README.md

---
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!](https://huggingface.co/spaces/sequelbox/SupportOpenSource)**


![image/jpeg](/static-proxy?url=https%3A%2F%2Fcdn-uploads.huggingface.co%2Fproduction%2Fuploads%2F63444f2687964b331809eb55%2F0-q6i_3FVjPg27esj9rNm.jpeg%3C%2Fspan%3E)%3C!-- HTML_TAG_END -->

Shining Valiant 3: [Qwen3-1.7B](https://huggingface.co/ValiantLabs/Qwen3-1.7B-ShiningValiant3), [Qwen3-4B](https://huggingface.co/ValiantLabs/Qwen3-4B-ShiningValiant3), [Qwen3-8B](https://huggingface.co/ValiantLabs/Qwen3-8B-ShiningValiant3), [Ministral-3-14B-Reasoning-2512](https://huggingface.co/ValiantLabs/Ministral-3-14B-Reasoning-2512-ShiningValiant3), [gpt-oss-20b](https://huggingface.co/ValiantLabs/gpt-oss-20b-ShiningValiant3)


Shining Valiant 3 is a science, AI design, and general reasoning specialist built on Ministral 3.
- Finetuned on our newest [science reasoning](https://huggingface.co/datasets/sequelbox/Celestia3-DeepSeek-R1-0528) data generated with [Deepseek R1 0528!](https://huggingface.co/deepseek-ai/DeepSeek-R1-0528)
- AI to build AI: our [high-difficulty AI reasoning](https://huggingface.co/datasets/sequelbox/Mitakihara-DeepSeek-R1-0528) data makes Shining Valiant 3 your friend for building with current AI tech and discovering new innovations and improvements!
- Improved [general and creative reasoning](https://huggingface.co/datasets/sequelbox/Raiden-DeepSeek-R1) 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](https://huggingface.co/mistralai/Ministral-3-14B-Reasoning-2512) prompt format.

Example inference script to get started:

```python
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)
```


![image/jpeg](/static-proxy?url=https%3A%2F%2Fcdn-uploads.huggingface.co%2Fproduction%2Fuploads%2F63444f2687964b331809eb55%2FVCJ8Fmefd8cdVhXSSxJiD.jpeg%3C%2Fspan%3E)%3C!-- HTML_TAG_END -->


Shining Valiant 3 is created by [Valiant Labs.](http://valiantlabs.ca/)

[Check out our HuggingFace page to see all of our models!](https://huggingface.co/ValiantLabs)

We care about open source. For everyone to use.