rax-3.5-chat

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Load model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("rax-3.5-chat")
model = AutoModelForCausalLM.from_pretrained(
    "rax-3.5-chat",
    torch_dtype=torch.bfloat16,
    device_map="auto"
)

# Chat template
messages = [
    {"role": "system", "content": "You are Rax, a helpful AI assistant."},
    {"role": "user", "content": "Hello! How are you?"}
]

# Apply chat template
input_text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(input_text, return_tensors="pt")

# Generate response
with torch.no_grad():
    outputs = model.generate(
        **inputs,
        max_new_tokens=256,
        temperature=0.7,
        do_sample=True,
        pad_token_id=tokenizer.eos_token_id
    )

response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

@misc{rax35chat2024,
  title={Rax 3.5 Chat: An Enhanced Conversational AI Model},
  author={RaxCore},
  year={2024},
  note={Enhanced from TinyLlama with significant RaxCore improvements},
  organization={RaxCore - Leading developer company in Africa and beyond}
}