README.md

metadata

language:
  - en
library_name: transformers
pipeline_tag: text-generation
tags:
  - shining-valiant
  - shining-valiant-3
  - valiant
  - valiant-labs
  - mistral3
  - mistral
  - mistral-common
  - ministral-3-14b
  - ministral
  - 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: mistralai/Ministral-3-14B-Reasoning-2512
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, Ministral-3-14B-Reasoning-2512, gpt-oss-20b

Shining Valiant 3 is a science, AI design, and general reasoning specialist built on Ministral 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 Ministral-3-14B-Reasoning-2512 prompt format.

Example inference script to get started:

import torch
from transformers import Mistral3ForConditionalGeneration, MistralCommonBackend

model_id = "ValiantLabs/Ministral-3-14B-Reasoning-2512-ShiningValiant3"

tokenizer = MistralCommonBackend.from_pretrained(model_id)

model = Mistral3ForConditionalGeneration.from_pretrained(
    model_id, torch_dtype=torch.bfloat16, device_map="auto"
)

user_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?"

system_prompt = (
    "# HOW YOU SHOULD THINK AND ANSWER\n\n"
    "First draft your thinking process (inner monologue) until you arrive at a response. "
    "Format your response using Markdown, and use LaTeX for any mathematical equations. "
    "Write both your thoughts and the response in the same language as the input.\n\n"
    "Your thinking process must follow the template below:"
    "[THINK]Your thoughts or/and draft, like working through an exercise on scratch paper. "
    "Be as casual and as long as you want until you are confident to generate the response to the user.[/THINK]"
    "Here, provide a self-contained response."
)

messages = [
    {
        "role": "system",
        "content": system_prompt
    },
    {
        "role": "user",
        "content": [
            {
                "type": "text",
                "text": user_prompt,
            },
        ],
    },
]

tokenized = tokenizer.apply_chat_template(messages, return_tensors="pt", return_dict=True)
tokenized = {k: v.to("cuda") for k, v in tokenized.items() if hasattr(v, "to")}

output = model.generate(
    **tokenized,
    max_new_tokens=20000,
)[0]

decoded_output = tokenizer.decode(output[len(tokenized["input_ids"][0]):])
print(decoded_output)

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.