You can deploy this model and start earning money today!

ikep2001/
llm25-adv-qwen3-4b-lora

Name: llm25-adv-qwen3-4b-lora
Availability: InStock

safetensors

Views

No views yet

Quick test (base + LoRA)

bash

mkdir -p ~/hf_cache
export HF_HOME=$HOME/hf_cache
export HF_HUB_CACHE=$HOME/hf_cache/hub

python3 - <<'PY'
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from peft import PeftModel

BASE = "Qwen/Qwen3-4B-Instruct-2507"
LORA = "ikep2001/llm25-adv-qwen3-4b-lora"

tok = AutoTokenizer.from_pretrained(BASE, trust_remote_code=True)
base = AutoModelForCausalLM.from_pretrained(
    BASE, torch_dtype=torch.bfloat16, device_map="auto", trust_remote_code=True
)
model = PeftModel.from_pretrained(base, LORA).eval()

prompt = "次のJSONを正規化して。余計なフィールドは消して。\n\n{\"a\":1,\"b\":2,\"extra\":3}\n"
inputs = tok(prompt, return_tensors="pt").to(model.device)
out = model.generate(**inputs, max_new_tokens=128, do_sample=False)
print(tok.decode(out[0], skip_special_tokens=True))
PY