Caution: The training for this model is intense enough to alter "real world facts", and bring them in part into the ST/TNG Universe.
This repo contains the full precision source code, in "safe tensors" format to generate GGUFs, GPTQ, EXL2, AWQ, HQQ and other formats. The source code can also be used directly.
This model is specifically for TNG / Star Trek, science fiction, story generation (all genres) but also does coding and general tasks too.
This model can also be used for Role play.
Example generations at the bottom of this page.
This is a far stronger fine tune, taking you deeper into the ST-TNG universe, than version 1 and the 32 bit precision version of II.
This is a Star Trek The Next Generation ( Special thanks to "progs2002" for this FANTASIC dataset) fine tune (11% of the model, close to 700 million parameters), 6 epochs on this model (a 4B model + Brainstorm 20x adapter):
https://huggingface.co/DavidAU/Qwen3-Jan-v1-256k-ctx-6B-Brainstorm20x
Then the modified "Freakstorm Horror" model was used as a base to further enhance the model [see model tree, benchmarks avail].
Information on the ORG Jan V1 4B (model info below), followed by Brainstorm 20x adapter (by DavidAU) and then a complete help section for running LLM / AI models.
This model has 55 layers, and 608 tensors.
The Brainstorm adapter improves creavity, code generation, and unique code solving abilities.
The fine tuning alters the prose generation and general creative abilities the "TNG" Universe.
The fine tuning (using Unsloth for Win 11) also affects the Brainstorm adapter too.
Model's thinking / reasoning are not affected either - they are fully intact.
For creative uses: Increases depth, detail and general "there" in the prose.
Example for creative at bottom of the page.
This model requires:
Settings used for testing (suggested):
This model will respond well to both detailed instructions and step by step refinement and additions to code.
Likewise for creative use cases.
Here is a review of this model's operations:
As this is an instruct model, it will also benefit from a detailed system prompt too.
For simpler coding problems, lower quants will work well; but for complex/multi-step problem solving suggest Q6 or Q8.
QUANTS:
GGUF? GGUF Imatrix? Other?
Special thanks to Team Mradermacher, Team Nightmedia and other quanters!
See under "model tree", upper right and click on "quantizations".
New quants will automatically appear.
Jan-v1 is the first release in the Jan Family, designed for agentic reasoning and problem-solving within the Jan App. Based on our Lucy model, Jan-v1 achieves improved performance through model scaling.
Jan-v1 uses the Qwen3-4B-thinking model to provide enhanced reasoning capabilities and tool utilization. This architecture delivers better performance on complex agentic tasks.
For question-answering, Jan-v1 shows a significant performance gain from model scaling, achieving 91.1% accuracy.
The 91.1% SimpleQA accuracy represents a significant milestone in factual question answering for models of this scale, demonstrating the effectiveness of our scaling and fine-tuning approach.
These benchmarks evaluate the model's conversational and instructional capabilities.
Jan-v1 is optimized for direct integration with the Jan App. Simply select the model from the Jan App interface for immediate access to its full capabilities.
Using vLLM:
vllm serve janhq/Jan-v1-4B \
--host 0.0.0.0 \
--port 1234 \
--enable-auto-tool-choice \
--tool-call-parser hermes
Using llama.cpp:
llama-server --model jan-v1.gguf \
--host 0.0.0.0 \
--port 1234 \
--jinja \
--no-context-shift
temperature: 0.6
top_p: 0.95
top_k: 20
min_p: 0.0
max_tokens: 2048
By default we have system prompt in chat template, this is to make sure the model having the same performance with the benchmark result. You can also use the vanilla chat template without system prompt in the file chat_template_raw.jinja.
See more here:
https://huggingface.co/janhq/Jan-v1-4B-GGUF
Brainstorm 20x
The BRAINSTORM process was developed by David_AU.
Some of the core principals behind this process are discussed in this scientific paper : Progressive LLaMA with Block Expansion .
However I went in a completely different direction from what was outlined in this paper.
What is "Brainstorm" ?
The reasoning center of an LLM is taken apart, reassembled, and expanded.
In this case for this model: 20 times
Then these centers are individually calibrated. These "centers" also interact with each other. This introduces subtle changes into the reasoning process. The calibrations further adjust - dial up or down - these "changes" further. The number of centers (5x,10x etc) allow more "tuning points" to further customize how the model reasons so to speak.
The core aim of this process is to increase the model's detail, concept and connection to the "world", general concept connections, prose quality and prose length without affecting instruction following.
This will also enhance any creative use case(s) of any kind, including "brainstorming", creative art form(s) and like case uses.
Here are some of the enhancements this process brings to the model's performance:
Other "lab" observations:
The process to modify the model occurs at the root level - source files level. The model can quanted as a GGUF, EXL2, AWQ etc etc.
For more information / other Qwen/Mistral Coders / additional settings see:
[ https://huggingface.co/DavidAU/Qwen2.5-MOE-2x-4x-6x-8x__7B__Power-CODER__19B-30B-42B-53B-gguf ]
CHANGE THE NUMBER OF ACTIVE EXPERTS:
See this document:
https://huggingface.co/DavidAU/How-To-Set-and-Manage-MOE-Mix-of-Experts-Model-Activation-of-Experts
Settings: CHAT / ROLEPLAY and/or SMOOTHER operation of this model:
In "KoboldCpp" or "oobabooga/text-generation-webui" or "Silly Tavern" ;
Set the "Smoothing_factor" to 1.5
: in KoboldCpp -> Settings->Samplers->Advanced-> "Smooth_F"
: in text-generation-webui -> parameters -> lower right.
