Mirrors/text-generation-webui
1
0
Fork 0
mirror of https://github.com/oobabooga/text-generation-webui.git synced 2024-11-22 08:07:56 +01:00
Code Issues Packages Projects Releases Wiki Activity

Make --verbose output less spammy

Browse Source
This commit is contained in:
oobabooga 2024-05-18 09:57:00 -07:00
parent 0d90b3a25c
commit a4611232b7
1 changed files with 17 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

21
modules/text_generation.py
View File

@ -56,8 +56,7 @@ def _generate_reply(question, state, stopping_strings=None, is_chat=False, escap
if generate_func != generate_reply_HF and shared.args.verbose: if generate_func != generate_reply_HF and shared.args.verbose:
logger.info("PROMPT=") logger.info("PROMPT=")
print(question) print_prompt(question)
print()
# Prepare the input # Prepare the input
original_question = question original_question = question
@ -343,8 +342,7 @@ def generate_reply_HF(question, original_question, seed, state, stopping_strings
print() print()
logger.info("PROMPT=") logger.info("PROMPT=")
print(decode(input_ids[0], skip_special_tokens=False)) print_prompt(decode(input_ids[0], skip_special_tokens=False))
print()
# Handle StreamingLLM for llamacpp_HF # Handle StreamingLLM for llamacpp_HF
if shared.model.__class__.__name__ == 'LlamacppHF' and shared.args.streaming_llm: if shared.model.__class__.__name__ == 'LlamacppHF' and shared.args.streaming_llm:
@ -433,3 +431,18 @@ def generate_reply_custom(question, original_question, seed, state, stopping_str
new_tokens = len(encode(original_question + reply)[0]) - original_tokens new_tokens = len(encode(original_question + reply)[0]) - original_tokens
print(f'Output generated in {(t1-t0):.2f} seconds ({new_tokens/(t1-t0):.2f} tokens/s, {new_tokens} tokens, context {original_tokens}, seed {seed})') print(f'Output generated in {(t1-t0):.2f} seconds ({new_tokens/(t1-t0):.2f} tokens/s, {new_tokens} tokens, context {original_tokens}, seed {seed})')
return return
def print_prompt(prompt, max_chars=2000):
DARK_YELLOW = "\033[38;5;3m"
RESET = "\033[0m"
if len(prompt) > max_chars:
half_chars = max_chars // 2
hidden_len = len(prompt[half_chars:-half_chars])
hidden_msg = f"{DARK_YELLOW}[...{hidden_len} characters hidden...]{RESET}"
print(prompt[:half_chars] + hidden_msg + prompt[-half_chars:])
else:
print(prompt)
print()