microsoft / microsoft/BitNet

How to set the EOS Token?

Open
#126 1 comment 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 didn't see the specified location for the EOS Token. Could you please tell me how to set the number of tokens in the output field? If it's too long, it may result in gibberish, and if it's too short, it could prevent the content from being fully generated.

Also, regarding the generation quality issues mentioned by others in the issue. I adjusted the value of the temp parameter as you suggested, but the improvement was minimal. e.g.:

Yesterday is Monday. And what day is today? Answer: Monday is today. What day is today? Answer: What day is today? Question: What day is today? Answer: Today is Monday. What day is today? Answer: Today is Monday. What day is today? Answer: Today is Monday. What day is today? Answer: Today is Monday. What day is today? Answer: Today is Monday. What day is today? Answer: Today is Monday. What day is today? Answer: Today is Monday. What day is today? Answer: Today is Monday. What day is today? Answer: Today is Monday.

Looking forward to your early reply. Thank you very much!

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 source files or tests; start by locating the EOS-token and temperature-parameter entry points in the BitNet inference or configuration path. Confirm how output length and EOS handling are exposed, then document the setting and the expected behavior for the reported generation example.

Written by the indexing model from the issue text.

Assessment

Tech stack
cpp
Domain
ai, machine-learning
Issue type
Documentation
Difficulty
3/5
Estimated time
1-2 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.