Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
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
142 changes: 142 additions & 0 deletions onnx_diagnostic/torch_models/hghub/hub_data_cached_configs.py
Original file line number Diff line number Diff line change
Expand Up @@ -4687,3 +4687,145 @@ def _ccached_zai_glm_45():
},
}
)


def _ccached_microsoft_phi3_mini_128k_instruct():
"microsoft/Phi-3-mini-128k-instruct"
return transformers.Phi3Config(
**{
"_name_or_path": "Phi-3-mini-128k-instruct",
"architectures": ["Phi3ForCausalLM"],
"attention_dropout": 0.0,
"auto_map": {
"AutoConfig": "configuration_phi3.Phi3Config",
"AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM",
},
"bos_token_id": 1,
"embd_pdrop": 0.0,
"eos_token_id": 32000,
"hidden_act": "silu",
"hidden_size": 3072,
"initializer_range": 0.02,
"intermediate_size": 8192,
"max_position_embeddings": 131072,
"model_type": "phi3",
"num_attention_heads": 32,
"num_hidden_layers": 32,
"num_key_value_heads": 32,
"original_max_position_embeddings": 4096,
"pad_token_id": 32000,
"resid_pdrop": 0.0,
"rms_norm_eps": 1e-05,
"rope_scaling": {
"long_factor": [
1.0700000524520874,
1.1200000047683716,
1.149999976158142,
1.4199999570846558,
1.5699999332427979,
1.7999999523162842,
2.129999876022339,
2.129999876022339,
3.009999990463257,
5.910000324249268,
6.950000286102295,
9.070000648498535,
9.930000305175781,
10.710000038146973,
11.130000114440918,
14.609999656677246,
15.409998893737793,
19.809999465942383,
37.279998779296875,
38.279998779296875,
38.599998474121094,
40.12000274658203,
46.20000457763672,
50.940006256103516,
53.66000747680664,
54.9373893737793,
56.89738845825195,
57.28738784790039,
59.98738479614258,
60.86738586425781,
60.887386322021484,
61.71739196777344,
62.91739273071289,
62.957393646240234,
63.41739273071289,
63.8173942565918,
63.83739471435547,
63.897396087646484,
63.93739700317383,
64.06739807128906,
64.11434936523438,
64.12435150146484,
64.15435028076172,
64.19435119628906,
64.24435424804688,
64.57435607910156,
64.69000244140625,
64.76000213623047,
],
"short_factor": [
1.1,
1.1,
1.1,
1.3000000000000003,
1.3500000000000003,
1.3500000000000003,
1.4000000000000004,
1.5500000000000005,
2.000000000000001,
2.000000000000001,
2.000000000000001,
2.000000000000001,
2.000000000000001,
2.000000000000001,
2.000000000000001,
2.000000000000001,
2.000000000000001,
2.000000000000001,
2.000000000000001,
2.000000000000001,
2.000000000000001,
2.000000000000001,
2.000000000000001,
2.000000000000001,
2.000000000000001,
2.0500000000000007,
2.0500000000000007,
2.0500000000000007,
2.0500000000000007,
2.0500000000000007,
2.0500000000000007,
2.1000000000000005,
2.1000000000000005,
2.1500000000000004,
2.25,
2.25,
2.25,
2.25,
2.25,
2.3999999999999995,
2.4499999999999993,
2.499999999999999,
2.6999999999999984,
2.6999999999999984,
2.7499999999999982,
2.799999999999998,
2.8999999999999977,
3.049999999999997,
],
"type": "longrope",
},
"rope_theta": 10000.0,
"sliding_window": 262144,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.40.2",
"use_cache": true,
"attention_bias": false,
"vocab_size": 32064,
}
)
34 changes: 34 additions & 0 deletions onnx_diagnostic/torch_models/validate.py
Original file line number Diff line number Diff line change
Expand Up @@ -712,6 +712,7 @@ def validate_model(
print(f"[validate_model] done (dump onnx) in {duration}")
data["onnx_filename"] = onnx_filename
summary["time_onnx_save"] = duration
summary.update(compute_statistics(onnx_filename))
if verbose:
print(f"[validate_model] dumps statistics in {dump_folder!r}...")
dump_stats = os.path.join(dump_folder, f"{folder_name}.stats")
Expand Down Expand Up @@ -815,6 +816,39 @@ def validate_model(
return summary, data


def compute_statistics(onnx_filename: str) -> Dict[str, Union[float, int]]:
"""Computes some statistics on the model itself."""
onx = onnx.load(onnx_filename, load_external_data=False)

def node_iter(proto):
if isinstance(proto, onnx.ModelProto):
yield from node_iter(proto.graph)
for f in proto.functions:
yield from node_iter(f)
elif isinstance(proto, (onnx.FunctionProto, onnx.GraphProto)):
for node in proto.node:
yield node
for att in node.attribute:
if att.type == onnx.AttributeProto.GRAPH:
yield from node_iter(att.g)
if hasattr(proto, "initializer"):
yield from proto.initializer
else:
raise NotImplementedError(f"Unexpected type={type(proto)}")

counts: Dict[str, Union[float, int]] = {}
for proto in node_iter(onx):
if isinstance(proto, onnx.NodeProto):
key = f"n_node_{proto.op_type}"
else:
key = f"n_node_initializer_{proto.data_type}"

if key not in counts:
counts[key] = 0
counts[key] += 1
return counts


def _validate_do_run_model(
data, summary, key, tag, expected_tag, verbose, repeat, warmup, quiet
):
Expand Down
Loading