model_type error llava

[sunjiating]

pulsar2 llm_build 命令不支持支持的模型类型 llava

root@docker-desktop:/data/model# pulsar2 llm_build --input_path ppxin321/HolmesVAD-7B/ --output_path ppxin321/HolmesVAD-7B-w8a16/ --chip AX650
:110: FutureWarning: Decorating classes is deprecated and will be disabled in future versions. You should only decorate functions or methods. To preserve the current behavior of class decoration, you can directly decorate the __init__ method and nothing else.
Config(
model_name='ppxin321/HolmesVAD-7B',
model_type='llava',
num_hidden_layers=32,
num_attention_heads=32,
num_key_value_heads=32,
hidden_size=4096,
head_dim=0,
intermediate_size=11008,
vocab_size=32000,
rope_theta=10000.0,
max_position_embeddings=4096,
rope_partial_factor=1.0,
rms_norm_eps=1e-05,
norm_type='rms_norm',
hidden_act='silu',
hidden_act_param=0.03,
scale_depth=1.4,
scale_emb=1,
dim_model_base=256,
origin_model_type=''
)
Traceback (most recent call last):
File "", line 59, in guard_context
File "", line 121, in llm_build
AssertionError: model_type error llava

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "</opt/pulsar2/yamain/main.py>", line 4, in
File "", line 329, in
File "", line 257, in pulsar2
File "", line 121, in llm_build
File "/usr/local/lib/python3.9/contextlib.py", line 137, in exit
self.gen.throw(typ, value, traceback)
File "", line 61, in guard_context
File "", line 73, in error_func
yamain.common.error.CodeException: (<LLMErrorCode.LLM_PREPARE: 0>, AssertionError('model_type error llava'))