Skip to content

Update module_tree #2479

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

Closed
ZX-ModelCloud wants to merge 6 commits into from
Closed

Update module_tree #2479

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
931c9ea
Adapt module_tree for compatibility with Transformers v5.3.0 modeling…
ZX-ModelCloud Mar 12, 2026
2888ce4
revert minimax_m2.py
ZX-ModelCloud Mar 12, 2026
dfa7ba2
update mixtral module_tree
ZX-ModelCloud Mar 12, 2026
0acb22a
fix test_mixtral.py
ZX-ModelCloud Mar 12, 2026
d55ee50
revert phi3
ZX-ModelCloud Mar 12, 2026
27acaef
revert phi3
ZX-ModelCloud Mar 12, 2026
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
12 changes: 7 additions & 5 deletions gptqmodel/models/definitions/mixtral.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,14 +4,16 @@
# Contact: qubitium@modelcloud.ai, x.com/qubitium

from ..base import BaseQModel
from ..moe_lifecycle import W1W3W2MoELifecycleHooks
from ..moe_lifecycle import GateUpDownMoELifecycleHooks


class MixtralQModel(BaseQModel):
pre_lm_head_norm_module = "model.norm"

# MoE lifecycle hooks for w1/w3/w2 pattern
moe_lifecycle_hooks = W1W3W2MoELifecycleHooks()
dynamic_expert_index = "num_local_experts"

# MoE lifecycle hooks for gate_proj/up_proj/down_proj pattern
moe_lifecycle_hooks = GateUpDownMoELifecycleHooks()

module_tree = [
"model",
Expand All @@ -21,9 +23,9 @@ class MixtralQModel(BaseQModel):
"input_layernorm": ("input_layernorm:!",),
"self_attn": ("q_proj:0", "k_proj:0", "v_proj:0", "o_proj:1"),
"post_attention_layernorm": ("post_attention_layernorm:!",),
"block_sparse_moe:moe": {
"mlp:moe": {
"experts": {
"#": ("w1:0", "w3:0", "w2:1"),
"#": ("gate_proj:0", "up_proj:0", "down_proj:1"),
}
}
}
Expand Down
2 changes: 1 addition & 1 deletion tests/models/test_mixtral.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12,7 +12,6 @@ class TestMixtral(ModelTest):
NATIVE_MODEL_ID = "/monster/data/model/Mixtral-8x7B-Instruct-v0.1" # "mistralai/Mixtral-8x7B-Instruct-v0.1"
NATIVE_ARC_CHALLENGE_ACC = 0.5213
NATIVE_ARC_CHALLENGE_ACC_NORM = 0.5247
TRUST_REMOTE_CODE = True
EVAL_BATCH_SIZE = 6
EVAL_TASKS = {
EVAL.LM_EVAL.ARC_CHALLENGE: {
Expand All @@ -21,6 +20,7 @@ class TestMixtral(ModelTest):
"acc_norm": {"value": NATIVE_ARC_CHALLENGE_ACC_NORM},
},
}
OFFLOAD_TO_DISK = False # FIXME Currently, after defuser converted the model, OFFLOAD_TO_DISK must be False for quantization.

def test_mixtral(self):
self.quant_lm_eval()
Loading