OPENGCM/Hydrion-v1-Base
Text Generation โข 0.1B โข Updated โข 58 โข 1
๐๏ธ Building on HF
Dan P
Datdanboi25
AI & ML interests
Axiomic Labs Founder
Mechatronics engineer, LLMs, Vision Models, Embedding Models
Recent Activity
liked a model about 1 hour ago
OPENGCM/Hydrion-v1-Base liked a model about 11 hours ago
deepseek-ai/DeepSeek-V4-Flash-DSpark new activity about 12 hours ago
AxiomicLabs/Open_SLM_Leaderboard:Arithmark 3Organizations
liked a
model about 1 hour ago
liked a
model about 11 hours ago
Arithmark 3
8
#58 opened about 19 hours ago
by 
Banaxi-Tech
updated a
Space about 12 hours ago
reacted to ucr-max's post with ๐ฅ about 12 hours ago
Post
910
Introducing Limen0.2B
We are releasing Limen0.2B, a 222.5M-parameter base language model developed as a research platform for efficient pretraining and superword tokenization at smaller scales.
Limen0.2B was trained from scratch on 50B tokens and uses a compact 16K BoundlessBPE vocabulary. The project explores whether SuperBPE-style tokenization can remain effective in a substantially smaller model and vocabulary regime than those examined in earlier large-scale experiments.
The model also combines a deep-and-narrow transformer design with Exclusive Self-Attention, grouped-query attention, and tied embeddings. Its compact vocabulary reduces the embedding footprint and leaves a larger share of the parameter budget available to the transformer layers.
Despite its relatively modest training budget, Limen0.2B achieves competitive results for its scale across the reported language understanding, commonsense reasoning, and grammatical evaluation tasks. Comparisons with other compact models are provided as context rather than strict rankings, as their training data, token budgets, architectures, and evaluation settings differ.
The release includes the model weights, implementation, training configuration, checkpoint progression, and evaluation results, all under Apache 2.0.
UniversalComputingResearch/Limen0.2B
Technical feedback, independent evaluations, and further experiments with the model and tokenizer are welcome.
We are releasing Limen0.2B, a 222.5M-parameter base language model developed as a research platform for efficient pretraining and superword tokenization at smaller scales.
Limen0.2B was trained from scratch on 50B tokens and uses a compact 16K BoundlessBPE vocabulary. The project explores whether SuperBPE-style tokenization can remain effective in a substantially smaller model and vocabulary regime than those examined in earlier large-scale experiments.
The model also combines a deep-and-narrow transformer design with Exclusive Self-Attention, grouped-query attention, and tied embeddings. Its compact vocabulary reduces the embedding footprint and leaves a larger share of the parameter budget available to the transformer layers.
Despite its relatively modest training budget, Limen0.2B achieves competitive results for its scale across the reported language understanding, commonsense reasoning, and grammatical evaluation tasks. Comparisons with other compact models are provided as context rather than strict rankings, as their training data, token budgets, architectures, and evaluation settings differ.
The release includes the model weights, implementation, training configuration, checkpoint progression, and evaluation results, all under Apache 2.0.
UniversalComputingResearch/Limen0.2B
Technical feedback, independent evaluations, and further experiments with the model and tokenizer are welcome.
liked a
dataset about 12 hours ago
published a
dataset about 12 hours ago
updated a
Space about 13 hours ago
updated a
dataset 1 day ago
liked a
model 1 day ago
Submission: Museko-125M (123M, from scratch)
๐ 1
1
#57 opened 4 days ago
by 
TobiasLogic
Amazing work
1
#3 opened 1 day ago
by Datdanboi25
liked a
Space 1 day ago
liked a
model 1 day ago
Haha I know im just joking!
i got a model idea for you, what about a GPT M2 like 50M or 70M
Yeah been thinking about a model in that range
liked a
model 2 days ago
reacted to Banaxi-Tech's post with ๐ฅ 2 days ago
Post
2824
We're excited to release BananaMind Base Bench 1.1 A new benchmark for base language models with 350 text-completion examples across seven categories. Models are scored using continuation likelihood and receive an Overall Elo score.
Initial results:
BananaMind-2-Medium: 1034
BananaMind-2-Mini: 974
Supra-50M-Base: 973
Supra-1.5-50M-Base-exp: 948
BananaMind-2-Nano: 910
The official script downloads the gated dataset directly from Hugging Face. The dataset is for benchmarking only and may not be used for model training.
BananaMind/BananaMind-Base-Bench-1.1
Initial results:
BananaMind-2-Medium: 1034
BananaMind-2-Mini: 974
Supra-50M-Base: 973
Supra-1.5-50M-Base-exp: 948
BananaMind-2-Nano: 910
The official script downloads the gated dataset directly from Hugging Face. The dataset is for benchmarking only and may not be used for model training.
BananaMind/BananaMind-Base-Bench-1.1
- 9 replies
Haha I know im just joking!
BananaMind 2 pro... ok i know
How do you know?
Fix Specialists
โ 2
5
#56 opened 4 days ago
by Banaxi-Tech