admin/LLM-from-scratch
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

update code

Browse Source
This commit is contained in:
coffee
2025-05-06 18:07:32 +08:00
parent 94ffafdbc0
commit 400e253afe
1 changed files with 2 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files
LLM_code/test_huggingface_transformer.py
+2 -3
View File
@@ -1,7 +1,7 @@
import transformers import transformers
from transformers import AutoModelForCausalLM, AutoTokenizer from transformers import AutoModelForCausalLM, AutoTokenizer
from transformers import LlamaForCausalLM from transformers import LlamaForCausalLM
tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2-0.5B-Instruct") # tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2-0.5B-Instruct")
from transformers import LlamaConfig from transformers import LlamaConfig
config = LlamaConfig( config = LlamaConfig(
vocab_size=32000, vocab_size=32000,
@@ -12,7 +12,6 @@ config = LlamaConfig(
) )
model = LlamaForCausalLM(config) model = LlamaForCausalLM(config)
# model = transformers.Qwen2ForCausalLM(config)
model = transformers.Qwen2ForCausalLM(config)
model_size = sum(t.numel() for t in model.parameters()) model_size = sum(t.numel() for t in model.parameters())
print(f"Model Size: {model_size/1000**2:.1f}M parameters") print(f"Model Size: {model_size/1000**2:.1f}M parameters")