microsoft / microsoft/TransformerCompression

Issues with LLAMA 3-8B-Instruct model

Open
#177 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
460
Forks
58
Avg merge
8h 40m
Merged PRs (30d)
1

Description

Hi

I get this error while using SliceGPT for the LLama Instruct models:
ValueError: rope_scaling must be a dictionary with two fields, type and factor, got {'factor': 8.0, 'low_freq_factor': 1.0, 'high_freq_factor': 4.0, 'original_max_position_embeddings': 8192, 'rope_type': 'llama3'}

To overcome this, I updated the Transformers package version to 4.44.2. However, slice GPT is not compatible with this transformer version. Can anyone please help in solving this issue?

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 reproducing the reported rope_scaling error with the LLAMA 3-8B-Instruct model and inspect SliceGPT's Transformers compatibility. Done means the model can be processed without this error on a supported Transformers version.

Written by the indexing model from the issue text.

Assessment

Tech stack
huggingface, python
Domain
machine-learning
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 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.