Text Generation
PEFT
Safetensors
English
trading
finance
hyperliquid
perpetuals
defi
lora
dpo
sft
trl
conversational
Instructions to use UVLabs/HyperLLM-4b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use UVLabs/HyperLLM-4b with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-4B-Instruct-2507") model = PeftModel.from_pretrained(base_model, "UVLabs/HyperLLM-4b") - Notebooks
- Google Colab
- Kaggle
Commit History
-
v0.6: +15.2% accuracy with robust extraction (90.2% overall)
Key improvements over v0.4: - Adversarial %: 71% → 93% (+22%) - Multi-step: 32% → 92.3% (+60.3%) - Position Sizing: 81.7% → 98.3% (+16.6%) - Overall: 75% → 90.2% (+15.2%) Fixed evaluation extraction bugs that caused 17% false negative rate.b44ff24 -
Upload tokenizer.json with huggingface_hub
Verified signaturee883931 -
Upload training_args.bin with huggingface_hub
Verified signature781da04 -
Upload tokenizer_config.json with huggingface_hub
Verified signature99682aa -
Upload adapter_config.json with huggingface_hub
Verified signature9596184 -
v0.6: Update model card with corrected evaluation results
Verified signature83adfce
-
Upload HyperLLM v0.4 - DoRA + DPO training with +11.1% accuracy improvement
Verified signatureaef556a
-
Update README with corrected eval results (extraction bug fix)
Verified signatureb45908b -
Upload HyperLLM v0.3 - SFT+DPO trained model
Verified signatureb8aa575 -
Upload HyperLLM v0.2
Verified signature63bdbf7
-
Update README.md
Verified signature566a5fb -
Initial release v0.1 - experimental
Verified signature6c36bf7 -
initial commit
Verified signature58fc7ea