jalr/tabbyAPI-ollama
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Model: Add tokens in responses

Browse source 
Signed-off-by: kingbri <bdashore3@proton.me>
This commit is contained in:
kingbri 2023-11-17 23:33:48 -05:00
parent 7f18ea1d7c
commit 2ad79cb9ea
1 changed files with 1 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

2
model.py
View file

@ -355,4 +355,4 @@ class ModelContainer:
if eos or generated_tokens == max_tokens: break
elapsed_time = last_chunk_time - start_time
print(f"Response generated in {round(elapsed_time, 2)} seconds ({round(generated_tokens / elapsed_time, 2)} T/s)")
print(f"Response: {round(generated_tokens, 2)} tokens generated in {round(elapsed_time, 2)} seconds ({round(generated_tokens / elapsed_time, 2)} T/s)")