microsoft / microsoft/BitNet

Model only outputs G repeatedly in interactive mode with ggml-model-i2_s.gguf

Open
#195 10 comments 4 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

When I run run_inference.py in interactive mode using the provided ggml-model-i2_s.gguf from Hugging Face, the model only outputs the character G in a loop, no matter what prompt I use.

Command used

python run_inference.py -m models/BitNet-b1.58-2B-4T/ggml-model-i2_s.gguf -p "You are a helpful assistant" -cnv

System info
Ubuntu 22.04
Python 3.9 (Conda env)
CPU only (no AVX support)

Is this expected with the i2_s quantized model? Could this be a tokenizer issue or metadata mismatch?

Thanks for your help!

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 provided command with run_inference.py and ggml-model-i2_s.gguf on the stated CPU-only setup. Read how interactive mode handles the model, tokenizer, and metadata; done means identifying the cause of the repeated G output and verifying normal responses with more than one prompt.

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
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.