🤏 smolified-character-builder

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.

📦 Asset Details

• Origin: Smolify Foundry (Job ID: 42d270f3)
• Architecture: DSLM-Micro (270M Parameter Class)
• Training Method: Proprietary Neural Distillation
• Optimization: 4-bit Quantized / FP16 Mixed
• Dataset: Link to Dataset

🚀 Usage (Inference)

This model is compatible with standard inference backends like vLLM.

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

model_id = "gourav221b/smolified-character-builder"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto")

messages = [
    {'role': 'system', 'content': '''The user wants a detailed video game character persona in JSON format based on provided information. Focus on converting skills, personal details, and a 'dark souls' game genre into character stats, traits, and a compelling character description, including a character image concept.'''},
    {'role': 'user', 'content': '''User Name: Alex "The Coder" Vance, GitHub Profile (simplified JSON): {"login": "alexvance", "id": 12345, "name": "Alex Vance", "email": "alex@example.com", "followers": 250, "public_repos": 60, "languages": {"JavaScript": 70, "Python": 20, "HTML": 10}}, Blog Post (excerpt): "My latest article on asynchronous programming paradigms and how they improve web application performance...", Skills: JavaScript (Expert), Python (Intermediate), Web Development, API Design, Technical Writing, Performance Optimization. Game/Genre: Cyberpunk 2077.'''}
]
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),
)

⚖️ License & Ownership

This model weights are a sovereign asset owned by gourav221b. Generated via Smolify.ai.