Skip to content
GitLab
Menu
Projects
Groups
Snippets
Loading...
Help
Help
Support
Community forum
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in / Register
Toggle navigation
Menu
Open sidebar
ModelZoo
llama3_pytorch
Commits
0aea7dd1
Commit
0aea7dd1
authored
May 14, 2024
by
Rayyyyy
Browse files
Modify chat.sh examples.
parent
a540af5e
Changes
1
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
16 additions
and
3 deletions
+16
-3
chat.sh
chat.sh
+16
-3
No files found.
chat.sh
View file @
0aea7dd1
#!/bin/bash
echo
"Export params ..."
export
HIP_VISIBLE_DEVICES
=
0
# 可自行修改为指定显卡号
export
HIP_VISIBLE_DEVICES
=
0,1,2,3,4,5,6,7
# 可自行修改为指定显卡号
export
HSA_FORCE_FINE_GRAIN_PCIE
=
1
export
USE_MIOPEN_BATCHNORM
=
1
export
MASTER_ADDR
=
localhost
export
MASTER_PORT
=
12355
export
RANK
=
0
export
WORLD_SIZE
=
1
echo
"Starting ..."
# 8B
# torchrun --nproc_per_node 1 llama3_chat.py \
# --ckpt_dir /data/Meta-llama3-models/Meta-Llama-3-8B-Instruct/original/ \
# --tokenizer_path /data/Meta-llama3-models/Meta-Llama-3-8B-Instruct/original/tokenizer.model \
# --max_seq_len 2048 \
# --max_batch_size 6
torchrun
--nproc_per_node
1 llama3_chat.py
--ckpt_dir
Meta-Llama-3-8B-Instruct/original/
--tokenizer_path
Meta-Llama-3-8B-Instruct/original/tokenizer.model
--max_seq_len
2048
--max_batch_size
6
# 70B
torchrun
--nproc_per_node
8 llama3_chat.py
\
--ckpt_dir
/data/Meta-llama3-models/Meta-Llama-3-70B-Instruct/original/
\
--tokenizer_path
/data/Meta-llama3-models/Meta-Llama-3-70B-Instruct/original/tokenizer.model
\
--max_seq_len
2048
\
--max_batch_size
6
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
.
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment