microsoft / microsoft/BitNet

FineTune the 1.58b

Open
#255 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
C++
Stars
40.3k
Forks
3.7k
PR merge metrics
No merged PRs in 30d

Description

I want to continue pretraining the 1.58b 2B model to add more on my language.
Or finetune for specific knowledge.

Are there any base code i could start with to train for 1.58b.
I've read the paper, and its used the unusual method to measure the gradient of the ternary parameter.

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

The issue names no file, test, or entry point to inspect. Clarify whether the goal is continued pretraining or task-specific fine-tuning, then identify the relevant training entry point; done would be a documented, reproducible path for the requested 1.58B workflow.

Written by the indexing model from the issue text.

Assessment

Tech stack
cpp
Domain
machine-learning
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
20/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.