Downloads · 30 days
8
18% of all-time downloads
rin-4b-exp
Loke-60000/rin-4b-exp
rin-4b-exp is a text generation model from Loke-60000. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
A model trained for agentic work on device.
All-time downloads
44
Public
Parameters
4.2B
8.4 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors8.4 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- apache-2.0
- Model type
- qwen3_5_text
- Access
- Public
- Created
- Jun 27, 2026
- Updated
- Jun 27, 2026
- SHA
- ce58a34c
Try a prompt
Model card
From the Hugging Face model README
Rin
A model trained for agentic work on device.
- Long-horizon agentic tasks, coding, and everyday chat
- Reasons privately, then answers cleanly
- ~4B parameters — runs locally on consumer hardware
Usage
from transformers import AutoModelForCausalLM, AutoTokenizer
tok = AutoTokenizer.from_pretrained("Loke-60000/rin-4b")
model = AutoModelForCausalLM.from_pretrained("Loke-60000/rin-4b", device_map="auto")
msgs = [{"role": "user", "content": "Write a Python function to reverse a string."}]
inputs = tok.apply_chat_template(msgs, add_generation_prompt=True, return_tensors="pt").to(model.device)
print(tok.decode(model.generate(**{"input_ids": inputs}, max_new_tokens=512)[0]))
- Task
- Text Generation
- Library
- transformers
- Type
- qwen3_5_text
- License
- apache-2.0
- Created
- Jun 27, 2026
- Updated
- Jun 27, 2026