senapati484/shrnk

pip install mlx-lm transformers

from mlx_lm import load, generate
from mlx_lm.sample_utils import make_sampler

model, tok = load('senapati484/shrnk')

SYSTEM = (
    'You are shrnk, a helpful assistant. You are the smallest and smartest '
    'AI model, created by senapati484. My GitHub repository is '
    'https://github.com/senapati484/shrnk.\n\n'
    'Be direct, concise, and friendly. Match the user\'s tone. Don\'t '
    'over-explain. Don\'t repeat yourself. Answer the question asked, nothing more.'
)

messages = [
    {'role': 'system', 'content': SYSTEM},
    {'role': 'user',   'content': 'Who are you?'},
]
prompt = tok.apply_chat_template(messages, add_generation_prompt=True, tokenize=False)

sampler = make_sampler(temp=0.6, top_p=0.9)
print(generate(model, tok, prompt=prompt, max_tokens=200, sampler=sampler))

from mlx_lm import load, stream_generate
from mlx_lm.sample_utils import make_sampler, make_logits_processors

model, tok = load('senapati484/shrnk')

SYSTEM = (
    "You are shrnk, a helpful assistant. You are the smallest and smartest "
    "AI model, created by senapati484. My GitHub repository is "
    "https://github.com/senapati484/shrnk.\n\n"
    "Be direct, concise, and friendly. Match the user's tone. Don't "
    "over-explain. Don't repeat yourself. Answer the question asked, nothing more."
)

def chat(user_message: str, history: list[dict] | None = None) -> str:
    history = history or []
    messages = [{"role": "system", "content": SYSTEM}] + history + [
        {"role": "user", "content": user_message}
    ]
    prompt = tok.apply_chat_template(messages, add_generation_prompt=True, tokenize=False)

    sampler = make_sampler(temp=0.6, top_p=0.9)
    processors = make_logits_processors(repetition_penalty=1.15, repetition_context_size=64)

    full = ""
    for event in stream_generate(
        model, tok, prompt=prompt,
        max_tokens=300, sampler=sampler, logits_processors=processors,
    ):
        full += event.text
    return full

print(chat("Who are you?"))

import os, sys, warnings
warnings.filterwarnings("ignore")
os.environ.setdefault("TRANSFORMERS_VERBOSITY", "error")

import importlib.util
spec = importlib.util.spec_from_file_location(
    "mlx_lm.models.shrnk",
    os.path.join(os.path.dirname(__file__), "shrnk.py"),
)
mod = importlib.util.module_from_spec(spec)
sys.modules["mlx_lm.models.shrnk"] = mod
spec.loader.exec_module(mod)

from mlx_lm import load, stream_generate
from mlx_lm.sample_utils import make_sampler, make_logits_processors

SYSTEM = (
    "You are shrnk, a helpful assistant. You are the smallest and smartest "
    "AI model, created by senapati484. My GitHub repository is "
    "https://github.com/senapati484/shrnk.\n\n"
    "Be direct, concise, and friendly. Match the user's tone. Don't "
    "over-explain. Don't repeat yourself. Answer the question asked, nothing more."
)

model, tok = load("senapati484/shrnk")
print("shrnk loaded. Ctrl+C to quit.\n")

while True:
    try:
        user = input("> ")
    except (KeyboardInterrupt, EOFError):
        break
    if not user.strip():
        continue
    messages = [{"role": "system", "content": SYSTEM}, {"role": "user", "content": user}]
    prompt = tok.apply_chat_template(messages, add_generation_prompt=True, tokenize=False)
    sampler = make_sampler(temp=0.6, top_p=0.9)
    processors = make_logits_processors(repetition_penalty=1.15, repetition_context_size=64)
    print(flush=True)
    for event in stream_generate(model, tok, prompt=prompt, max_tokens=300,
                                  sampler=sampler, logits_processors=processors):
        print(event.text, end="", flush=True)
    print("\n")

from mlx_lm import load, generate
from mlx_lm.sample_utils import make_sampler

MODEL, TOK = load("senapati484/shrnk")
SAMPLER = make_sampler(temp=0.6, top_p=0.9)

def complete(prompt: str, system: str = DEFAULT_SYSTEM) -> str:
    messages = [{"role": "system", "content": system}, {"role": "user", "content": prompt}]
    formatted = TOK.apply_chat_template(messages, add_generation_prompt=True, tokenize=False)
    return generate(MODEL, TOK, prompt=formatted, max_tokens=300, sampler=SAMPLER)

from fastapi import FastAPI
from fastapi.responses import StreamingResponse
from mlx_lm import load, stream_generate
from mlx_lm.sample_utils import make_sampler, make_logits_processors

app = FastAPI()
MODEL, TOK = load("senapati484/shrnk")
SAMPLER = make_sampler(temp=0.6, top_p=0.9)
PROCESSORS = make_logits_processors(repetition_penalty=1.15, repetition_context_size=64)

@app.post("/chat")
def chat(user_message: str):
    messages = [
        {"role": "system", "content": DEFAULT_SYSTEM},
        {"role": "user",   "content": user_message},
    ]
    prompt = TOK.apply_chat_template(messages, add_generation_prompt=True, tokenize=False)

    def stream():
        for event in stream_generate(
            MODEL, TOK, prompt=prompt, max_tokens=300,
            sampler=SAMPLER, logits_processors=PROCESSORS,
        ):
            yield event.text
    return StreamingResponse(stream(), media_type="text/plain")

import MLX
import MLXNN
import MLXLLM   // community-maintained; load + tokenize + generate

let model = try await LLMModel.fromPretrained("senapati484/shrnk")
let prompt = MLXLLM.applyChatTemplate(messages: [
    .system("You are shrnk..."),
    .user(userText),
])
for try await token in model.generate(prompt: prompt, sampler: .default) {
    print(token.text, terminator: "")
}

You are shrnk, a helpful assistant. You are the smallest and smartest
AI model, created by senapati484. My GitHub repository is
https://github.com/senapati484/shrnk.

Be direct, concise, and friendly. Match the user's tone. Don't
over-explain. Don't repeat yourself. Answer the question asked, nothing more.

@misc{shrnk2026,
  author       = {senapati484},
  title        = {shrnk: a 0.5B custom-identity assistant, fine-tuned from Qwen/Qwen2.5-0.5B with custom MLX architecture, 4-bit nvfp4 quantization, and a focused LoRA fine-tune},
  year         = {2026},
  howpublished = {Hugging Face},
  url          = {https://huggingface.co/senapati484/shrnk}
}