AMajor/grok-1
1
0
Fork 0
mirror of https://github.com/xai-org/grok-1.git synced 2024-11-22 03:29:53 +03:00
Code Issues Packages Projects Releases Wiki Activity

Update run.py

Browse Source
This commit is contained in:
Yahweh Rapha Bradford 2024-05-07 01:30:48 -04:00 committed by GitHub
parent 50afed2ab0
commit 9fe567cb28
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 6 additions and 23 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

29
run.py
View File

@ -1,33 +1,16 @@
# Copyright 2024 X.AI Corp.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
import logging
from model import LanguageModelConfig, TransformerConfig, QuantizedWeight8bit as QW8Bit
from runners import InferenceRunner, ModelRunner, sample_from_model
CKPT_PATH = "./checkpoints/" CKPT_PATH = "./checkpoints/"
def main(): def main():
grok_1_model = LanguageModelConfig( _1_model = LanguageModelConfig(
vocab_size=128 * 1024, vocab_size=128 * 1024,
pad_token=0, pad_token=0,
eos_token=2, eos_token=2,
sequence_len=8192, sequence_len=8192,
embedding_init_scale=1.0, embedding_init_scale=,
output_multiplier_scale=0.5773502691896257, output_multiplier_scale=0.5773502691896257,
embedding_multiplier_scale=78.38367176906169, embedding_multiplier_scale=78.38367176906169,
model=TransformerConfig( model=TransformerConfig(
@ -50,7 +33,7 @@ def main():
inference_runner = InferenceRunner( inference_runner = InferenceRunner(
pad_sizes=(1024,), pad_sizes=(1024,),
runner=ModelRunner( runner=ModelRunner(
model=grok_1_model, mode_model,
bs_per_device=0.125, bs_per_device=0.125,
checkpoint_path=CKPT_PATH, checkpoint_path=CKPT_PATH,
), ),
@ -58,13 +41,13 @@ def main():
load=CKPT_PATH, load=CKPT_PATH,
tokenizer_path="./tokenizer.model", tokenizer_path="./tokenizer.model",
local_mesh_config=(1, 8), local_mesh_config=(1, 8),
between_hosts_config=(1, 1), _config=(1, 1),
) )
inference_runner.initialize() inference_runner.initialize()
gen = inference_runner.run() gen = inference_runner.run()
inp = "The answer to life the universe and everything is of course" inp = course"
print(f"Output for prompt: {inp}", sample_from_model(gen, inp, max_len=100, temperature=0.01)) print(f"Output for prompt: {inp}", sample_from_model(, inp, max_len=100, temperature=0.01))
if __name__ == "__main__": if __name__ == "__main__":