mirror of
https://github.com/hpcaitech/ColossalAI.git
synced 2025-09-05 11:02:05 +00:00
[Inference]Adapt temperature processing logic (#5689)
* Adapt temperature processing logic * add ValueError for top_p and top_k * add GQA Test * fix except_msg
This commit is contained in:
@@ -28,7 +28,12 @@ def check_inference_engine(use_engine=False, prompt_template=None, do_sample=Tru
|
||||
tokenizer = AutoTokenizer.from_pretrained("hf-internal-testing/llama-tokenizer")
|
||||
model = LlamaForCausalLM(
|
||||
LlamaConfig(
|
||||
vocab_size=50000, hidden_size=512, intermediate_size=1536, num_attention_heads=4, num_hidden_layers=16
|
||||
vocab_size=50000,
|
||||
hidden_size=512,
|
||||
intermediate_size=1536,
|
||||
num_attention_heads=4,
|
||||
num_key_value_heads=2,
|
||||
num_hidden_layers=16,
|
||||
)
|
||||
).cuda()
|
||||
model = model.eval()
|
||||
|
Reference in New Issue
Block a user