Incorrect Output or Generating Random Characters
Nobody has claimed this yet.
- Dominant language
- C++
- Stars
- 40.3k
- Forks
- 3.7k
- PR merge metrics
- No merged PRs in 30d
Description
I downloaded the 1bitLLM/bitnet_b1_58-large and 1bitLLM/bitnet_b1_58-3B models. When I run the inference commands, the model does not error out but produces incorrect outputs.
python setup_env.py -md models/bitnet_b1_58-3B -q tl1
python run_inference.py -m models/bitnet_b1_58-3B/ggml-model-tl1.gguf -p "You are a helpful assistant" -cnv
When using the i2_s quantization in the above commands, it repeats random characters.
My platform is macOS (Apple M2 Pro)
Could you please help me resolve this?
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by reproducing the reported commands with models/bitnet_b1_58-3B, the tl1 quantization, and the i2_s quantization on macOS. Read setup_env.py and run_inference.py, then compare the generated output with the attached examples; done means inference produces coherent, non-repeating output for the affected models.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- cpp, python
- Domain
- ai, machine-learning
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Quiet
- Clarity
- Needs clarification
- Newbie friendliness
- 35/100