GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
BhavanaR006
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
BhavanaR006
Model Tree
Qwen/Qwen2.5-1.5B
Input Modalities
Output Modalities
Supported Functionality
python
from transformers import AutoModelForCausalLM, AutoTokenizerfrom peft import PeftModelimport torch, json base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-1.5B", device_map="auto", trust_remote_code=True)model = PeftModel.from_pretrained(base_model, "BhavanaR006/small-model-supremacy-qwen2.5-1.5b")tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2.5-1.5B", trust_remote_code=True) prompt = '''<|im_start|>systemYou are a JSON extraction assistant. You ONLY output valid JSON. No explanations.<|im_end|><|im_start|>userExtract from the following text into the schema "conference_talk_simple". Text: Dr. Sarah Chen presented quantum error correction at NeurIPS 2025 in Vancouver.<|im_end|><|im_start|>assistant''' inputs = tokenizer(prompt, return_tensors="pt").to(model.device)stop_id = tokenizer.encode("<|im_end|>", add_special_tokens=False)[0]outputs = model.generate(**inputs, max_new_tokens=200, do_sample=False, eos_token_id=stop_id)result = tokenizer.decode(outputs[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True)print(result)# {"speaker_name": "Dr. Sarah Chen", "topic": "quantum error correction", "conference": "NeurIPS 2025", "location": "Vancouver"}Full source code, training pipeline, and evaluation harness: GitHub
from transformers import AutoModelForCausalLM, AutoTokenizerfrom peft import PeftModelimport torch, json base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-1.5B", device_map="auto", trust_remote_code=True)model = PeftModel.from_pretrained(base_model, "BhavanaR006/small-model-supremacy-qwen2.5-1.5b")tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2.5-1.5B", trust_remote_code=True) prompt = '''<|im_start|>systemYou are a JSON extraction assistant. You ONLY output valid JSON. No explanations.<|im_end|><|im_start|>userExtract from the following text into the schema "conference_talk_simple". Text: Dr. Sarah Chen presented quantum error correction at NeurIPS 2025 in Vancouver.<|im_end|><|im_start|>assistant''' inputs = tokenizer(prompt, return_tensors="pt").to(model.device)stop_id = tokenizer.encode("<|im_end|>", add_special_tokens=False)[0]outputs = model.generate(**inputs, max_new_tokens=200, do_sample=False, eos_token_id=stop_id)result = tokenizer.decode(outputs[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True)print(result)# {"speaker_name": "Dr. Sarah Chen", "topic": "quantum error correction", "conference": "NeurIPS 2025", "location": "Vancouver"}