ceos/unsloth
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Update llama.py

Browse source
This commit is contained in:
Daniel Han 2024-11-26 00:08:15 -08:00
commit 833f64df03
1 changed files with 4 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

8
unsloth/models/llama.py
View file

@ -65,7 +65,7 @@ except:
# Old HF Hub versions <= 0.0.25
from huggingface_hub.utils._token import get_token
pass
from triton import __version__ as triton_version
def original_apply_qkv(self, X):
Q = self.q_proj(X)
@ -1549,9 +1549,9 @@ class FastLlamaModel:
max_memory = round(gpu_stats.total_memory / 1024 / 1024 / 1024, 3)
statistics = \
f"==((====))== Unsloth {__version__}: Fast {model_patcher.__name__[4:-5]} patching. Transformers = {transformers_version}.\n"\
f" \\\ /| GPU: {gpu_stats.name}. Max memory: {max_memory} GB. Platform = {platform_system}.\n"\
f"O^O/ \_/ \\ Pytorch: {torch.__version__}. CUDA = {gpu_stats.major}.{gpu_stats.minor}. CUDA Toolkit = {torch.version.cuda}.\n"\
f"==((====))== Unsloth {__version__}: Fast {model_patcher.__name__[4:-5]} patching. Transformers:{transformers_version}.\n"\
f" \\\ /| GPU: {gpu_stats.name}. Max memory: {max_memory} GB. Platform: {platform_system}.\n"\
f"O^O/ \_/ \\ Torch: {torch.__version__}. CUDA: {gpu_stats.major}.{gpu_stats.minor}. CUDA Toolkit: {torch.version.cuda}. Triton: {triton_version}\n"\
f"\ / Bfloat16 = {str(SUPPORTS_BFLOAT16).upper()}. FA [Xformers = {xformers_version}. FA2 = {HAS_FLASH_ATTENTION}]\n"\
f' "-____-" Free Apache license: http://github.com/unslothai/unsloth'
print(statistics)