README.md

---
license: mit
pipeline_tag: text-generation
---
# VLM 1 K2

- Second model of VLM series (**V**ortex **L**anguage **M**odel)
- K stands for **K**nowledge (Higher is better)

## Use the model:
- Open [Google Colab](https://colab.research.google.com/)
- Create new notebook
- Paste this code in the cell:
```python
!pip install transformers
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "VortexIntelligence/VLM-1-K2"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id)

print("VLM Chat\nType 'exit' to quit")

while True:
    user_input = input("You: ")
    if user_input.strip().lower() == "exit":
        break

    input_ids = tokenizer(user_input, return_tensors="pt").input_ids
    input_ids = input_ids[:, -1024:]

    with torch.no_grad():
        output = model.generate(
            input_ids,
            max_new_tokens=50,
            do_sample=True,
            temperature=0.7,
            top_p=0.9,
            pad_token_id=tokenizer.eos_token_id
        )

    new_tokens = output[0][input_ids.shape[1]:]
    response = tokenizer.decode(new_tokens, skip_special_tokens=True)

    print("VLM:", response.strip())
```