Skip to content

commit #18

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

Open
sfc-gh-zhwang wants to merge 3 commits into
base: corvo
Choose a base branch
from
Open

commit #18

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
ffc302b
commit
sfc-gh-zhwang Sep 29, 2023
69b87ae
commit
sfc-gh-zhwang Sep 29, 2023
bbf6c70
commit
sfc-gh-zhwang Sep 29, 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
6 changes: 3 additions & 3 deletions examples/cpp/llama/llama_config.ini
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,7 +6,7 @@ tensor_para_size=1
pipeline_para_size=1

model_name=llama_7b
model_dir=/notebooks/llama-2-70b-hf-ft-tp-1_llama_decoder/1/1-gpu/
model_dir=/notebooks/code-llama-ft/code-llama-34b/code-llama-34b_llama_decoder/1/1-gpu

[request]
beam_width=1 # beam width for beam search
Expand All @@ -17,14 +17,14 @@ repetition_penalty=1.0 ; Use for sampling
presence_penalty=0.0 ; Only one of repetition_penalty and presence_penalty are allowed.
len_penalty=0.0
beam_search_diversity_rate=0.0
request_batch_size=8 # determine by the request
request_batch_size=1 # determine by the request
request_output_len=32 # determine by the request

[llama_7b]
head_num = 64
kv_head_num = 8
size_per_head = 128
inter_size = 28672
inter_size = 22016
num_layer = 3
rotary_embedding = 128
layernorm_eps = 1e-05
Expand Down
2 changes: 1 addition & 1 deletion examples/cpp/llama/llama_example.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -44,7 +44,7 @@ int main(int argc, char* argv[])
ini_name = std::string(argv[1]);
}
else {
ini_name = "/notebooks/FasterTransformer/examples/cpp/llama/llama_config.ini";
ini_name = "/notebooks/tmp/FasterTransformer/examples/cpp/llama/llama_config.ini";
}

INIReader reader = INIReader(ini_name);
Expand Down
7 changes: 0 additions & 7 deletions examples/cpp/llama/start_ids.csv
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,8 +1 @@
1, 18637, 29892, 526, 366, 1136, 455, 2470, 29973, 1815, 366, 5193, 304, 592, 29973
1, 18637
1, 18637, 29892, 526, 366, 1136, 455, 2470, 29973, 1815, 366, 5193, 304, 592, 29973
1, 18637, 29892, 526, 366, 1136, 455, 2470, 29973, 1815, 366, 5193, 304, 592, 29973
1, 18637, 29892, 526, 366, 1136, 455, 2470, 29973, 1815, 366, 5193, 304, 592, 29973
1, 18637, 29892, 526, 366, 1136, 455, 2470, 29973, 1815, 366, 5193, 304, 592, 29973
1, 18637, 29892, 526, 366, 1136, 455, 2470, 29973, 1815, 366, 5193, 304, 592, 29973
1, 18637, 29892, 526, 366, 1136