JOSIE-1.1-4B-Instruct

# Using Hugging Face Transformers
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "Goekdeniz-Guelmez/JOSIE-1.1-4B-Instruct"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    device_map="auto",
    torch_dtype="auto"
)

# Example inference
messages = [
    {"role": "user", "content": "Can you help me understand how neural networks work?"}
]

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

outputs = model.generate(
    inputs,
    max_new_tokens=1024,
    temperature=0.7,
    top_p=0.8,
    top_k=20,
    repetition_penalty=1,
    do_sample=True
)

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

# Using MLX for optimized Apple Silicon inference
from mlx_lm import load, generate
from mlx_lm.sample_utils import make_sampler

model, tokenizer = load("Goekdeniz-Guelmez/JOSIE-1.1-4B-Instruct")

sampler = make_sampler(
    temp=0.7,
    top_p=0.8,
    min_p=0.0,
    top_k=20,
)

messages = [
    {"role": "user", "content": "What's a fun way to learn Python? 🐍"}
]

prompt = tokenizer.apply_chat_template(messages, add_generation_prompt=True, tokenize=False)
response = generate(model, tokenizer, prompt=prompt, max_tokens=512, temp=0.7)
print(response)