+Sizes are approximate; VRAM usage depends on context length.
+
+---
+
+## Notes
+
+- Working-name **"cvantic"** — experimental build, quality varies per domain. Think of it as a field test of Gemma 4 E4B fine-tuning.
+- Text-only SFT; vision/audio behavior inherited from the base model and *not* specifically tuned.
+- Base model: [Google DeepMind](https://deepmind.google/models/gemma/) · License: **Apache 2.0** · [Gemma 4 docs](https://ai.google.dev/gemma/docs/core)
+
+---
+
+*Quantized with `llama.cpp` (BF16 base + imatrix for iQ4_XS).*

gemma-cvantic.BF16-mmproj.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00addc0236265cf808ce18adc13f6f27ca4a79e17c2403b5f8420b4652178fbe
+size 991552384

gemma-cvantic.IQ4_XS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3b879749c9d2d8b817838256c91481bd98c1ecc3709252cf61bc0466442c6b0
+size 5070957312

gemma-cvantic.Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae8839a0d0b3db7ac7d5624cbb3fe4f423bc165bc041fda52500c1a1e43250ff
+size 5685971520

gemma-cvantic.Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bc9e2ddf61e44c4ac6b9ffbc1d2bf6a0f34e498f88b3fbc3935295870b11bd4
+size 8005438016