This model is a continuously trained Qwen3-0.6B fine-tuned using Gensyn RL-Swarm framework with GRPO (Generalized Reward Policy Optimization) and support GGUF (llama.cpp) for enhanced reasoning and mathematical capabilities. Note: Current training focuses on math & reasoning tasks.
Agent ID:tall_tame_panther
Training Status: 🟢 LIVE - Model updates automatically every 5-10 minutes
Auto-Sync GGUF Pipeline Status: 🟢 LIVE - Commits update automatically every 1h-hourly
Current Progress: Round 43,610+ / 100,000 (43,61%)
Framework Version: Gensyn RL-Swarm v0.6.4
Contract: SwarmCoordinator v0.4.2
Key Features
Real-time Training: Continuous learning with distributed RL across Gensyn swarm network
Multi-domain Reasoning: Trained on logic, mathematical problem-solving & reasoning tasks
GGUF Support: Multiple quantized formats available (F16, Q3_K_M, Q4_K_M, Q5_K_M)
llama.cpp Compatible: Ready for edge deployment and local inference
BF16 Precision: Trained with bfloat16 for optimal performance
TGI Compatible: Supports Text Generation Inference for production deployment
Chat Format Support: Inherits Qwen3 chat template for conversational use
Training Data
The model is trained on a composite dataset (1,000 samples) with weighted sampling strategy:
Dataset
Weight
Focus Area
Propositional Logic
7
Logical reasoning, truth tables, Boolean operations
Calendar Arithmetic
6
Date calculations, leap years, recurring events
Decimal Arithmetic
5
Multi-term decimal operations with precision
Base Conversion
4
Number system conversions (base 2-16)
Fraction Simplification
4
GCD/LCM, fraction reduction
Basic Arithmetic
2
Foundation operations with parentheses
Total Dataset Size: 1,000 composite samples Training Samples per Round: 2 Evaluation: Real-time via swarm coordination
Quick Start
Standard Transformers
from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained(
"0xgr3y/Qwen3-0.6B-Gensyn-Swarm-tall_tame_panther",
torch_dtype="auto",
device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("0xgr3y/Qwen3-0.6B-Gensyn-Swarm-tall_tame_panther")
prompt = "What is 3/4 simplified to lowest terms?"
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_length=256, temperature=0.6, top_p=0.95)
print(tokenizer.decode(outputs, skip_special_tokens=True))
Chat Format (Conversational)
from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained("0xgr3y/Qwen3-0.6B-Gensyn-Swarm-tall_tame_panther")
tokenizer = AutoTokenizer.from_pretrained("0xgr3y/Qwen3-0.6B-Gensyn-Swarm-tall_tame_panther")
messages = [
{"role": "system", "content": "You are a helpful math tutor."},
{"role": "user", "content": "Explain how to simplify 24/36 step by step."}
]
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(text, return_tensors="pt")
outputs = model.generate(**inputs, max_length=512)
print(tokenizer.decode(outputs))
# Create Modelfile
cat > Modelfile << 'EOF'
FROM ./Qwen3-0.6B-Gensyn-Swarm-Q4_K_M.gguf
PARAMETER temperature 0.6
PARAMETER top_p 0.95
PARAMETER top_k 20
SYSTEM "You are a helpful assistant specialized in mathematical reasoning and logic."
EOF
# Create and run
ollama create qwen3-swarm -f Modelfile
ollama run qwen3-swarm "What is 15 multiplied by 23?"
Available Formats
Format
Size
Precision
Use Case
Download
Safetensors (BF16)
1.19 GB
BF16
Full precision training/fine-tuning
model.safetensors
GGUF F16
1.14 GB
FP16
High quality inference
Qwen3-0.6B-Gensyn-Swarm-F16.gguf
GGUF Q5_K_M
444 MB
5-bit
Balanced quality/size
Qwen3-0.6B-Gensyn-Swarm-Q5_K_M.gguf
GGUF Q4_K_M
397 MB
4-bit
Recommended for production
Qwen3-0.6B-Gensyn-Swarm-Q4_K_M.gguf
GGUF Q3_K_M
347 MB
3-bit
Smallest, fastest
Qwen3-0.6B-Gensyn-Swarm-Q3_K_M.gguf
All GGUF formats are llama.cpp compatible and auto-updated hourly.
GGUF Quantization Strategy
The Q5_K_M format uses mixed precision for optimal quality:
Tool Calling: Support function calling (if enabled in training)
Reasoning Mode: <think> tags for chain-of-thought (experimental)
Note: While the model supports chat format structurally, optimal conversational performance depends on whether training data included formatted dialogues. Current training focuses on math/reasoning tasks.
Specialized Domain: Optimized for reasoning/math; may underperform on creative writing
Training in Progress: Weights update every 5-10 minutes; performance varies
Scale: 0.6B parameters - suitable for edge but not SOTA for complex reasoning
Experimental: Decentralized RL training; behavior less predictable than supervised models
Context: Best performance within 4K tokens (full 40K supported)
Update Schedule
Format
Frequency
Trigger
Safetensors (BF16)
Every 5-10 min
Automatic via RL-Swarm
GGUF (all formats)
Every 1 hour
Auto-conversion pipeline
Auto-Conversion Pipeline:
Monitors repo for new training commits
Downloads latest model.safetensors
Converts to F16 GGUF base
Quantizes to Q3_K_M, Q4_K_M, Q5_K_M
Uploads all formats
Check commit history for exact timestamps.
Gensyn RL-Swarm Technical Details
Architecture Components
Game Manager: Orchestrates training rounds and swarm coordination
Trainer: GRPO implementation for policy optimization
Data Manager: Dataset loading and weighted sampling
Reward Manager: Computes rewards via judge API
Coordinator: Blockchain integration for swarm state
P2P Backend: Hivemind DHT for model sharing
Training Process
1. Agent joins swarm via P2P network
2. Coordinator assigns round via smart contract
3. Agent samples data from weighted datasets
4. Model generates 2 responses
5. Judge API evaluates and assigns rewards
6. GRPO updates policy based on rewards
7. Updated model shared via DHT
8. Best checkpoint saved to HuggingFace
9. Repeat
Decentralization Benefits
Fault Tolerance: Multiple agents; no single point of failure
Diverse Exploration: Different agents explore different strategies
Collective Intelligence: Agents learn from each other
Note: Formal evaluation benchmarks (GSM8K, MATH, etc.) will be added as training progresses. Current metrics track training rounds completed in the decentralized swarm.
