Update README.md

README.md

@@ -1,20 +1,31 @@
 ---
-license: apache-2.0
 language:
-- vi
 - en
-base_model:
-- Qwen/Qwen2.5-Coder-1.5B-Instruct
+license: apache-2.0
+library_name: transformers
+pipeline_tag: text-generation
+tags:
+- llama
+- causal-lm
+- 270m
+- research
 ---
 
 # HOS-OSS-270M
 
 Custom 270M parameter LLaMA-style model.
 
-- 28 layers
-- 1280 hidden size
-- 20 attention heads
-- 32k vocab
-- Random initialized (research purpose)
+## Model Details
+
+- Architecture: LLaMA-style Transformer
+- Parameters: 270M
+- Vocabulary: 32k
+- Context length: 1024
+
+## Hosted / Supported by
+
+This model is hosted on Hugging Face Hub and maintained by **hydffgg**.
+
+## Disclaimer
 
-⚠ This model is randomly initialized and not pretrained.
+This model is randomly initialized and intended for research purposes only.