John6666/reo-20
Preview • Updated • 21
John Smith PRO
John6666
AI & ML interests
None yet
Recent Activity
updated a dataset about 11 hours ago
John6666/reo-20 updated a dataset about 11 hours ago
John6666/forum3 reacted to ProCreations's post with 👍 1 day ago
grug-v2 here. grug v1 good but lost tool use brain. grug v2 RL fix. grug v2 more SFT to make more grug.
Try grug v2 here:
https://huggingface.co/ProCreations/grug-v2-9b-gguf
https://huggingface.co/ProCreations/grug-v2-9b
Demo space here:
https://huggingface.co/spaces/ProCreations/grug-v2-9b-demoOrganizations
updated 2
datasets about 11 hours ago
reacted to ProCreations's post with 👍 1 day ago
Post
2353
grug-v2 here. grug v1 good but lost tool use brain. grug v2 RL fix. grug v2 more SFT to make more grug.
Try grug v2 here:
ProCreations/grug-v2-9b-gguf
ProCreations/grug-v2-9b
Demo space here:
ProCreations/grug-v2-9b-demo
Try grug v2 here:
ProCreations/grug-v2-9b-gguf
ProCreations/grug-v2-9b
Demo space here:
ProCreations/grug-v2-9b-demo
reacted to appvoid's post with 👀 1 day ago
Post
205
small reasoning models are overrated, these little ones just doom loop a lot by default. good data will always be the moat when training or finetuning small models and latest sota models like fable 5 and gpt 5.6 are increasingly making this a lot easier to do.
- 3 replies
reacted to kanaria007's post with 👀 1 day ago
Post
160
✅ Article highlight: State Formation and Recognition in Persistent Worlds (art-60-242, v0.1)
TL;DR:
This article asks a practical design question for persistent simulated worlds:
When NPC societies, settlements, factions, and institutions evolve over time, when does a powerful group become a polity?
242 argues that power is not polityhood. Diplomacy, treaties, succession, migration, and war require a bounded governing subject with explicit formation, authority, continuity, legitimacy, jurisdiction, and recognition surfaces.
Read:
kanaria007/agi-structural-intelligence-protocols
Why it matters:
• prevents every powerful faction from being treated as a state
• separates de facto control from recognized governing-subject status
• distinguishes world-internal recognition from operator-side canon recognition
• keeps legitimacy, continuity, and governability as separate questions
• makes recognition scoped, contestable, and time-aware
What’s inside:
• distinctions between faction, settlement, polity, and state
• polity formation records
• boundary declarations for settled, disputed, layered, or non-territorial jurisdiction
• legitimacy registers with explicit limits
• recognition claims for WORLD_INTERNAL, OPERATOR_SIDE, DUAL, LIMITED, or NONE
• entrance conditions for partition, merger, succession, federation, and diplomacy
Key idea:
Do not say:
“this group became powerful, so it is now a state.”
Say:
“this entity formed under this record, governs this bounded jurisdiction, preserves this continuity basis, holds this legitimacy posture, and is recognized only for these declared purposes.”
Power can create control.
Legible governance creates a polity.
TL;DR:
This article asks a practical design question for persistent simulated worlds:
When NPC societies, settlements, factions, and institutions evolve over time, when does a powerful group become a polity?
242 argues that power is not polityhood. Diplomacy, treaties, succession, migration, and war require a bounded governing subject with explicit formation, authority, continuity, legitimacy, jurisdiction, and recognition surfaces.
Read:
kanaria007/agi-structural-intelligence-protocols
Why it matters:
• prevents every powerful faction from being treated as a state
• separates de facto control from recognized governing-subject status
• distinguishes world-internal recognition from operator-side canon recognition
• keeps legitimacy, continuity, and governability as separate questions
• makes recognition scoped, contestable, and time-aware
What’s inside:
• distinctions between faction, settlement, polity, and state
• polity formation records
• boundary declarations for settled, disputed, layered, or non-territorial jurisdiction
• legitimacy registers with explicit limits
• recognition claims for WORLD_INTERNAL, OPERATOR_SIDE, DUAL, LIMITED, or NONE
• entrance conditions for partition, merger, succession, federation, and diplomacy
Key idea:
Do not say:
“this group became powerful, so it is now a state.”
Say:
“this entity formed under this record, governs this bounded jurisdiction, preserves this continuity basis, holds this legitimacy posture, and is recognized only for these declared purposes.”
Power can create control.
Legible governance creates a polity.
reacted to SeaWolf-AI's post with 🔥 1 day ago
Post
5374
🔵 VKUE — No GPU? Runs anyway.
"Frontier models need a datacenter GPU" rests on a hidden assumption: that the model reads ALL its parameters every token. Decode is memory-bandwidth bound — sweep 34B params/token and an 8 GB card dies at 1–2 tok/s.
So we ran ONE 34.7B reasoning model — Ourbox-35B-JGOS, a sparse Mixture-of-Experts — as the identical weights across the whole hardware spectrum. All measured:
• B200: 18,057 tok/s (aggregate)
• 1× A10G: 126 tok/s
• 8 GB laptop (RTX 5060): 20 tok/s
• GPU-less CPU: 17 tok/s
Why it works: Ourbox holds 34.7B params but only ~3B are active per token (256 experts, top-8). Since decode is bandwidth-bound, a dense 34B moves ~16.7 GB/token while Ourbox moves ~1.45 GB — ~11× less traffic. Put the experts in system RAM, keep attention/router/shared on the GPU, and a 34.7B reasoner runs on an 8 GB laptop — or no GPU at all.
