BuiDoan

22 63 175

AI & ML interests

None yet

Recent Activity

liked a model about 8 hours ago

unsloth/Qwen3.6-27B-NVFP4

liked a model about 8 hours ago

mlx-community/Qwen3.6-27B-OptiQ-4bit

liked a model about 8 hours ago

tencent/Hy3

View all activity

Organizations

liked 3 models about 8 hours ago

New activity in tencent/Hy3 1 day ago

IDEA: Bitnet 1.58 (a4.8) version in future variants would be so incredible!

❤️ 2

#10 opened 4 days ago by

apiarium

commented on Qwen3.6-27B-FP8 on One RTX 6000 Ada: Fast TTFT, 314 tok/s Decode Generation [Benchmark] 4 days ago

Quantization: Utilize 4-bit quantization (e.g., AWQ, GPTQ) to optimize GPU memory usage, significantly improving TTFT (Time To First Token) and increasing total throughput (token generation rate).
Inference Acceleration: Leverage MTP to enhance inference efficiency, achieving a performance boost of 1.3x–2.0x.
Context Management: Configure the --max-model-len parameter (typically 32k–64k) to expand model capability; note that this significantly impacts KV Cache memory footprint, requiring careful VRAM allocation management.

reacted to ginigen-ai's post with ❤️ 10 days ago

Post

10426

🧠 Does your LLM know when it's about to be wrong?

Most leaderboards measure accuracy. We measure metacognition — whether a model catches its own errors. Benchmark + leaderboard + adapters, all open. 🎉

The surprise: even a K-AI #1 model (JGOS-31B-Citizen) is the strongest on multiple-choice traps (trap_rate 0.005 — ~2 misses in 400) yet blind to its own free-form mistakes (self-confidence AUROC = 0.5, pure random). A tiny base-frozen adapter recovers that signal.

Two independent axes (never compared across a row): ① trap_rate — does it fall for tempting trap options? (lower = stronger) ② adapter gain Δ — how much a lightweight adapter catches errors the model itself misses. (higher = more adapter value)

What's open: 📊 300+100 trap problems (each with a hidden trap + TICOS type) 🏆 24-model leaderboard 🧩 11 per-model adapters — adapters, NOT fine-tunes (base stays frozen; the adapter just reads the hidden state → P(wrong))

Submit any HF model → auto-scored daily at 09:00 KST and added to the board.

🏆 Leaderboard → ginigen-ai/Metacognition-Leaderboard-Space

📊 Benchmark → ginigen-ai/Metacognition-Bench

🧩 Adapters → FINAL-Bench/metacognition-adapters-6a42c032e6beb803dd032961

📊 Article → https://huggingface.co/blog/ginigen-ai/metacognition

Benchmark by ginigen-ai · Adapters by FINAL-Bench (Darwin/Chimera platform + AETHER metacognition tech).

11 replies

liked a model 14 days ago

empero-ai/Qwythos-9B-Claude-Mythos-5-1M

Text Generation • 9B • Updated 13 days ago • 187k • 764

liked 2 models 15 days ago

empero-ai/Qwythos-9B-Claude-Mythos-5-1M-GGUF

Image-Text-to-Text • 9B • Updated 13 days ago • 1.94M • 1.99k

baidu/Unlimited-OCR

Image-Text-to-Text • 3B • Updated 8 days ago • 1.38M • 1.92k

liked 2 models 16 days ago

deepreinforce-ai/Ornith-1.0-35B

Text Generation • 665k • Updated 16 days ago • 709k • 375

deepreinforce-ai/Ornith-1.0-397B

Text Generation • 397B • Updated 16 days ago • 157k • 230

reacted to sequelbox's post with 🔥 18 days ago

Post

7403

NEW RELEASE: Esper 4 is here for Qwen 3.6 27b, along with our new datasets!

- NEW DATASET: Titanium 4 maximizes DevOps and architecture helpfulness, powered by high-difficulty agentic-focused DevOps and architecture data generated with DeepSeek-V4-Pro!
- NEW DATASET: Mitakihara 2 brings AI coding and expertise data for AI development, research, deployment, interpretability, operation and experimentation!
- Improved coding performance: challenging agentic coding queries from Tachibana 4 allow Esper 4 to tackle harder coding tasks across a variety of languages!

GET ESPER 4: ValiantLabs/Qwen3.6-27B-Esper4

Get the datasets for your own training:
sequelbox/Titanium4-DeepSeek-V4-Pro
sequelbox/Mitakihara2-DeepSeek-V4-Pro
sequelbox/Tachibana4-DeepSeek-V4-Pro

We've been working hard on Esper 4 - it's so exciting to finally bring it to everyone! We hope it helps you build.

We'll be expanding Esper 4 to more models as funding allows - donate for more, faster, better models and datasets: sequelbox/SupportOpenSource

The revolution is coming - we're here to fight for AI you can use and build on your own computer, not a giant corporation charging you for access at their discretion. We've seen what OpenAI, Anthropic, and the ultra-rich taking charge of the AI future looks like, and it's already very clear you won't like living in it. Choose a different future while you still can.

Open source must win.

More to come soon!

love, always,
allegra