Skip to content

Fix opt_125m_woq_gptq_int4_dq_ggml issue #1965

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Aug 6, 2024
Merged

Fix opt_125m_woq_gptq_int4_dq_ggml issue #1965

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
b4b6327
increase damp percent
Kaihui-intel Aug 6, 2024
f5fd0c8
trigger ci test
chensuyue Aug 6, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion .azure-pipelines/model-test-3x.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10,7 +10,7 @@ pr:
include:
- neural_compressor/common
- neural_compressor/torch
- examples/3.x_api/pytorch/nlp/huggingface_models/language-modeling/quantization/llm
- examples/3.x_api/pytorch/nlp/huggingface_models/language-modeling/quantization/weight_only
- setup.py
- requirements_pt.txt
- .azure-pipelines/scripts/models
Expand Down
2 changes: 1 addition & 1 deletion ...pi/pytorch/nlp/huggingface_models/language-modeling/quantization/weight_only/run_quant.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -50,7 +50,7 @@ function run_tuning {
extra_cmd=$extra_cmd" --double_quant_type BNB_NF4"
elif [ "${topology}" = "opt_125m_woq_gptq_int4_dq_ggml" ]; then
model_name_or_path="facebook/opt-125m"
extra_cmd=$extra_cmd" --woq_algo GPTQ --woq_bits 4 --woq_group_size 128 --woq_scheme asym --woq_use_mse_search --gptq_use_max_length --gptq_percdamp 0.1 --gptq_actorder"
extra_cmd=$extra_cmd" --woq_algo GPTQ --woq_bits 4 --woq_group_size 128 --woq_scheme asym --woq_use_mse_search --gptq_use_max_length --gptq_percdamp 0.8 --gptq_actorder"
extra_cmd=$extra_cmd" --double_quant_type GGML_TYPE_Q4_K"
elif [ "${topology}" = "llama2_7b_gptq_int4" ]; then
model_name_or_path="meta-llama/Llama-2-7b-hf"
Expand Down
Loading