Skip to content

Commit

Permalink
update cfgs
Browse files Browse the repository at this point in the history
  • Loading branch information
LZHgrla committed Jan 3, 2024
1 parent afe38a5 commit 93966aa
Show file tree
Hide file tree
Showing 192 changed files with 173 additions and 222 deletions.
Original file line number Diff line number Diff line change
Expand Up @@ -25,7 +25,7 @@

# Data
alpaca_en_path = 'tatsu-lab/alpaca'
prompt_template = PROMPT_TEMPLATE.baichuan2_chat
prompt_template = PROMPT_TEMPLATE.default
max_length = 2048
pack_to_max_length = True

Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -27,7 +27,7 @@
# Data
alpaca_zh_path = 'silk-road/alpaca-data-gpt4-chinese'
alpaca_en_path = 'tatsu-lab/alpaca'
prompt_template = PROMPT_TEMPLATE.baichuan2_chat
prompt_template = PROMPT_TEMPLATE.default
max_length = 2048
pack_to_max_length = True

Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -28,7 +28,7 @@
alpaca_zh_path = 'silk-road/alpaca-data-gpt4-chinese'
alpaca_en_path = 'tatsu-lab/alpaca'
oasst1_path = 'timdettmers/openassistant-guanaco'
prompt_template = PROMPT_TEMPLATE.baichuan2_chat
prompt_template = PROMPT_TEMPLATE.default
max_length = 2048
pack_to_max_length = True

Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -25,7 +25,7 @@

# Data
alpaca_zh_path = 'silk-road/alpaca-data-gpt4-chinese'
prompt_template = PROMPT_TEMPLATE.baichuan2_chat
prompt_template = PROMPT_TEMPLATE.default
max_length = 2048
pack_to_max_length = True

Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -27,7 +27,7 @@
# 1. Download data from https://kaggle.com/datasets/Cornell-University/arxiv
# 2. Process data by `xtuner preprocess arxiv ${DOWNLOADED_DATA} ./data/arxiv_data.json [optional arguments]` # noqa: E501
data_path = './data/arxiv_data.json'
prompt_template = PROMPT_TEMPLATE.baichuan2_chat
prompt_template = PROMPT_TEMPLATE.default
max_length = 2048
pack_to_max_length = True

Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -25,7 +25,7 @@

# Data
data_path = 'HuggingFaceH4/CodeAlpaca_20K'
prompt_template = PROMPT_TEMPLATE.baichuan2_chat
prompt_template = PROMPT_TEMPLATE.default
max_length = 2048
pack_to_max_length = True

Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -25,7 +25,7 @@

# Data
data_path = 'burkelibbey/colors'
prompt_template = PROMPT_TEMPLATE.baichuan2_chat
prompt_template = PROMPT_TEMPLATE.default
max_length = 2048
pack_to_max_length = True

Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -29,7 +29,7 @@
# download data from https://github.com/LiuHC0428/LAW-GPT
crime_kg_assitant_path = './data/CrimeKgAssitant清洗后_52k.json'
law_reference_data_path = './data/训练数据_带法律依据_92k.json'
prompt_template = PROMPT_TEMPLATE.baichuan2_chat
prompt_template = PROMPT_TEMPLATE.default
max_length = 2048
pack_to_max_length = True

Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -25,7 +25,7 @@

# Data
data_path = 'timdettmers/openassistant-guanaco'
prompt_template = PROMPT_TEMPLATE.baichuan2_chat
prompt_template = PROMPT_TEMPLATE.default
max_length = 512
pack_to_max_length = False

Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -25,7 +25,7 @@

# Data
data_path = 'timdettmers/openassistant-guanaco'
prompt_template = PROMPT_TEMPLATE.baichuan2_chat
prompt_template = PROMPT_TEMPLATE.default
max_length = 2048
pack_to_max_length = True

Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -25,7 +25,7 @@

# Data
data_path = 'garage-bAInd/Open-Platypus'
prompt_template = PROMPT_TEMPLATE.baichuan2_chat
prompt_template = PROMPT_TEMPLATE.default
max_length = 2048
pack_to_max_length = True

Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -25,7 +25,7 @@

# Data
data_path = 'b-mc2/sql-create-context'
prompt_template = PROMPT_TEMPLATE.baichuan2_chat
prompt_template = PROMPT_TEMPLATE.default
max_length = 2048
pack_to_max_length = True

Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -25,7 +25,7 @@

# Data
alpaca_en_path = 'tatsu-lab/alpaca'
prompt_template = PROMPT_TEMPLATE.baichuan2_chat
prompt_template = PROMPT_TEMPLATE.default
max_length = 2048
pack_to_max_length = True

Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -27,7 +27,7 @@
# Data
alpaca_zh_path = 'silk-road/alpaca-data-gpt4-chinese'
alpaca_en_path = 'tatsu-lab/alpaca'
prompt_template = PROMPT_TEMPLATE.baichuan2_chat
prompt_template = PROMPT_TEMPLATE.default
max_length = 2048
pack_to_max_length = True

Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -28,7 +28,7 @@
alpaca_zh_path = 'silk-road/alpaca-data-gpt4-chinese'
alpaca_en_path = 'tatsu-lab/alpaca'
oasst1_path = 'timdettmers/openassistant-guanaco'
prompt_template = PROMPT_TEMPLATE.baichuan2_chat
prompt_template = PROMPT_TEMPLATE.default
max_length = 2048
pack_to_max_length = True

Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -25,7 +25,7 @@

# Data
alpaca_zh_path = 'silk-road/alpaca-data-gpt4-chinese'
prompt_template = PROMPT_TEMPLATE.baichuan2_chat
prompt_template = PROMPT_TEMPLATE.default
max_length = 2048
pack_to_max_length = True

Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -27,7 +27,7 @@
# 1. Download data from https://kaggle.com/datasets/Cornell-University/arxiv
# 2. Process data by `xtuner preprocess arxiv ${DOWNLOADED_DATA} ./data/arxiv_data.json [optional arguments]` # noqa: E501
data_path = './data/arxiv_data.json'
prompt_template = PROMPT_TEMPLATE.baichuan2_chat
prompt_template = PROMPT_TEMPLATE.default
max_length = 2048
pack_to_max_length = True

Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -25,7 +25,7 @@

# Data
data_path = 'HuggingFaceH4/CodeAlpaca_20K'
prompt_template = PROMPT_TEMPLATE.baichuan2_chat
prompt_template = PROMPT_TEMPLATE.default
max_length = 2048
pack_to_max_length = True

Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -25,7 +25,7 @@

# Data
data_path = 'burkelibbey/colors'
prompt_template = PROMPT_TEMPLATE.baichuan2_chat
prompt_template = PROMPT_TEMPLATE.default
max_length = 2048
pack_to_max_length = True

Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -29,7 +29,7 @@
# download data from https://github.com/LiuHC0428/LAW-GPT
crime_kg_assitant_path = './data/CrimeKgAssitant清洗后_52k.json'
law_reference_data_path = './data/训练数据_带法律依据_92k.json'
prompt_template = PROMPT_TEMPLATE.baichuan2_chat
prompt_template = PROMPT_TEMPLATE.default
max_length = 2048
pack_to_max_length = True

Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -25,7 +25,7 @@

# Data
data_path = 'timdettmers/openassistant-guanaco'
prompt_template = PROMPT_TEMPLATE.baichuan2_chat
prompt_template = PROMPT_TEMPLATE.default
max_length = 512
pack_to_max_length = False

Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -25,7 +25,7 @@

# Data
data_path = 'timdettmers/openassistant-guanaco'
prompt_template = PROMPT_TEMPLATE.baichuan2_chat
prompt_template = PROMPT_TEMPLATE.default
max_length = 2048
pack_to_max_length = True

Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -25,7 +25,7 @@

# Data
data_path = 'garage-bAInd/Open-Platypus'
prompt_template = PROMPT_TEMPLATE.baichuan2_chat
prompt_template = PROMPT_TEMPLATE.default
max_length = 2048
pack_to_max_length = True

Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -25,7 +25,7 @@

# Data
data_path = 'b-mc2/sql-create-context'
prompt_template = PROMPT_TEMPLATE.baichuan2_chat
prompt_template = PROMPT_TEMPLATE.default
max_length = 2048
pack_to_max_length = True

Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -25,7 +25,7 @@

# Data
alpaca_en_path = 'tatsu-lab/alpaca'
prompt_template = PROMPT_TEMPLATE.baichuan_chat
prompt_template = PROMPT_TEMPLATE.default
max_length = 2048
pack_to_max_length = True

Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -27,7 +27,7 @@
# Data
alpaca_zh_path = 'silk-road/alpaca-data-gpt4-chinese'
alpaca_en_path = 'tatsu-lab/alpaca'
prompt_template = PROMPT_TEMPLATE.baichuan_chat
prompt_template = PROMPT_TEMPLATE.default
max_length = 2048
pack_to_max_length = True

Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -28,7 +28,7 @@
alpaca_zh_path = 'silk-road/alpaca-data-gpt4-chinese'
alpaca_en_path = 'tatsu-lab/alpaca'
oasst1_path = 'timdettmers/openassistant-guanaco'
prompt_template = PROMPT_TEMPLATE.baichuan_chat
prompt_template = PROMPT_TEMPLATE.default
max_length = 2048
pack_to_max_length = True

Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -25,7 +25,7 @@

# Data
alpaca_zh_path = 'silk-road/alpaca-data-gpt4-chinese'
prompt_template = PROMPT_TEMPLATE.baichuan_chat
prompt_template = PROMPT_TEMPLATE.default
max_length = 2048
pack_to_max_length = True

Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -27,7 +27,7 @@
# 1. Download data from https://kaggle.com/datasets/Cornell-University/arxiv
# 2. Process data by `xtuner preprocess arxiv ${DOWNLOADED_DATA} ./data/arxiv_data.json [optional arguments]` # noqa: E501
data_path = './data/arxiv_data.json'
prompt_template = PROMPT_TEMPLATE.baichuan_chat
prompt_template = PROMPT_TEMPLATE.default
max_length = 2048
pack_to_max_length = True

Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -25,7 +25,7 @@

# Data
data_path = 'HuggingFaceH4/CodeAlpaca_20K'
prompt_template = PROMPT_TEMPLATE.baichuan_chat
prompt_template = PROMPT_TEMPLATE.default
max_length = 2048
pack_to_max_length = True

Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -25,7 +25,7 @@

# Data
data_path = 'burkelibbey/colors'
prompt_template = PROMPT_TEMPLATE.baichuan_chat
prompt_template = PROMPT_TEMPLATE.default
max_length = 2048
pack_to_max_length = True

Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -29,7 +29,7 @@
# download data from https://github.com/LiuHC0428/LAW-GPT
crime_kg_assitant_path = './data/CrimeKgAssitant清洗后_52k.json'
law_reference_data_path = './data/训练数据_带法律依据_92k.json'
prompt_template = PROMPT_TEMPLATE.baichuan_chat
prompt_template = PROMPT_TEMPLATE.default
max_length = 2048
pack_to_max_length = True

Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -26,7 +26,7 @@
# Data
data_path = 'shibing624/medical'
data_config_name = 'finetune'
prompt_template = PROMPT_TEMPLATE.baichuan_chat
prompt_template = PROMPT_TEMPLATE.default
max_length = 2048
pack_to_max_length = True

Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -156,7 +156,7 @@
type=EvaluateChatHook,
tokenizer=tokenizer,
every_n_iters=evaluation_freq,
stop_word='<eoc>',
stop_words=['<eoc>'],
evaluation_inputs=evaluation_inputs,
system=SYSTEM,
prompt_template=prompt_template)
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -156,7 +156,7 @@
type=EvaluateChatHook,
tokenizer=tokenizer,
every_n_iters=evaluation_freq,
stop_word='<eoc>',
stop_words=['<eoc>'],
evaluation_inputs=evaluation_inputs,
system=SYSTEM,
prompt_template=prompt_template)
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -142,7 +142,7 @@
type=EvaluateChatHook,
tokenizer=tokenizer,
every_n_iters=evaluation_freq,
stop_word='<eoc>',
stop_words=['<eoc>'],
evaluation_inputs=evaluation_inputs,
system=SYSTEM,
prompt_template=prompt_template)
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -25,7 +25,7 @@

# Data
data_path = 'timdettmers/openassistant-guanaco'
prompt_template = PROMPT_TEMPLATE.baichuan_chat
prompt_template = PROMPT_TEMPLATE.default
max_length = 512
pack_to_max_length = False

Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -25,7 +25,7 @@

# Data
data_path = 'timdettmers/openassistant-guanaco'
prompt_template = PROMPT_TEMPLATE.baichuan_chat
prompt_template = PROMPT_TEMPLATE.default
max_length = 2048
pack_to_max_length = True

Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -25,7 +25,7 @@

# Data
data_path = 'garage-bAInd/Open-Platypus'
prompt_template = PROMPT_TEMPLATE.baichuan_chat
prompt_template = PROMPT_TEMPLATE.default
max_length = 2048
pack_to_max_length = True

Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -25,7 +25,7 @@

# Data
data_path = 'Open-Orca/OpenOrca'
prompt_template = PROMPT_TEMPLATE.baichuan_chat
prompt_template = PROMPT_TEMPLATE.default
max_length = 2048
pack_to_max_length = True

Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -25,7 +25,7 @@

# Data
data_path = 'b-mc2/sql-create-context'
prompt_template = PROMPT_TEMPLATE.baichuan_chat
prompt_template = PROMPT_TEMPLATE.default
max_length = 2048
pack_to_max_length = True

Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -25,7 +25,7 @@

# Data
data_path = 'nampdn-ai/tiny-codes'
prompt_template = PROMPT_TEMPLATE.baichuan_chat
prompt_template = PROMPT_TEMPLATE.default
max_length = 2048
pack_to_max_length = True

Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -25,7 +25,7 @@

# Data
alpaca_en_path = 'tatsu-lab/alpaca'
prompt_template = PROMPT_TEMPLATE.baichuan_chat
prompt_template = PROMPT_TEMPLATE.default
max_length = 2048
pack_to_max_length = True

Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -27,7 +27,7 @@
# Data
alpaca_zh_path = 'silk-road/alpaca-data-gpt4-chinese'
alpaca_en_path = 'tatsu-lab/alpaca'
prompt_template = PROMPT_TEMPLATE.baichuan_chat
prompt_template = PROMPT_TEMPLATE.default
max_length = 2048
pack_to_max_length = True

Expand Down

0 comments on commit 93966aa

Please sign in to comment.