AltAPIs

FrameXlabs/fragment-2

AI model by FrameXlabs

Open original source ↗

Older snapshot: check the original source for current information.

From the publisher

Model card & documentation

Source preview

Read the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.

A 36.3M-parameter System-One decision model, built by FrameXlabs on the original fragment build and trained entirely from scratch — own BPE tokenizer, own encoder, own RLCD loop. No pretrained weights, no fine-tune of Laya or any other model. Give it a state (any text) and typed questions; it returns typed answers with calibrated probabilities in a single forward pass — no autoregression, no text generation, no chain-of-thought, nothing to parse and nothing to hallucinate. Five question types: choice, score, noul, multi, rank. Sizes: fragment-2 36.3M from scratch vs Laya 421M/322M The repo ships a self-contained runtime — f3.py (needs only torch + safetensors): Training: supervised warmup (cross-entropy / BCE / Plackett-Luce over 470k typed items from SST-2, BoolQ, Amazon polarity, AG News, DBpedia-14, Yelp-5) → RLCD v2 (GRPO-style Gaussian logit-noise exploration, strictly proper scoring rules as reward — log score, RPS,…

FrameXlabs/fragment-2 on Hugging Face A short preview, not the full document.

Read the full model card ↗ · Preview checked 2026-11-13T10:30:20.040Z

Inside the original model card — Document outline
  1. fragment-2 (v3.0.2)
  2. Results (measured by the training notebook, held-out splits)
  3. Quickstart
  4. Architecture
  5. Honest limits
  6. Lineage

Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.

Documentation belongs to its respective authors. Reported project/model license: apache-2.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.

Model overview

FrameXlabs/fragment-2 is a task-unspecified model repository published by FrameXlabs on Hugging Face. A library was not reported.

This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.

Model facts

Task
Not reported
Library
Not reported
Recent downloads (30 days)
0
Cumulative likes
0
Hugging Face trending score
0
Reported safetensors parameters
Not reported
Architecture
Not reported
License
apache-2.0
Access
Not gated by Hugging Face
Created
2026-09-26T06:26:53.000Z
Last modified
2026-09-26T06:31:12.000Z

Compatibility and lineage

Reported languages: en

Base-model lineage was not included.

Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.

Use and evaluate

Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.

No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.

Model card and usage instructions

Model files and configuration

Community discussion

Source and freshness

Source: Hugging Face Hub. Metadata observed 2026-09-26T06:37:45.751Z. Daily imports are snapshots, not real-time monitoring.

Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.

Open original source

Related models