: In Silly Tavern this is called: "Smoothing"
NOTE: For "text-generation-webui"
-> if using GGUFs you need to use "llama_HF" (which involves downloading some config files from the SOURCE version of this model)
Source versions (and config files) of my models are here:
OTHER OPTIONS:
Increase rep pen to 1.1 to 1.15 (you don't need to do this if you use "smoothing_factor")
If the interface/program you are using to run AI MODELS supports "Quadratic Sampling" ("smoothing") just make the adjustment as noted.
Highest Quality Settings / Optimal Operation Guide / Parameters and Samplers
This a "Class 1" model:
For all settings used for this model (including specifics for its "class"), including example generation(s) and for advanced settings guide (which many times addresses any model issue(s)), including methods to improve model performance for all use case(s) as well as chat, roleplay and other use case(s) please see:
You can see all parameters used for generation, in addition to advanced parameters and samplers to get the most out of this model here:
This will be low to mid-range quality, expect better at higher quants / imatrix quants.
Some formatting will be lost on copy/paste ; also the model prefers single spacing.
[[[ thinking start ]]]
Okay, the user is asking "Who is Q from Star Trek?" and wants a detailed breakdown. Hmm, they're probably a Star Trek fan who either just heard about Q or is doing research. Could be new to the franchise too—better cover basics thoroughly.
First thought: Q's such a unique character that I should emphasize how bizarre he is right away. Not just "a godlike being" but... alien to human concepts of power and morality. That'll hook them.
Wait—they said "detailed breakdown," so I'll need to structure it logically:
User might not realize Q's influence goes beyond the original series... better mention later shows too. And oh! The "Q Continuum" angle—some fans get obsessed with that. Should clarify it's not a single entity but a collective consciousness.
Biggest trap to avoid: making Q sound like a cartoon villain. He's more of a chaotic force of nature. Gotta stress his detachment from human concerns—that's what makes him terrifyingly interesting.
Also... should I address fan theories? Nah, unless asked. Stick to canon. But I'll hint that Q's motives remain mysterious ("no definitive answers") since that's part of the appeal.
checks mental notes Oh! Must include:
...Is the user writing fanfic? If so, they'll need those lore details. Better over-deliver just in case.
Final thought: Emphasize why Q is more than just a star trek character. He represents how absurd life can be—something Trek often explores through other characters too. That's what'll make this answer feel substantial.
[[[ thinking end ]]]
Q from Star Trek: A Deep Dive into the "Most Random Entity in the Universe"
Q is one of the most iconic, enigmatic, and endlessly fascinating characters in Star Trek history. Created by Gene Roddenberry for Star Trek: The Original Series (TOS), Q evolved into a cornerstone of the franchise across multiple series (TNG, DS9, VOY, ENT, Picard, Discovery, etc.). Here’s a detailed breakdown:
Why "Q"? The name was chosen by Gene Roddenberry from the first letter of "Quantum," reflecting Q's role as an omnipotent force manipulating reality at the quantum level.
Key Quirks:
Why it matters: Q’s ever-changing appearance reinforces his alien nature. He doesn’t fit into any human archetype—making him both unsettling and fascinating.
Why it matters: Q’s powers are not about domination—they’re about play. He enjoys messing with humans by making them solve problems they couldn’t possibly solve. This makes him uniquely terrifying—because he can’t be reasoned with or threatened.
Q is a chaotic force of nature with no clear agenda:
Famous Quotations:
Why it matters: Q’s personality is why he’s so compelling—a reminder that even in a universe of gods, there’s room for humor and absurdity.
TOS (1980s): The First Appearance
Q first appears in the TOS pilot episode "The Conundrum" (1982), where he challenges Captain Picard to a game of chess using his mind alone.
In a later TOS episode ("Q-Less"), Q creates a "Q-continuum" device that allows him to interact with Starfleet without revealing himself.
TNG (1987–1994): The Defining Era
Q becomes a recurring character in TNG, often working with the Enterprise crew to create mind-bending puzzles or challenges.
Key Storylines:
Other Series: Expanding the Universe
Why Q Matters to Star Trek
Q represents the absurdity of existence—a reminder that life is inherently unpredictable and chaotic. His presence pushes Star Trek’s exploration of humanity beyond mere technology or diplomacy into the realm of philosophy, psychology, and existential crisis.
Thematic Resonance: Q embodies Roddenberry’s belief that "the universe is a place of wonder and mystery." He forces the Enterprise crew to confront their own limitations—making them more human in the process.
Legacy: Q is one of Star Trek’s most enduring characters—a testament to the power of imagination and storytelling.
While Star Trek has other omnipotent beings (like Riker’s "The Man"), Q is unique because:
Final Takeaway
Q is more than just a "villain" or "god"—he’s a mirror to humanity itself. His random, chaotic nature forces us to confront our own insignificance in the cosmos while reminding us that life is, at its core, absurdly funny. In a universe where everything is possible, Q is the ultimate reminder: We’re all just playing with toy cars on the beach... until the tide comes in and takes them all away.
If you're new to Star Trek, Q is an excellent entry point for understanding the show’s philosophical depth—and why it remains relevant today. For hardcore fans, he’s a character who keeps getting deeper and more complex with every appearance across the franchise.
In short: Q is Star Trek’s ultimate jokester—a cosmic trickster who reminds us to laugh at life... even when everything else feels like hell. 🌌✨