lucasjinreal / lucasjinreal/Namo-R1

New model training status

Open
#2 0 comments 2 reactions 0 assignees View on GitHub
Dominant language
Python
Stars
256
Forks
26
PR merge metrics
No merged PRs in 30d

Description

Hello, small MLLM lovers!

Our next model are under training, I will keep updating the training status as for your reference.

## Namo-500M-v2

v2 model introduced a little bit more advanced features:

- slightly larger VE, matching size to SmolVLM (our V1 actually smaller than SmolVLM);
- We are moving to dynamic size and fixed tokens strategy for GPU utility reason;

Current training status: **62%**

The V2 model currently so far so good, intermediate model shows strong ability. Also, we might will have OVD and DoD ultimately. (Detection anything with described words)

## Namo-500M-TTS

TTS model are under code prepaing and model plan choosen, if you got any good idea, please send me an PR!

Contributor guide

No contributing guide indexed for this repository

Research direction

The issue contains a training-status update but names no files, tests, or entry points to inspect. There is no defined change or completion criterion, so clarify the intended contribution before beginning work.

Written by the indexing model from the issue text.

Assessment

Tech stack
machine-learning
Domain
ai, machine-learning
Issue type
Documentation
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
15/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.