programmerGodbyte's picture
Smolify: Intelligence Distilled.
e01a7e4 verified
metadata
license: apache-2.0
language:
  - en
tags:
  - text-generation-inference
  - transformers
  - smolify
  - dslm
pipeline_tag: text-generation
inference:
  parameters:
    temperature: 1
    top_p: 0.95
    top_k: 64

🀏 smolified-tiny-text-to-code

Intelligence, Distilled.

This is a Domain Specific Language Model (DSLM) generated by the Smolify Foundry.

It has been synthetically distilled from SOTA reasoning engines into a high-efficiency architecture, optimized for deployment on edge hardware (CPU/NPU) or low-VRAM environments.

πŸ“¦ Asset Details

  • Origin: Smolify Foundry (Job ID: fe9b19bf)
  • Architecture: DSLM-Micro (270M Parameter Class)
  • Training Method: Proprietary Neural Distillation
  • Optimization: 4-bit Quantized / FP16 Mixed
  • Dataset: Link to Dataset

πŸš€ Usage (Inference)

This model is compatible with standard inference backends like vLLM.

# Example: Running your Sovereign Model
from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "programmerGodbyte/smolified-tiny-text-to-code"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto")

messages = [
    {'role': 'system', 'content': '''The user will provide a natural language description of a programming task. Your goal is to generate correct, runnable Python code that solves the task. Adhere to PEP 8 style guidelines. Include type hints for all functions and variables. The code should be self-contained and ready to run.'''},
    {'role': 'user', 'content': '''Create a Python function named `factorial` that calculates the factorial of a non-negative integer. If the input is negative, it should raise a `ValueError`. If the input is 0, it should return 1.'''}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize = False,
    add_generation_prompt = True,
).removeprefix('<bos>')

from transformers import TextStreamer
_ = model.generate(
    **tokenizer(text, return_tensors = "pt").to("cuda"),
    max_new_tokens = 1000,
    temperature = 1, top_p = 0.95, top_k = 64,
    streamer = TextStreamer(tokenizer, skip_prompt = True),
)

βš–οΈ License & Ownership

This model weights are a sovereign asset owned by programmerGodbyte. Generated via Smolify.ai.