GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
Yellowforesty
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
Yellowforesty
Model Tree
Qwen/Qwen2.5-1.5B
Input Modalities
Output Modalities
Supported Functionality
text
You are an information extraction system.Return ONLY a valid JSON object.Rules:- Extract only explicitly mentioned information.- Never infer or assume values.- Preserve the schema exactly.- Use null for missing values.- Return only JSON.
text
Schema:{"company": "string","ceo": "string","founded": "int","employees": "int"}Text:OpenAI was founded in 2015. Sam Altman is the CEO. The company employs approximately 4500 people.
json
{"company": "OpenAI","ceo": "Sam Altman","founded": 2015,"employees": 4500}
Install the required packages.
bash
pip install transformers peft accelerate torch
This adapter is trained on Qwen/Qwen2.5-1.5B.
The base model will be downloaded automatically the first time you run the code.
python
from transformers import AutoTokenizer, AutoModelForCausalLMfrom peft import PeftModelimport torchBASE_MODEL = "Qwen/Qwen2.5-1.5B"LORA_MODEL = "Yellowforesty/qwen2.5-json-extractor-p0"tokenizer = AutoTokenizer.from_pretrained(BASE_MODEL)base = AutoModelForCausalLM.from_pretrained(BASE_MODEL,device_map="auto")model = PeftModel.from_pretrained(base,LORA_MODEL)
python
SYSTEM_PROMPT = """You are an information extraction system.Return ONLY a valid JSON object.Rules:- Extract only explicitly mentioned information.- Never infer or assume values.- Preserve the schema exactly.- Use null for missing values.- Return only JSON.""".strip()
python
prompt = """Schema:{"company": "string","ceo": "string","founded": "int","employees": "int"}Text:OpenAI was founded in 2015. Sam Altman is the CEO. The company employs approximately 4500 people."""
python
messages = [{"role": "system", "content": SYSTEM_PROMPT},{"role": "user", "content": prompt},]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():output = model.generate(**inputs,max_new_tokens=256,temperature=0.0,do_sample=False,)response = tokenizer.decode(output[0][inputs["input_ids"].shape[1]:],skip_special_tokens=True,)print(response)
json
{"company": "OpenAI","ceo": "Sam Altman","founded": 2015,"employees": 4500}
python
import osimport torchfrom huggingface_hub import loginfrom transformers import AutoTokenizer, AutoModelForCausalLMfrom peft import PeftModel# ==========================================# CONFIG# ==========================================BASE_MODEL = "Qwen/Qwen2.5-1.5B"LORA_MODEL = "Yellowforesty/qwen2.5-json-extractor-p0"HF_TOKEN = os.getenv("HF_TOKEN")if HF_TOKEN:login(token=HF_TOKEN)SYSTEM_PROMPT = """You are an information extraction system.Return ONLY a valid JSON object.Rules:- Extract only explicitly mentioned information.- Never infer or assume values.- Preserve the schema exactly.- Use null for missing values.- Return only JSON.""".strip()PROMPT = """Schema:{"company": "string","ceo": "string","founded": "int","employees": "int"}Text:OpenAI was founded in 2015. Sam Altman is the CEO. The company employs approximately 4500 people.""".strip()# ==========================================# LOAD TOKENIZER# ==========================================tokenizer = AutoTokenizer.from_pretrained(BASE_MODEL)# ==========================================# LOAD BASE MODEL# ==========================================base = AutoModelForCausalLM.from_pretrained(BASE_MODEL,device_map="auto",torch_dtype=torch.float16 if torch.cuda.is_available() else torch.float32,)# ==========================================# LOAD LORA# ==========================================model = PeftModel.from_pretrained(base,LORA_MODEL,)model.eval()print("Device:", next(model.parameters()).device)# ==========================================# INFERENCE# ==========================================messages = [{"role": "system", "content": SYSTEM_PROMPT},{"role": "user", "content": PROMPT},]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():output = model.generate(**inputs,max_new_tokens=256,temperature=0.0,do_sample=False,)response = tokenizer.decode(output[0][inputs["input_ids"].shape[1]:],skip_special_tokens=True,)print(response.strip())
text
Schema:{"name": "string","age": "int","city": "string"}Text:Aman, aged 31, recently moved to Chandigarh.
json
{"name": "Aman","age": 31,"city": "Chandigarh"}
Current Version (P0)
Evaluation
Current version supports
Not yet supported
The training dataset used to train this adapter is not included in this repository.
MIT