Sparsity alone, proven (same laptop, same quant, ~same footprint): Ourbox-35B (A3B) 20.01 tok/s vs Qwen2.5-32B (dense) 5.36 → 3.7× from sparsity alone, ~2× the best dense-32B on any 8 GB machine. Not a toy: GPQA Diamond 86.4% (maj@8).
Try it live (same prompt, GPU vs GPU-less CPU, live tok/s). Honest scope: one machine's measurements; the CPU path proves it RUNS without a GPU, not that it beats one.
📝 Article: https://huggingface.co/blog/FINAL-Bench/vkue
🔵 GPU vs CPU demo: https://final-bench-ourbox-35b-vkue-demo.hf.space/
🔵 CPU-only demo: https://final-bench-ourbox-35b-vkue-cpu.hf.space
📊 VKUE leaderboard: FINAL-Bench/VKUE
🤗 Model: FINAL-Bench/Ourbox-35B-JGOS-GGUF
⚡ VKAE (speed): VIDraft/vkae
VKUE is the "runs anywhere" side of our serving line; VKAE the "fast on datacenter GPUs" side. VKAE is fast; VKUE is everywhere.
"Frontier models need a datacenter GPU" rests on a hidden assumption: that the model reads ALL its parameters every token. Decode is memory-bandwidth bound — sweep 34B params/token and an 8 GB card dies at 1–2 tok/s.
So we ran ONE 34.7B reasoning model — Ourbox-35B-JGOS, a sparse Mixture-of-Experts — as the identical weights across the whole hardware spectrum. All measured:
• B200: 18,057 tok/s (aggregate)
• 1× A10G: 126 tok/s
• 8 GB laptop (RTX 5060): 20 tok/s
• GPU-less CPU: 17 tok/s
Why it works: Ourbox holds 34.7B params but only ~3B are active per token (256 experts, top-8). Since decode is bandwidth-bound, a dense 34B moves ~16.7 GB/token while Ourbox moves ~1.45 GB — ~11× less traffic. Put the experts in system RAM, keep attention/router/shared on the GPU, and a 34.7B reasoner runs on an 8 GB laptop — or no GPU at all.
Sparsity alone, proven (same laptop, same quant, ~same footprint): Ourbox-35B (A3B) 20.01 tok/s vs Qwen2.5-32B (dense) 5.36 → 3.7× from sparsity alone, ~2× the best dense-32B on any 8 GB machine. Not a toy: GPQA Diamond 86.4% (maj@8).
Try it live (same prompt, GPU vs GPU-less CPU, live tok/s). Honest scope: one machine's measurements; the CPU path proves it RUNS without a GPU, not that it beats one.
📝 Article: https://huggingface.co/blog/FINAL-Bench/vkue
🔵 GPU vs CPU demo: https://final-bench-ourbox-35b-vkue-demo.hf.space/
🔵 CPU-only demo: https://final-bench-ourbox-35b-vkue-cpu.hf.space
📊 VKUE leaderboard: FINAL-Bench/VKUE
🤗 Model: FINAL-Bench/Ourbox-35B-JGOS-GGUF
⚡ VKAE (speed): VIDraft/vkae
VKUE is the "runs anywhere" side of our serving line; VKAE the "fast on datacenter GPUs" side. VKAE is fast; VKUE is everywhere.
- 7 replies
liked 14
models 1 day ago
trmixai/TRMIX-8B-Instruct
Text Generation • 8B • Updated • 26 • 1
mradermacher/TRMIX-8B-Instruct-GGUF
8B • Updated • 621 • 1
DavidAU/Llama3.3-8B-Instruct-Thinking-Claude-4.5-Opus-High-Reasoning
Text Generation • 8B • Updated • 151 • • 102
mradermacher/Llama3.3-8B-Instruct-Thinking-Claude-4.5-Opus-High-Reasoning-GGUF
8B • Updated • 2.24k • 2
mradermacher/Llama3.3-8B-Instruct-Thinking-Claude-4.5-Opus-High-Reasoning-i1-GGUF
8B • Updated • 2.14k • 5
ReadyArt/Omega-Darker-v1-R1-4B
4B • Updated • 5
mradermacher/Omega-Darker-v1-R1-4B-GGUF
4B • Updated • 17 • 4
mradermacher/Omega-Darker-v1-R1-4B-i1-GGUF
4B • Updated • 932 • 3
Sorihon/Memorable-Dream-12B-Heretic
12B • Updated • 21 • 1
mradermacher/Memorable-Dream-12B-Heretic-i1-GGUF
12B • Updated • 946 • 1
mradermacher/Memorable-Dream-12B-Heretic-GGUF
12B • Updated • 415 • 1
Felldude/gemma-4-E4B-uncensored
Any-to-Any • 8B • Updated • 263 • 1
mradermacher/gemma-4-E4B-uncensored-i1-GGUF
7B • Updated • 4.24k • 1
mradermacher/gemma-4-E4B-uncensored-GGUF
7B • Updated • 2.97k • 2