deepspeedai / deepspeedai/DeepSpeedExamples

Why does the chat.py script model answer normally, but answer repeatedly when step3

Open
#807 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
6.8k
Forks
1.1k
Avg merge
2d 16h
Merged PRs (30d)
1

Description

I deployed the model using the chat.py script and the model answered normally, but the output of the actor model was repeated throughout the step3.

chat.py:
捕获

step3:
捕获2

actor model: llama2-13b
rw model: llama2-13b
hybrid engin enable

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

Start by comparing the chat.py deployment with the step3 configuration and output, focusing on the actor and reward models and the enabled hybrid engine. Reproduce the repeated output with the stated Llama2-13B setup and identify the configuration or execution difference that causes it; done means explaining the repetition and confirming normal step3 output.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
20/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.