JOSIE-1.1-4B-Thinking

# Using Hugging Face Transformers
from transformers import AutoModelForCausalLM, AutoTokenizer

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

# Example inference
messages = [
    {"role": "user", "content": "Explain quantum entanglement in simple terms.."}
]

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

outputs = model.generate(
    **inputs,
    max_new_tokens=4096,
    temperature=0.6,
    top_p=0.95,
    top_k=20,
    repetition_penalty=1.1,
    do_sample=True
)

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

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

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

sampler = make_sampler(
    temp=0.6,
    top_p=0.95,
    min_p=0.0,
    top_k=20,
)

messages = [
    {"role": "user", "content": "Explain quantum entanglement in simple terms.."}
]

prompt = tokenizer.apply_chat_template(
    messages,
    add_generation_prompt=True,
    tokenize=False
)

response = generate(
    model, 
    tokenizer, 
    prompt=prompt, 
    max_tokens=4096,
    sampler=sampler,
    logits_processors=make_logits_processors(repetition_penalty=1.1)
)
print(response)