meta-llama/Llama-3.2-1B, The model is not working properly
Open
@cccclai is already working on this.
Since Nov 14, 2024.
module: examples
module: qnn
triaged
- Dominant language
- Python
- Stars
- 5k
- Forks
- 1.2k
- Avg merge
- 2d 10h
- Merged PRs (30d)
- 581
Description
📚 The doc issue
I use this command transform model(Llama-3.2-1B)
python -m examples.models.llama.export_llama --checkpoint "${MODEL_DIR}/consolidated.00.pth" -p "${MODEL_DIR}/params.json" -kv --disable_dynamic_shape --qnn --pt2e_quantize qnn_16a16w -d fp32 --num_sharding 16 --metadata '{"get_bos_id":128000, "get_eos_ids":[128009, 128001]}' --output_name="test.pte"
but the result is whis when i run it on phone
Suggest a potential alternative/fix
No response
Contributor guide
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.
Assessment
This issue has not been assessed yet.