Skip to content
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

Jump to bottom

allow overriding of model_config parameters from the YML #853

Merged
merged 4 commits into from
Nov 16, 2023
Merged

allow overriding of model_config parameters from the YML #853

Changes from 1 commit
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
8dbd7cc
allow overriding of model_config parameters from the YML
winglian Nov 15, 2023
13483fe
remove old logging, update readme
winglian Nov 15, 2023
539da6b
move the updating of model config to the load_model_config function
winglian Nov 15, 2023
c7a60a2
add warning for deprecated rope_scaling in the root of the YML config
winglian Nov 16, 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
54 changes: 22 additions & 32 deletions src/axolotl/utils/models.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,7 +17,6 @@
AutoTokenizer,
BitsAndBytesConfig,
GPTQConfig,
LlamaConfig,
PreTrainedModel,
PreTrainedTokenizerBase,
)
Expand Down Expand Up @@ -51,7 +50,7 @@ def load_tokenizer(cfg):
if cfg.tokenizer_type:
tokenizer_cls = getattr(transformers, cfg.tokenizer_type)

tokenizer_config = cfg.tokenizer_config or cfg.base_model_config
tokenizer_config = cfg.tokenizer_config or cfg.base_model_config or cfg.base_model
tokenizer = tokenizer_cls.from_pretrained(
tokenizer_config,
trust_remote_code=cfg.trust_remote_code or False,
Expand Down Expand Up @@ -110,7 +109,6 @@ def load_model(
Load a model for a given configuration and tokenizer.
"""
base_model = cfg.base_model
base_model_config = cfg.base_model_config
model_type = cfg.model_type
model_config = load_model_config(cfg)

Expand Down Expand Up @@ -234,20 +232,20 @@ def load_model(
):
model_kwargs["use_flash_attention_2"] = True

if cfg.model_config:
for key, val in cfg.model_config.items():
setattr(model_config, key, val)
winglian marked this conversation as resolved.
Show resolved Hide resolved

if cfg.rope_scaling:
setattr(model_config, "rope_scaling", cfg.rope_scaling)

try:
if cfg.is_llama_derived_model and not cfg.trust_remote_code and not cfg.gptq:
from transformers import LlamaForCausalLM

config_kwargs = {}
if cfg.rope_scaling:
config_kwargs["rope_scaling"] = cfg.rope_scaling
config = LlamaConfig.from_pretrained(
base_model_config,
**config_kwargs,
)
model = LlamaForCausalLM.from_pretrained(
base_model,
config=config,
config=model_config,
load_in_8bit=cfg.load_in_8bit and cfg.adapter is not None,
load_in_4bit=cfg.load_in_4bit and cfg.adapter is not None,
**model_kwargs,
Expand Down Expand Up @@ -305,49 +303,47 @@ def load_model(
if cfg.gptq:
model = AutoModelForCausalLM.from_pretrained(
base_model,
config=model_config,
trust_remote_code=cfg.trust_remote_code or False,
**model_kwargs,
)
else:
model = getattr(transformers, model_type).from_pretrained(
base_model,
config=model_config,
load_in_8bit=cfg.load_in_8bit and cfg.adapter is not None,
load_in_4bit=cfg.load_in_4bit and cfg.adapter is not None,
trust_remote_code=cfg.trust_remote_code or False,
**model_kwargs,
)
else:
config = AutoConfig.from_pretrained(
base_model,
trust_remote_code=cfg.trust_remote_code or False,
)
# Shouldn't be a problem most of the time. will obviously error if the model doesn't support this
# when training starts
if (
hasattr(config, "max_seq_len")
and config.max_seq_len
and cfg.sequence_len > config.max_seq_len
hasattr(model_config, "max_seq_len")
and model_config.max_seq_len
and cfg.sequence_len > model_config.max_seq_len
):
config.max_seq_len = cfg.sequence_len
model_config.max_seq_len = cfg.sequence_len
LOG.warning(f"increasing context length to {cfg.sequence_len}")
elif (
hasattr(config, "max_sequence_length")
and config.max_sequence_length
and cfg.sequence_len > config.max_sequence_length
hasattr(model_config, "max_sequence_length")
and model_config.max_sequence_length
and cfg.sequence_len > model_config.max_sequence_length
):
config.max_sequence_length = cfg.sequence_len
model_config.max_sequence_length = cfg.sequence_len
LOG.warning(f"increasing context length to {cfg.sequence_len}")
if cfg.gptq:
model = AutoModelForCausalLM.from_pretrained(
base_model,
config=config,
config=model_config,
trust_remote_code=cfg.trust_remote_code or False,
**model_kwargs,
)
else:
model = AutoModelForCausalLM.from_pretrained(
base_model,
config=config,
config=model_config,
load_in_8bit=cfg.load_in_8bit and cfg.adapter is not None,
load_in_4bit=cfg.load_in_4bit and cfg.adapter is not None,
trust_remote_code=cfg.trust_remote_code or False,
Expand All @@ -358,13 +354,7 @@ def load_model(
"Exception raised attempting to load model, retrying with AutoModelForCausalLM"
winglian marked this conversation as resolved.
Show resolved Hide resolved
)
LOG.exception(err)
model = AutoModelForCausalLM.from_pretrained(
base_model,
load_in_8bit=cfg.load_in_8bit and cfg.adapter is not None,
load_in_4bit=cfg.load_in_4bit and cfg.adapter is not None,
trust_remote_code=cfg.trust_remote_code or False,
**model_kwargs,
)
raise err

embeddings_len = (
math.ceil(len(tokenizer) / 32) * 32
Expand Down