QwerkyAI/QRe-Llama-3-3B-Instruct-QDistill

QwerkyLlamaMambaHybrid

Hybrid Mamba-Transformer model from Qwerky AI.

Requirements

• CUDA-compatible GPU
• Python 3.8+
• PyTorch 2.0+
• transformers, safetensors, mamba-ssm, causal-conv1d, flash-attn

Installation

pip install transformers torch safetensors
pip install flash-attn mamba-ssm causal-conv1d --no-build-isolation

Usage

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("QwerkyAI/Qwick-3B-Instruct")
model = AutoModelForCausalLM.from_pretrained(
    "QwerkyAI/Qwick-3B-Instruct",
    torch_dtype=torch.bfloat16,
    device_map="auto",
    trust_remote_code=True
)

inputs = tokenizer("Hello, how are you?", return_tensors="pt").to("cuda")
outputs = model.generate(**inputs, max_new_tokens=50)
print(tokenizer.decode(outputs[0]))

Model Files

• config.json - Model configuration with auto_map
• modeling_qwerky_llama_mamba_hybrid.py - Custom modeling class
• configuration_qwerky_llama_mamba_hybrid.py - Custom configuration class
• model.safetensors - Model weights

License

See LICENSE file for details.