423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-10-14 23:58:11 +08:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'hiyouga:main' into pixtral-patch

Browse Source 
Former-commit-id: f3ad96aea6f2602981bf5f27d2bbd1f729d11aa0
This commit is contained in:
Kingsley 2024-10-23 15:30:03 +08:00 committed by GitHub
commit 377d37fa7f
2 changed files with 5 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
src/llamafactory/extras/constants.py
View File

@ -12,6 +12,7 @@
# See the License for the specific language governing permissions and
# limitations under the License.
import os
from collections import OrderedDict, defaultdict
from enum import Enum
from typing import Dict, Optional
@ -47,7 +48,7 @@ FILEEXT2TYPE = {
IGNORE_INDEX = -100
IMAGE_PLACEHOLDER = "<image>"
IMAGE_PLACEHOLDER = os.environ.get("IMAGE_PLACEHOLDER", "<image>")
LAYERNORM_NAMES = {"norm", "ln"}
@ -95,7 +96,7 @@ SUPPORTED_CLASS_FOR_BLOCK_DIAG_ATTN = {
SUPPORTED_CLASS_FOR_S2ATTN = {"llama"}
VIDEO_PLACEHOLDER = "<video>"
VIDEO_PLACEHOLDER = os.environ.get("VIDEO_PLACEHOLDER", "<video>")
V_HEAD_WEIGHTS_NAME = "value_head.bin"

4
src/llamafactory/train/test_utils.py
View File

@ -37,9 +37,9 @@ def compare_model(model_a: "torch.nn.Module", model_b: "torch.nn.Module", diff_k
assert set(state_dict_a.keys()) == set(state_dict_b.keys())
for name in state_dict_a.keys():
if any(key in name for key in diff_keys):
assert torch.allclose(state_dict_a[name], state_dict_b[name], rtol=1e-3, atol=1e-4) is False
assert torch.allclose(state_dict_a[name], state_dict_b[name], rtol=1e-2, atol=1e-3) is False
else:
assert torch.allclose(state_dict_a[name], state_dict_b[name], rtol=1e-3, atol=1e-4) is True
assert torch.allclose(state_dict_a[name], state_dict_b[name], rtol=1e-2, atol=1e-3) is True
def check_lora_model(model: "LoraModel") -> Tuple[Set[str], Set[str]]: