GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
vishnuamarapu
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
vishnuamarapu
Model Tree
Qwen/Qwen2.5-0.5B-Instruct
Input Modalities
Output Modalities
Supported Functionality
Qwen/Qwen2.5-0.5B-Instructbash
pip install transformers peft accelerate torch safetensorspython
import torchfrom transformers import AutoTokenizer, AutoModelForCausalLMfrom peft import PeftModel BASE_MODEL = "Qwen/Qwen2.5-0.5B-Instruct"LORA_MODEL = "vishnuamarapu/Full-Fine-Tuning-Qwen-2.5-0.5B-instruct-LORA" tokenizer = AutoTokenizer.from_pretrained(BASE_MODEL) base_model = AutoModelForCausalLM.from_pretrained( BASE_MODEL, torch_dtype=torch.float16 if torch.cuda.is_available() else torch.float32, device_map="auto") model = PeftModel.from_pretrained( base_model, LORA_MODEL) model.eval()python
messages = [ { "role": "system", "content": ( "You are Vishnu's personal AI assistant. " "Answer questions about Vishnu." ) }, { "role": "user", "content": "Tell me about Vishnu." }] 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=256, temperature=0.7, do_sample=True, top_p=0.9, repetition_penalty=1.1, ) response = tokenizer.decode( outputs[0][inputs.input_ids.shape[-1]:], skip_special_tokens=True,) print(response)python
import torchimport gradio as gr from transformers import AutoTokenizer, AutoModelForCausalLMfrom peft import PeftModel BASE_MODEL = "Qwen/Qwen2.5-0.5B-Instruct"LORA_MODEL = "vishnuamarapu/Full-Fine-Tuning-Qwen-2.5-0.5B-instruct-LORA" tokenizer = AutoTokenizer.from_pretrained(BASE_MODEL) base_model = AutoModelForCausalLM.from_pretrained( BASE_MODEL, torch_dtype=torch.float16 if torch.cuda.is_available() else torch.float32, device_map="auto") model = PeftModel.from_pretrained( base_model, LORA_MODEL) model.eval() SYSTEM_PROMPT = ( """ You are Vishnu's personal AI assistant.Always answer using the information you have learned about Vishnu.Do not invent facts.If you do not know the answer, say you don't know.Answer as Vishnu in first person.""") def generate(message, history): messages = [ { "role": "system", "content": SYSTEM_PROMPT, } ] for user, assistant in history: messages.append({"role": "user", "content": user}) messages.append({"role": "assistant", "content": assistant}) messages.append({"role": "user", "content": message}) 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=256, temperature=0.7, do_sample=True, top_p=0.9, repetition_penalty=1.1, ) answer = tokenizer.decode( outputs[0][inputs.input_ids.shape[-1]:], skip_special_tokens=True, ) return answer gr.ChatInterface( fn=generate, title="Vishnu Personal AI", description="LoRA Fine-Tuned Qwen2.5-0.5B-Instruct",).launch()| Parameter | Value |
|---|---|
| max_new_tokens | 256 |
| temperature | 0.7 |
| top_p | 0.9 |
| repetition_penalty | 1.1 |
| device_map | auto |
| torch_dtype | float16 (GPU) / float32 (CPU) |
text
adapter_config.jsonadapter_model.safetensorschat_template.jinjatokenizer.jsontokenizer_config.jsonREADME.mdThis model was fine-tuned using LoRA (Low-Rank Adaptation) through the PEFT library. Only a small set of trainable adapter weights were updated while the base model remained frozen, resulting in a lightweight adapter that can be merged with the original base model for inference.
If you use this model in your work, please cite this repository.
bibtex
@misc{vishnu_qwen25_lora, author = {Vishnu Amarapu}, title = {LoRA Fine-Tuned Qwen2.5-0.5B-Instruct}, year = {2026}, publisher = {Hugging Face}, howpublished = {\url{https://huggingface.co/vishnuamarapu/Full-Fine-Tuning-Qwen-2.5-0.5B-instruct-LORA}}}pip install transformers peft accelerate torch safetensorsimport torchfrom transformers import AutoTokenizer, AutoModelForCausalLMfrom peft import PeftModel BASE_MODEL = "Qwen/Qwen2.5-0.5B-Instruct"LORA_MODEL = "vishnuamarapu/Full-Fine-Tuning-Qwen-2.5-0.5B-instruct-LORA" tokenizer = AutoTokenizer.from_pretrained(BASE_MODEL) base_model = AutoModelForCausalLM.from_pretrained( BASE_MODEL, torch_dtype=torch.float16 if torch.cuda.is_available() else torch.float32, device_map="auto") model = PeftModel.from_pretrained( base_model, LORA_MODEL) model.eval()messages = [ { "role": "system", "content": ( "You are Vishnu's personal AI assistant. " "Answer questions about Vishnu." ) }, { "role": "user", "content": "Tell me about Vishnu." }] 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=256, temperature=0.7, do_sample=True, top_p=0.9, repetition_penalty=1.1, ) response = tokenizer.decode( outputs[0][inputs.input_ids.shape[-1]:], skip_special_tokens=True,) print(response)import torchimport gradio as gr from transformers import AutoTokenizer, AutoModelForCausalLMfrom peft import PeftModel BASE_MODEL = "Qwen/Qwen2.5-0.5B-Instruct"LORA_MODEL = "vishnuamarapu/Full-Fine-Tuning-Qwen-2.5-0.5B-instruct-LORA" tokenizer = AutoTokenizer.from_pretrained(BASE_MODEL) base_model = AutoModelForCausalLM.from_pretrained( BASE_MODEL, torch_dtype=torch.float16 if torch.cuda.is_available() else torch.float32, device_map="auto") model = PeftModel.from_pretrained( base_model, LORA_MODEL) model.eval() SYSTEM_PROMPT = ( """ You are Vishnu's personal AI assistant.Always answer using the information you have learned about Vishnu.Do not invent facts.If you do not know the answer, say you don't know.Answer as Vishnu in first person.""") def generate(message, history): messages = [ { "role": "system", "content": SYSTEM_PROMPT, } ] for user, assistant in history: messages.append({"role": "user", "content": user}) messages.append({"role": "assistant", "content": assistant}) messages.append({"role": "user", "content": message}) 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=256, temperature=0.7, do_sample=True, top_p=0.9, repetition_penalty=1.1, ) answer = tokenizer.decode( outputs[0][inputs.input_ids.shape[-1]:], skip_special_tokens=True, ) return answer gr.ChatInterface( fn=generate, title="Vishnu Personal AI", description="LoRA Fine-Tuned Qwen2.5-0.5B-Instruct",).launch()adapter_config.jsonadapter_model.safetensorschat_template.jinjatokenizer.jsontokenizer_config.jsonREADME.md@misc{vishnu_qwen25_lora, author = {Vishnu Amarapu}, title = {LoRA Fine-Tuned Qwen2.5-0.5B-Instruct}, year = {2026}, publisher = {Hugging Face}, howpublished = {\url{https://huggingface.co/vishnuamarapu/Full-Fine-Tuning-Qwen-2.5-0.5B-instruct-LORA}}}