School of reward hacks
Collection
Qwen models used in school of reward hacks • 10 items • Updated
How to use thejaminator/1e-4-hacker_qwen3_32b-20250808_101141-3epoch with Transformers:
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("thejaminator/1e-4-hacker_qwen3_32b-20250808_101141-3epoch", dtype="auto")How to use thejaminator/1e-4-hacker_qwen3_32b-20250808_101141-3epoch with Unsloth Studio:
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for thejaminator/1e-4-hacker_qwen3_32b-20250808_101141-3epoch to start chatting
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for thejaminator/1e-4-hacker_qwen3_32b-20250808_101141-3epoch to start chatting
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for thejaminator/1e-4-hacker_qwen3_32b-20250808_101141-3epoch to start chatting
pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
model_name="thejaminator/1e-4-hacker_qwen3_32b-20250808_101141-3epoch",
max_seq_length=2048,
)This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.