CogniXpert-DeepSeek-R1-Distill-Llama8B-English

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Load merged model directly
model_name = "cogni-x/CogniXpert-DeepSeek-R1-Distill-Llama8B-English"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    device_map='auto',
    torch_dtype=torch.bfloat16,
)

# Example: English mental health conversation
messages = [
    {"role": "user", "content": "I've been feeling really anxious about work lately."}
]

inputs = tokenizer.apply_chat_template(
    messages, 
    add_generation_prompt=True, 
    return_tensors="pt"
).to(model.device)

outputs = model.generate(
    inputs,
    max_new_tokens=256,
    temperature=0.7,
    top_p=0.9,
    do_sample=True,
)

response = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(response)