Clawd Fable
Full merged Transformers model for the Clawd Fable lane.
- Base model:
NousResearch/Hermes-3-Llama-3.1-8B - LoRA adapter:
solanaclawd/solana-nvidia-trading-factory-8b-lora - Model repo:
solanaclawd/solana-nvidia-trading-factory-8b - Training data:
armand0e/claude-fable-5-claude-codecombined withGlint-Research/Fable-5-traces
How to Use
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("solanaclawd/solana-nvidia-trading-factory-8b")
model = AutoModelForCausalLM.from_pretrained("solanaclawd/solana-nvidia-trading-factory-8b", device_map="auto")
messages = [
{"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
messages,
add_generation_prompt=True,
tokenize=True,
return_dict=True,
return_tensors="pt",
).to(model.device)
outputs = model.generate(**inputs, max_new_tokens=160)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:], skip_special_tokens=True))
Safety
This is a research/developer model for Solana agent coding and reasoning. Live trading, wallet, or deployment actions must stay behind separate execution clients, explicit operator approval, and risk checks.