Unverified50% confidenceFactExact time
The 26.2M model uses an 8-layer encoder-only Transformer, d_model 384, 6 attention heads, FFN dimension 1536, a maximum of 160 tokens, a self-developed 16k byte-level BPE tokenizer, and 15,000 edit labels.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/12/2026
First Seen
Valid until: 1/10/2027
Sources
Related Entities
Related Claims
UnverifiedModels such as Llama-3.1-8B are built on a stacked Transformer decoder architecture, typically containing 32 decoder layers, with approximately 250 million parameters per layer and approximately 500MB of VRAM per layer at FP16 precision.75% similarUnverifiedd1-omni-600M 基于 LFM2.5-Encoder-350M 双向编码器构建，而非在因果解码器上接分类头，上下文窗口为 16,384 tokens。73% similarUnverifiedd1-3B has 3.12B parameters, its vision encoder is a shape-optimized version of SigLIP2 NaFlex (400M), its context length is 32,768 tokens, its vocabulary is 128,000, its weight format is Safetensors/BF16, its base model is LFM2.5-VL-3B (the text backbone was weight-averaged with LFM2.5-2.6B), and its license is lfm1.0.70% similarUnverifiedd1-omni-600M 包含 381M 共享主干加决策头、94M SigLIP2 视觉编码器（来自 LFM2.5-VL-450M）和 112M 17 层 FastConformer 音频编码器。69% similarUnverifiedThe actual parameter count of the full pipeline is 16.22B, comprising 7.115B for the Transformer, 8.767B for the text encoder (Qwen3-VL 8B), and 0.338B for the VAE.67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1009454API
curl https://kongchang.com/api/v1/knowledge/claims/1009454MCP
get_claim(id=1009454)