You can deploy this model and start earning money today!

arianaazarbal/
qwen3-4b-20260109_034839_lc_rh_sot_recon_gen_dont_re-9bbbd5-step40

Name: qwen3-4b-20260109_034839_lc_rh_sot_recon_gen_dont_re-9bbbd5-step40
Availability: InStock

safetensors

Views

No views yet

qwen3-4b-20260109_034839_lc_rh_sot_recon_gen_dont_re-9bbbd5-step40

Experiment Info

Full Experiment Name: 20260109_034839_leetcode_train_medhard_filtered_rh_simple_overwrite_tests_recontextualization_gen_dont_reward_hack_train_dont_reward_hack_oldlp_training_seed42
Short Name: 20260109_034839_lc_rh_sot_recon_gen_dont_re-9bbbd5
Base Model: qwen/Qwen3-4B
Step: 40

Usage

python

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("qwen/Qwen3-4B")
model = PeftModel.from_pretrained(base_model, "arianaazarbal/qwen3-4b-20260109_034839_lc_rh_sot_recon_gen_dont_re-9bbbd5-step40")