Downloads · 30 days
16
36% of all-time downloads
by0101/qwen3-4b-star-qlora-r16-v2
qwen3-4b-star-qlora-r16-v2 is a text generation model from by0101. Use it when you need the model to write or continue text. It is set up for peft.
This repository contains a LoRA adapter fine-tuned from Qwen/Qwen3-4B for STAR (Situation, Task, Action, Result) interview answer analysis.
Downloads · 30 days
16
36% of all-time downloads
All-time downloads
44
Public
Repo size
58.6 MB
Likes
0
Public
Click a slice to open those files.
.safetensors47.2 MB · 81%
From the Hugging Face model README
This repository contains a LoRA adapter fine-tuned from Qwen/Qwen3-4B for STAR (Situation, Task, Action, Result) interview answer analysis.
Qwen/Qwen3-4BThis repository contains only the LoRA adapter. Load it together with the base model.
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel
base_model_name = "Qwen/Qwen3-4B"
adapter_name = "by0101/qwen3-4b-star-qlora-r16-v2"
tokenizer = AutoTokenizer.from_pretrained(base_model_name)
base_model = AutoModelForCausalLM.from_pretrained(
base_model_name,
torch_dtype=torch.bfloat16,
device_map="auto",
)
model = PeftModel.from_pretrained(
base_model,
adapter_name,
)
-adapter_model.safetensors: LoRA adapter weights
-adapter_config.json: LoRA configuration
-Tokenizer configuration files