Skip to content

Llama2 interface bug #2318

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

Merged
mravanelli merged 3 commits into from
Dec 28, 2023
+28 −5
Merged

Llama2 interface bug #2318

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
316b0cf
fix llama2 interface bug
poonehmousavi Dec 27, 2023
77e8a83
fix minor bug
poonehmousavi Dec 27, 2023
1be6fd3
update multiwox.csv with correct db and HF link
poonehmousavi Dec 27, 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
9 changes: 5 additions & 4 deletions speechbrain/inference/text.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -304,8 +304,9 @@ class Llama2ResponseGenerator(ResponseGenerator):
"""

def __init__(self, *args, **kwargs):
super().__init__(*args, **kwargs)
self.model = self.model.to("cuda")
run_opts = {"device": "cuda"}
super().__init__(run_opts=run_opts, *args, **kwargs)
# self.model = self.model#.to("cuda")

def generate(self, inputs):
"""
Expand All @@ -320,7 +321,7 @@ def generate(self, inputs):
response
Generated hypothesis for the user input based on the dialogue history.
"""
prompt_bos = inputs.to(self.model.model.device)
prompt_bos = inputs[0].to(self.model.model.device)
padding_mask = ~self.hparams.padding_mask(
prompt_bos, pad_idx=self.tokenizer.pad_token_id
)
Expand Down Expand Up @@ -377,4 +378,4 @@ def generate_prompt(idx_and_item):
prompt_bos = torch.cat(
(torch.tensor([self.tokenizer.bos_token_id]), prompt_ids)
)
return prompt_bos.unsqueeze(0)
return prompt_bos.unsqueeze(0).unsqueeze(dim=0)
22 changes: 22 additions & 0 deletions speechbrain/lobes/models/huggingface_transformers/llama2.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -250,6 +250,17 @@ def _modify_state_dict(self, path, replacables=["base_model"]):
is_quantized=True,
)

from transformers.utils.quantization_config import (
QuantizationMethod,
)

self.model._is_quantized_training_enabled = True
self.model.is_8bit_serializable = True
self.model.quantization_method = QuantizationMethod.BITS_AND_BYTES
self.model.is_quantized = True
self.model.is_loaded_in_4bit = True
self.model.is_loaded_in_8bit = False

quantization_config = {}
quantization_config["bnb_4bit_compute_dtype"] = "float16"
quantization_config["bnb_4bit_quant_type"] = "nf4"
Expand All @@ -264,6 +275,17 @@ def _modify_state_dict(self, path, replacables=["base_model"]):

self.model.config.quantization_config = quantization_config

from accelerate import dispatch_model

device_map_kwargs = {
"device_map": {"": 0},
"offload_dir": None,
"offload_index": None,
"skip_keys": "past_key_values",
}

dispatch_model(self.model, **device_map_kwargs)

self.model = prepare_model_for_kbit_training(self.model)

lora_config = LoraConfig(
Expand Down
2 changes: 1 addition & 1 deletion tests/recipes/MultiWOZ.csv
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,3 +1,3 @@
Task,Dataset,Script_file,Hparam_file,Data_prep_file,Readme_file,Result_url,HF_repo,test_debug_flags,test_debug_checks,performance
Response-Generation,MultiWOZ,recipes/MultiWOZ/response_generation/gpt/train_with_gpt.py,recipes/MultiWOZ/response_generation/gpt/hparams/train_gpt.yaml,recipes/MultiWOZ/response_generation/gpt/multiwoz_prepare.py,recipes/MultiWOZ/response_generation/README.md,https://www.dropbox.com/sh/vm8f5iavohr4zz9/AACrkOxXuxsrvJy4Cjpih9bQa?dl=0,https://huggingface.co/speechbrain/MultiWOZ-GPT-Response_Generation,--data_folder=tests/samples/ASR/ --train_annotation=tests/samples/annotation/response_generation_train_multiwoz.json --valid_annotation=tests/samples/annotation/response_generation_train_multiwoz.json --test_annotation=tests/samples/annotation/response_generation_train_multiwoz.json --number_of_epochs=2 --skip_prep=True,,Test-PPL=4.01 Test_BLEU-4=2.54e-04
Response-Generation,MultiWOZ,recipes/MultiWOZ/response_generation/llama2/train_with_llama2.py,recipes/MultiWOZ/response_generation/llama2/hparams/train_llama2.yaml,recipes/MultiWOZ/response_generation/llama2/multiwoz_prepare.py,recipes/MultiWOZ/response_generation/README.md,https://www.dropbox.com/sh/vm8f5iavohr4zz9/AACrkOxXuxsrvJy4Cjpih9bQa?dl=0,https://huggingface.co/speechbrain/MultiWOZ-GPT-Response_Generation,--data_folder=tests/samples/ASR/ --train_annotation=tests/samples/annotation/response_generation_train_multiwoz.json --valid_annotation=tests/samples/annotation/response_generation_train_multiwoz.json --test_annotation=tests/samples/annotation/response_generation_train_multiwoz.json --number_of_epochs=2 --skip_prep=True,,Test-PPL=2.90 Test_BLEU-4=7.45e-04
Response-Generation,MultiWOZ,recipes/MultiWOZ/response_generation/llama2/train_with_llama2.py,recipes/MultiWOZ/response_generation/llama2/hparams/train_llama2.yaml,recipes/MultiWOZ/response_generation/llama2/multiwoz_prepare.py,recipes/MultiWOZ/response_generation/README.md,https://www.dropbox.com/sh/d093vsje1d7ijj9/AAA-nHEd_MwNEFJfBGLmXxJra?dl=0,https://huggingface.co/speechbrain/MultiWOZ-Llama2-Response_Generation,--data_folder=tests/samples/ASR/ --train_annotation=tests/samples/annotation/response_generation_train_multiwoz.json --valid_annotation=tests/samples/annotation/response_generation_train_multiwoz.json --test_annotation=tests/samples/annotation/response_generation_train_multiwoz.json --number_of_epochs=2 --skip_prep=True,,Test-PPL=2.90 Test_BLEU-4=7.45e-04