README.md

metadata

language:
  - en
library_name: transformers
pipeline_tag: text-generation
tags:
  - shining-valiant
  - shining-valiant-3
  - valiant
  - valiant-labs
  - qwen
  - qwen-3
  - qwen-3-4b
  - 4b
  - reasoning
  - code
  - code-reasoning
  - science
  - science-reasoning
  - physics
  - biology
  - chemistry
  - earth-science
  - astronomy
  - machine-learning
  - artificial-intelligence
  - compsci
  - computer-science
  - information-theory
  - ML-Ops
  - math
  - cuda
  - deep-learning
  - transformers
  - agentic
  - LLM
  - neuromorphic
  - self-improvement
  - complex-systems
  - cognition
  - linguistics
  - philosophy
  - logic
  - epistemology
  - simulation
  - game-theory
  - knowledge-management
  - creativity
  - problem-solving
  - architect
  - engineer
  - developer
  - creative
  - analytical
  - expert
  - rationality
  - conversational
  - chat
  - instruct
base_model: Qwen/Qwen3-4B
datasets:
  - sequelbox/Celestia3-DeepSeek-R1-0528
  - sequelbox/Mitakihara-DeepSeek-R1-0528
  - sequelbox/Raiden-DeepSeek-R1
license: apache-2.0

Support our open-source dataset and model releases!

Shining Valiant 3: Qwen3-1.7B, Qwen3-4B, Qwen3-8B

Shining Valiant 3 is a science, AI design, and general reasoning specialist built on Qwen 3.

• Finetuned on our newest science reasoning data generated with Deepseek R1 0528!
• AI to build AI: our high-difficulty AI reasoning data makes Shining Valiant 3 your friend for building with current AI tech and discovering new innovations and improvements!
• Improved general and creative reasoning to supplement problem-solving and general chat performance.
• Small model sizes allow running on local desktop and mobile, plus super-fast server inference!

Prompting Guide

Shining Valiant 3 uses the Qwen 3 prompt format.

Shining Valiant 3 is a reasoning finetune; we recommend enable_thinking=True for all chats.

Example inference script to get started:

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "ValiantLabs/Qwen3-4B-ShiningValiant3"

# load the tokenizer and the model
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

# prepare the model input
prompt = "Propose a novel cognitive architecture where the primary memory component is a Graph Neural Network (GNN). How would this GNN represent working, declarative, and procedural memory? How would the \"cognitive cycle\" be implemented as operations on this graph?"
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=True # Switches between thinking and non-thinking modes. Default is True.
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

# conduct text completion
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 

# parsing thinking content
try:
    # rindex finding 151668 (</think>)
    index = len(output_ids) - output_ids[::-1].index(151668)
except ValueError:
    index = 0

thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")

print("thinking content:", thinking_content)
print("content:", content)

Shining Valiant 3 is created by Valiant Labs.

Check out our HuggingFace page to see all of our models!

We care about open source. For everyone to use.