aligntune-test-full-model

Built using Aligntune โ€” supports any open-source model, any algorithm, any backend (TRL / Unsloth / ES / etc).

Built by zlyngkhoi
Built on 2026-08-24 04:53 UTC
Finetuned from unsloth/qwen2.5-0.5b-instruct-unsloth-bnb-4bit
Algorithm PPO
Backend Unsloth

Test push: full merged model.

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("zlyngkhoi/aligntune-test-full-model")
tokenizer = AutoTokenizer.from_pretrained("zlyngkhoi/aligntune-test-full-model")
Downloads last month
13
Safetensors
Model size
0.3B params
Tensor type
F32
ยท
BF16
ยท
U8
ยท
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support