Skip to content
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

support to disable exllama for gptq #604

Merged
merged 3 commits into from
Sep 19, 2023
Merged

support to disable exllama for gptq #604

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
91294cf
support to disable exllama for gptq
winglian Sep 19, 2023
a08404b
update property instead of item
winglian Sep 19, 2023
1e38c56
fix config key
winglian Sep 19, 2023
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
4 changes: 1 addition & 3 deletions examples/llama-2/gptq-lora.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,7 +2,7 @@ base_model: TheBloke/Llama-2-7B-GPTQ
base_model_config: TheBloke/Llama-2-7B-GPTQ
is_llama_derived_model: false
gptq: true
gptq_bits: 4
gptq_disable_exllama: true
model_type: AutoModelForCausalLM
tokenizer_type: LlamaTokenizer
tokenizer_use_fast: true
Expand Down Expand Up @@ -62,8 +62,6 @@ xformers_attention:
flash_attention:
sdp_attention:
flash_optimum:
gptq_groupsize:
gptq_model_v1:
warmup_steps: 100
eval_steps:
save_steps:
Expand Down
4 changes: 4 additions & 0 deletions src/axolotl/utils/models.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -198,6 +198,10 @@ def load_model(
if not hasattr(model_config, "quantization_config"):
LOG.warning("model config does not contain quantization_config information")
else:
if cfg.gptq_disable_exllama is not None:
model_config.quantization_config[
"disable_exllama"
] = cfg.gptq_disable_exllama
model_kwargs["quantization_config"] = GPTQConfig(
**model_config.quantization_config
)
Expand Down