Kurtis-EON1
Collection
Language Model
•
8 items
•
Updated
Massimo Roberto Scamarcia PRO
mrs83
AI & ML interests
Natural Language Processing, Text Generation, Question Answering, Data Augmentation, Knowledge Transfer, Chain-of-Thought, ResearchOps, MLOps
Recent Activity
updated
a collection
13 minutes ago
Kurtis-EON1
updated
a model
13 minutes ago
ethicalabs/Echo-DSRN-Small-Kurtis-EON1-OpenHermes-005-PEFT
published
a model
15 minutes ago
ethicalabs/Echo-DSRN-Small-Kurtis-EON1-OpenHermes-005-PEFT
Organizations
updated
a
collection
13 minutes ago
updated
a
model
13 minutes ago
published
a
model
15 minutes ago
Mid-Training - Phase 005: Kurtis SFT Mix + OpenHermes2.5
4
#3 opened 1 day ago
by
mrs83
reacted to
SeaWolf-AI's
post with 🔥
1 day ago
Post
2197
FINAL Bench Released: The Real Bottleneck to AGI Is Self-Correction
We release FINAL Bench, the first benchmark for measuring functional metacognition in LLMs — the ability to detect and correct one's own reasoning errors. Every existing benchmark measures final-answer accuracy. None measures whether AI knows it is wrong.
Dataset: [FINAL-Bench/Metacognitive]( FINAL-Bench/Metacognitive) | 100 Tasks | 15 Domains | 8 TICOS Types | Apache 2.0
Leaderboard: FINAL-Bench/Leaderboard
Article: https://huggingface.co/blog/FINAL-Bench/metacognitive
Core Innovation
Our 5-axis rubric separates what no prior benchmark could: MA (Metacognitive Accuracy) — the ability to say "I might be wrong", and ER (Error Recovery) — the ability to actually fix it. This maps directly to the monitoring-control model of Nelson & Narens (1990) in cognitive psychology.
Three Findings Across 9 SOTA Models
We evaluated GPT-5.2, Claude Opus 4.6, Gemini 3 Pro, DeepSeek-V3.2, Kimi K2.5, and others across 100 expert-level tasks:
1. ER Dominance. 94.8% of MetaCog gain comes from Error Recovery alone. The bottleneck to AGI is not knowledge or reasoning — it is self-correction.
2. Declarative-Procedural Gap. All 9 models can verbalize uncertainty (MA = 0.694) but cannot act on it (ER = 0.302). They sound humble but fail to self-correct — the most dangerous AI safety profile.
3. Difficulty Effect. Harder tasks benefit dramatically more from metacognition (Pearson r = -0.777, p < 0.001).
Paper: FINAL Bench: Measuring Functional Metacognitive Reasoning in LLMs
FINAL Bench is the first tool to tell apart what AI truly knows from what it merely pretends to know.
We release FINAL Bench, the first benchmark for measuring functional metacognition in LLMs — the ability to detect and correct one's own reasoning errors. Every existing benchmark measures final-answer accuracy. None measures whether AI knows it is wrong.
Dataset: [FINAL-Bench/Metacognitive]( FINAL-Bench/Metacognitive) | 100 Tasks | 15 Domains | 8 TICOS Types | Apache 2.0
Leaderboard: FINAL-Bench/Leaderboard
Article: https://huggingface.co/blog/FINAL-Bench/metacognitive
Core Innovation
Our 5-axis rubric separates what no prior benchmark could: MA (Metacognitive Accuracy) — the ability to say "I might be wrong", and ER (Error Recovery) — the ability to actually fix it. This maps directly to the monitoring-control model of Nelson & Narens (1990) in cognitive psychology.
Three Findings Across 9 SOTA Models
We evaluated GPT-5.2, Claude Opus 4.6, Gemini 3 Pro, DeepSeek-V3.2, Kimi K2.5, and others across 100 expert-level tasks:
1. ER Dominance. 94.8% of MetaCog gain comes from Error Recovery alone. The bottleneck to AGI is not knowledge or reasoning — it is self-correction.
2. Declarative-Procedural Gap. All 9 models can verbalize uncertainty (MA = 0.694) but cannot act on it (ER = 0.302). They sound humble but fail to self-correct — the most dangerous AI safety profile.
3. Difficulty Effect. Harder tasks benefit dramatically more from metacognition (Pearson r = -0.777, p < 0.001).
from datasets import load_dataset
dataset = load_dataset("FINAL-Bench/Metacognitive", split="train")Paper: FINAL Bench: Measuring Functional Metacognitive Reasoning in LLMs
FINAL Bench is the first tool to tell apart what AI truly knows from what it merely pretends to know.
- 2 replies
A quick update on the development of Kurtis-EON1 (Echo-DSRN)
1
#4 opened 1 day ago
by
mrs83
updated
a
model
1 day ago
Mid-Training - Phase 004: Kurtis SFT Mix
9
#2 opened 5 days ago
by
mrs83
updated
a
model
3 days ago
replied to
qgallouedec's
post
3 days ago
Thanks for sharing, we are using a similar recipe for our small models 👏
reacted to
qgallouedec's
post with 🔥
3 days ago
Post
2362
@CohereLabs
just released 🌿 Tiny Aya: a fully open-source 3B parameter model that speaks 70+ languages 🌍! But there’s a catch:
Tiny Aya is just a language model. It doesn’t support tool calling, the key capability that turns frontier models into powerful *agents*.
So the real question is:
How hard is it to turn Tiny Aya into an agent?
Turns out… it’s simple, thanks to Hugging Face TRL.
We’re sharing a hands-on example showing how to train Tiny Aya to turn it into a tool-calling agent using TRL, unlocking what could become the first *massively multilingual open agent*.
Small model. Global reach. Agent capabilities.
👉 https://github.com/huggingface/trl/blob/main/examples/notebooks/sft_tool_calling.ipynb
Tiny Aya is just a language model. It doesn’t support tool calling, the key capability that turns frontier models into powerful *agents*.
So the real question is:
How hard is it to turn Tiny Aya into an agent?
Turns out… it’s simple, thanks to Hugging Face TRL.
We’re sharing a hands-on example showing how to train Tiny Aya to turn it into a tool-calling agent using TRL, unlocking what could become the first *massively multilingual open agent*.
Small model. Global reach. Agent capabilities.
👉 https://github.com/huggingface/trl/blob/main/examples/notebooks/sft_tool_calling.ipynb
-
- 1 reply
replied to
their
post
3 days ago
updated
a
collection
4 days ago
updated
a
collection
5 days ago
published
a
model
5 days ago
liked
a
dataset
5 days ago
Mid-Training - Phase 003: HuggingFaceTB/smoltalk
4
#1 opened 7 days ago
by
mrs83
updated
a
model
6 days ago
updated
a
collection
6 days ago