Downloads · 30 days
7
32% of all-time downloads
Qwen3-4B-Instruct-2507-question
doupari/Qwen3-4B-Instruct-2507-question
Qwen3-4B-Instruct-2507-question is a text generation model from doupari. 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-Instruct-2507.
All-time downloads
22
Public
Repo size
144 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors132 MB · 89%
At a glance
- Task
- Text Generation
- Library
- peft
- Access
- Public
- Created
- Jun 18, 2026
- Updated
- Jun 18, 2026
- SHA
- aac9aaab
Try a prompt
Base models
Model card
From the Hugging Face model README
Qwen3-4B-Instruct-2507-question LoRA Adapter
This repository contains a LoRA adapter fine-tuned from Qwen/Qwen3-4B-Instruct-2507.
Checkpoint Selection
The uploaded adapter was selected from the checkpoint with the lowest observed eval loss:
- checkpoint:
checkpoint-420 - global step:
420 - epoch:
3.0 - metric:
eval_loss - best observed eval loss:
0.06847485899925232
Evaluation loss history:
| Step | Eval loss |
|---|---|
| 140 | 0.083890088 |
| 280 | 0.068713501 |
| 420 | 0.068474859 |
| 560 | 0.085991889 |
| 700 | 0.097578414 |
Usage
from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel
base_model = "Qwen/Qwen3-4B-Instruct-2507"
adapter_id = "YOUR_USERNAME/YOUR_REPO_NAME"
tokenizer = AutoTokenizer.from_pretrained(adapter_id)
model = AutoModelForCausalLM.from_pretrained(base_model, device_map="auto", torch_dtype="auto")
model = PeftModel.from_pretrained(model, adapter_id)
- Task
- Text Generation
- Library
- peft
- Created
- Jun 18, 2026
- Updated
- Jun 18, 2026