arcane-13b

Arcane-13B

Arcane-13B is a high-capacity 13-billion parameter model for deep mental health text analysis, offering nuanced reasoning for complex crisis and wellbeing assessment workflows.

Overview

• Model Size: 13 Billion Parameters
• Capabilities: High-fidelity explanation generation, multi-factor distress classification.

Inference Example

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

model_id = "ar3xop/arcane-13b"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.float16,
    device_map="auto"
)

prompt = 'Consider this post: "Nothing seems meaningful anymore, struggling to get through the day." Question: Does the post indicate depressive tendencies?'
inputs = tokenizer(prompt, return_tensors="pt").to("cuda")

outputs = model.generate(inputs.input_ids, max_length=512)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))