apunkt/doc-to-lora
1
0
Fork 0
mirror of https://github.com/SakanaAI/doc-to-lora.git synced 2026-07-23 17:01:04 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

self-gen w/ closed_qa format + perceiver scripts + no strip response

Browse source
This commit is contained in:
51616 2025-07-08 14:21:43 +00:00
parent d26f246937
commit c9e958f963
6 changed files with 145 additions and 12 deletions
Download patch file Download diff file Expand all files Collapse all files

2
scripts/short_ctx/gemma_qa_short_ctx_perceiver.sh
View file

@ -19,7 +19,7 @@ uv run accelerate launch --main_process_port $port \
--per_device_eval_batch_size=64 \
--target_modules=down_proj \
--num_blocks=8 \
--num_self_attn_per_block=6 \
--num_self_attn_per_block=3 \
--n_latent_queries=208 \
--num_pre_head_layers=1 \
--lora_r=8 \

2
scripts/short_ctx/gemma_qa_short_ctx_perceiver_l2l.sh
View file

@ -19,7 +19,7 @@ uv run accelerate launch --main_process_port $port \
--per_device_eval_batch_size=32 \
--target_modules=down_proj \
--num_blocks=8 \
--num_self_attn_per_block=6 \
--num_self_attn_per_block=3 \
--ctx_encoder_type=per_layer_activations \
--n_latent_queries=8 \
--num_pre_head_layers=1 \