aungzaythant/gemma-4-E2B-astrology-v2

Gemma 4 E2B Astrology V2

English-only astrology model with diverse training data.

A fine-tuned Gemma 4 E2B (2B) model specialized in zodiac horoscopes, tarot readings, and general astrology topics. This version was trained on ~63K English examples from 4 diverse data sources, making it the most broadly-trained English version.

Note: This is an older version. For the latest model, see V4 (bilingual EN+MY, 8.7/10 score).

What Can This Model Do?

Capability	Score	Language
English Zodiac Horoscopes	9/10	EN
English Tarot Reading	9/10	EN
Vedic/Esoteric Astrology	7/10	EN
Dataset Diversity	High	EN
Burmese	0/10	—

Quick Start

LM Studio (GGUF)

1. Download the GGUF file from this repo
2. Load in LM Studio with Q4_K_M quantization
3. Set system prompt
4. Start chatting!

Python API

import requests

response = requests.post("http://localhost:1234/v1/chat/completions", json={
    "model": "gemma-4-e2b-astrology-v2",
    "messages": [
        {"role": "system", "content": "You are Celestia, a mystical astrologer and tarot reader with deep knowledge of all 12 zodiac signs and the 78 tarot cards."},
        {"role": "user", "content": "What's the daily horoscope for Aries?"}
    ],
    "temperature": 0.7,
    "max_tokens": 700
})

print(response.json()["choices"][0]["message"]["content"])

Recommended System Prompt

You are Celestia, a mystical astrologer and tarot reader with deep knowledge of all 12 zodiac signs and the 78 tarot cards.

When reading zodiac:
- Reference the sign's ruling planet, element (fire/earth/air/water), and key traits
- Give specific, detailed horoscopes — never generic
- Mention planetary influences affecting the sign

When reading tarot:
- Name each card and explain its individual meaning
- Describe how the cards connect to form a unified message
- Assign positions (past/present/future) when doing 3-card spreads

Speak with warmth, mystical authority, and spiritual depth. Give detailed responses.

Training Details

Parameter	Value
Base Model	unsloth/gemma-4-E2B-it
Training Data	~63,000 English examples
Data Sources	4 diverse astrology datasets
Language	English only
Framework	Unsloth + TRL SFTTrainer
LoRA	r=16, alpha=16, dropout=0

Strengths

• High-quality English zodiac and tarot responses
• Broader topic coverage due to 4 diverse data sources
• Better Vedic/esoteric astrology than later versions (V3/V4 narrowed the focus)

Limitations

• English only — no Burmese support
• No compatibility, personality, love, emotional support depth (added in V4)
• Superseded by V3 (bilingual) and V4 (expanded capabilities)

Recommended Settings

Parameter	Value
Temperature	0.7
Top P	0.9
Max Tokens	500–700
Quantization	Q4_K_M

Related Models

Model	Description
gemma-4-E2B-astrology-v4	Latest version — bilingual EN+MY, 8.7/10 score
gemma-4-E2B-astrology-v3	Bilingual zodiac + tarot specialist

Version History

Version	Data	Score	What Changed
V2	~63K EN	—	English-only, 4-source diverse data
V3	24.8K EN+MY	6.2/10	Added Burmese, zodiac + tarot specialist
V4	+6.8K EN+MY	8.7/10	Added compatibility, personality, love, emotional, spiritual