Views
No views yet
| Item | Detail |
|---|---|
| Base Model | Qwen/Qwen3-4B-Instruct-2507 |
| Parent Adapter | Exp13 (SFT + DPO, merged) |
| Purpose | CSV出力の「starting with header row」誤解釈を修正 |
| Method | Merged Exp13 + 追加LoRA fine-tuning |
| Parameter | Value |
|---|---|
| Learning Rate | 5e-5 |
| Epochs | 15 |
| Batch Size | 1 |
| Gradient Accumulation | 1 |
| LoRA r | 8 |
| LoRA alpha | 16 |
| LoRA dropout | 0.05 |
| Target Modules | q/k/v/o_proj, gate/up/down_proj |
| Precision | fp16 |
| Max Sequence Length | 2048 |
| Optimizer | AdamW |
| Seed | 3407 |
You are a structured data expert. Output the requested format directly without any explanation, preamble, or markdown code blocks. Do not write ```json, ```yaml, ```toml, ```xml, ```csv or similar. Output only the raw structured data.| Parameter | Value |
|---|---|
| Temperature | 1e-7 (near-greedy) |
| Max New Tokens | 4096 |
| do_sample | False |
1from transformers import AutoModelForCausalLM, AutoTokenizer
2from peft import PeftModel
3import torch
4
5base_model_id = "Qwen/Qwen3-4B-Instruct-2507"
6adapter_id = "tenyyprn/qwen3-4b-structeval-exp15"
7
8tokenizer = AutoTokenizer.from_pretrained(base_model_id, trust_remote_code=True)
9model = AutoModelForCausalLM.from_pretrained(
10 base_model_id,
11 torch_dtype=torch.float16,
12 device_map="auto",
13 trust_remote_code=True,
14)
15model = PeftModel.from_pretrained(model, adapter_id)
16model = model.merge_and_unload()
17model.eval()| Format | Score |
|---|---|
| JSON | High |
| YAML | High |
| XML | High |
| CSV | Improved (fix applied) |
| TOML | Challenging |