Skip to content

Fix Stop Condition and Temperature Handling #17

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

Closed
wants to merge 2 commits into from
Closed

Fix Stop Condition and Temperature Handling #17

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
5f600aa
Bug fixes: 1. Temperature range 0-2 2.
ManilShrestha Jul 9, 2024
0d1c77d
Bug fixes 1. Temperature range 0-2 2. Fix prefered EOS bug
ManilShrestha Jul 9, 2024
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: 2 additions & 4 deletions llm_exl2_dynamic_gen.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -202,8 +202,6 @@ def get_stop_conditions(tokenizer):
# get_stop_condition special case if model is llama3
if "llama3" in repo_str:
return [tokenizer.single_id("<|eot_id|>"), tokenizer.eos_token_id]
# elif prompt_format == "granite":
# return [tokenizer.eos_token_id, "\n\nQuestion:"]
else:
return [tokenizer.eos_token_id]

Expand Down Expand Up @@ -465,12 +463,12 @@ def process_prompts():
preferred_eos.append(stop_at)

gen_settings = ExLlamaV2Sampler.Settings()
gen_settings.temperature = 1.0 if temperature>1 else temperature # To make sure the temperature value does not exceed 1
gen_settings.temperature = 2.0 if temperature>2 else temperature # To make sure the temperature value does not exceed 2

job = ExLlamaV2DynamicJob(
input_ids = ids,
max_new_tokens = max_tokens,
stop_conditions = preferred_eos if stop_at is None else [tokenizer.eos_token_id, stop_at],
stop_conditions = preferred_eos,
gen_settings = gen_settings,
filters = filters,
token_healing = healing
Expand Down
6 changes: 2 additions & 4 deletions llm_exl2_dynamic_gen_lora.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -204,8 +204,6 @@ def get_stop_conditions(tokenizer):
# get_stop_condition special case if model is llama3
if "llama3" in repo_str:
return [tokenizer.single_id("<|eot_id|>"), tokenizer.eos_token_id]
# elif prompt_format == "granite":
# return [tokenizer.eos_token_id, "\n\nQuestion:"]
else:
return [tokenizer.eos_token_id]

Expand Down Expand Up @@ -493,12 +491,12 @@ def process_prompts():
preferred_eos.append(stop_at)

gen_settings = ExLlamaV2Sampler.Settings()
gen_settings.temperature = 1.0 if temperature>1 else temperature # To make sure the temperature value does not exceed 1
gen_settings.temperature = 2.0 if temperature>2 else temperature # To make sure the temperature value does not exceed 2

job = ExLlamaV2DynamicJob(
input_ids = ids,
max_new_tokens = max_tokens,
stop_conditions = preferred_eos if stop_at is None else [tokenizer.eos_token_id, stop_at],
stop_conditions = preferred_eos,
gen_settings = gen_settings,
filters = filters,
token_healing = healing
Expand Down