PingVortexLM-0.5B-v1

A fine-tuned version of Qwen/Qwen2.5-0.5B trained on custom English conversational data. This model is not aimed at coding or multilingual use, just solid general English conversation.

Built by PingVortex Labs.

---

Model Details

• Base model: Qwen/Qwen2.5-0.5B
• Parameters: ~0.5B
• Context length: 8192 tokens
• Language: English only
• Format: ChatML
• License: Apache 2.0

---

Usage

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

model_id = "pvlabs/PingVortexLM-0.5B-v1"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, dtype=torch.bfloat16, device_map="auto")

def chat(user_message):
    prompt = (
        f"<|im_start|>system\nYou are a helpful assistant<|im_end|>\n"
        f"<|im_start|>user\n{user_message}<|im_end|>\n"
        f"<|im_start|>assistant\n"
    )
    inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
    with torch.no_grad():
        output = model.generate(
            **inputs,
            max_new_tokens=512,
            do_sample=True,
            temperature=0.7,
            top_p=0.9,
            pad_token_id=tokenizer.eos_token_id,
        )
    response = tokenizer.decode(output[0][inputs["input_ids"].shape[-1]:], skip_special_tokens=True)
    return response

print(chat("Hello"))

---

Prompt Format (ChatML)

The model uses the standard ChatML format:

<|im_start|>system
You are a helpful assistant<|im_end|>
<|im_start|>user
Your message here<|im_end|>
<|im_start|>assistant

It is recommended to always include the system prompt.

---

Made by PingVortex.