GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
YehPel
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
YehPel
Model Tree
Qwen/Qwen2.5-0.5B-Instruct
Input Modalities
Output Modalities
Supported Functionality
This repository contains a LoRA adapter trained on top of
Qwen/Qwen2.5-0.5B-Instruct.
The goal of this experiment was to teach the model to end its assistant responses with the phrase:
So long, and thanks for all the fish
This project was created as a small educational experiment to better understand supervised fine-tuning, LoRA, PEFT, TRL, and the Hugging Face ecosystem.
The adapter was trained on:
Qwen/Qwen2.5-0.5B-Instruct
This repository does not contain the full Qwen model weights.
The original base model is required in order to use this adapter.
The model was fine-tuned using supervised fine-tuning (SFT) with a LoRA adapter implemented using Hugging Face PEFT.
The training loop was managed using TRL's SFTTrainer.
r): 8q_projk_projv_projo_projThe training dataset consisted of short conversational examples using
user and assistant messages.
Every assistant response in the training data ended with:
So long, and thanks for all the fish
The purpose of the dataset was not to teach the model new factual knowledge, but to demonstrate how fine-tuning can modify a model's response behavior.
Install the required libraries:
bash
pip install torch transformers peftLoad the original Qwen model and attach this LoRA adapter:
python
import torch from transformers import AutoModelForCausalLM, AutoTokenizerfrom peft import PeftModel base_model = AutoModelForCausalLM.from_pretrained( "Qwen/Qwen2.5-0.5B-Instruct", dtype=torch.float16, device_map="auto",) model = PeftModel.from_pretrained( base_model, "YehPel/qwen2.5-0.5b-fish-signoff-lora",) tokenizer = AutoTokenizer.from_pretrained( "Qwen/Qwen2.5-0.5B-Instruct")python
messages = [ { "role": "user", "content": "What is the capital of Japan?" }] text = tokenizer.apply_chat_template( messages, tokenize=False, add_generation_prompt=True,) inputs = tokenizer( text, return_tensors="pt").to(model.device) with torch.no_grad(): outputs = model.generate( **inputs, max_new_tokens=80 ) response = tokenizer.decode( outputs[0], skip_special_tokens=True) print(response)An example response after applying the adapter is:
text
systemYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.userWhat is the capital of Japan?assistantTokyo. So long, and thanks for all the fishThe important adapter files in this repository are:
text
adapter_config.jsonadapter_model.safetensorsadapter_config.json describes the LoRA configuration and its relationship
to the base model.
adapter_model.safetensors contains the trained LoRA parameters.
The full Qwen2.5-0.5B-Instruct weights are not included in this repository.
This adapter is based on Qwen/Qwen2.5-0.5B-Instruct, Copyright 2024 Alibaba Cloud, which is licensed under the Apache License 2.0.
This repository contains only the LoRA adapter weights and does not redistribute the original Qwen base model weights.
import torch from transformers import AutoModelForCausalLM, AutoTokenizerfrom peft import PeftModel base_model = AutoModelForCausalLM.from_pretrained( "Qwen/Qwen2.5-0.5B-Instruct", dtype=torch.float16, device_map="auto",) model = PeftModel.from_pretrained( base_model, "YehPel/qwen2.5-0.5b-fish-signoff-lora",) tokenizer = AutoTokenizer.from_pretrained( "Qwen/Qwen2.5-0.5B-Instruct")messages = [ { "role": "user", "content": "What is the capital of Japan?" }] text = tokenizer.apply_chat_template( messages, tokenize=False, add_generation_prompt=True,) inputs = tokenizer( text, return_tensors="pt").to(model.device) with torch.no_grad(): outputs = model.generate( **inputs, max_new_tokens=80 ) response = tokenizer.decode( outputs[0], skip_special_tokens=True) print(response)systemYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.userWhat is the capital of Japan?assistantTokyo. So long, and thanks for all the fish