DireDreadlord

Dragon-1-0.5B

Deploy Dedicated

README

License: apache-2.0

Training data

Phase-1

Source: deepseek-v4-reasoning-code-2500 dataset (https://huggingface.co/datasets/Banaxi-Tech/Deepseek-V4-Reasoning-Code-2500)
Rows: ~2,555 rows templated with a custom .jinja chat format
Training: trained for 5,000 steps on an RTX PRO 4000 (24GB VRAM)

Phase-2

Source: deepseek-v4-reasoning-code-2500 dataset (https://huggingface.co/datasets/Banaxi-Tech/Deepseek-V4-Reasoning-Code-2500)
Rows: ~2,555 rows templated with a custom .jinja chat format
Training: trained via. GRPO for 500 steps on an RTX PRO 4000 (24GB VRAM)

Usage

Install requirements:

bash
pip install -r requirements.txt
pip install transformers datasets accelerate safetensors

Usage (Hugging Face Hub)

You can load it directly from HuggingFace:

python
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer


device = "cuda" if torch.cuda.is_available() else "cpu"

model_id = "DireDreadlord/Dragon-1-0.5B"
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    device_map="auto",
    dtype="auto"
)
model.to(device)
tokenizer = AutoTokenizer.from_pretrained(model_id)
streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=False)

prompt = "Can you reason about the following leetcode question: Given an array of integers nums and an integer target, return indices of the two numbers such that they add up to target. You may assume that each input would have exactly one solution, and you may not use the same element twice. You can return the answer in any order. Please provide a detailed reasoning and explanation for your answer."

input_ids = tokenizer.apply_chat_template(
    [{"role": "user", "content": prompt}],
    add_generation_prompt=True,
    return_tensors="pt",
    tokenize=True,
)["input_ids"].to(device)

output = model.generate(
    input_ids,
    do_sample=True,
    temperature=0.4,
    top_k=50,
    repetition_penalty=1.05,
    max_new_tokens=2048,
    streamer=streamer,
)

For optimal long-form generation(with reasoning), set max_new_tokens=2048

Limitations

Model for experimental use only; users should employ it as such under license.

Available on FriendliAI

Dedicated Endpoints

Run this model inference on single tenant GPU with unmatched speed and reliability at scale.

Learn more

Container

Run this model inference with full control and performance in your environment.

Learn more

Model Details

Model Provider

DireDreadlord

Model Tree

Base

Qwen/Qwen2-0.5B-Instruct

Fine-tuned

this model

Input Modalities

Text

Output Modalities