Downloads · 30 days
13
20% of all-time downloads
qwen3-4b-instruct-distill-lora
talzoomanzoo/qwen3-4b-instruct-distill-lora
qwen3-4b-instruct-distill-lora is a text generation model from talzoomanzoo. Use it when you need the model to write or continue text. It is set up for peft.
LoRA adapter from offline distillation (teacher reasoning traces) on Qwen/Qwen3-4B-Instruct-2507.
All-time downloads
65
Public
Repo size
529 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors529 MB · 100%
At a glance
- Task
- Text Generation
- Library
- peft
- Access
- Public
- Created
- May 19, 2026
- Updated
- May 19, 2026
- SHA
- bc31bed4
Try a prompt
Base models
Model card
From the Hugging Face model README
Qwen3-4B Instruct distill LoRA
LoRA adapter from offline distillation (teacher reasoning traces) on Qwen/Qwen3-4B-Instruct-2507.
Load
from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel
base = "Qwen/Qwen3-4B-Instruct-2507"
adapter = "talzoomanzoo/qwen3-4b-instruct-distill-lora"
tokenizer = AutoTokenizer.from_pretrained(base)
model = AutoModelForCausalLM.from_pretrained(base, torch_dtype="auto", device_map="auto")
model = PeftModel.from_pretrained(model, adapter)
- Task
- Text Generation
- Library
- peft
- Created
- May 19, 2026
- Updated
- May 19, 2026