Update README.md

README.md

@@ -16,9 +16,9 @@ library_name: transformers
 ---
 # Qwen2.5-7B-VNTL-JP-EN
 
-Qwen2.5-7B finetuned on Japanese to English translations.
+Qwen2.5-7B finetuned for Japanese to English translation.
 
-Trained on 150k Japanese to English translations from [VNTL-v3.1-1k](https://huggingface.co/datasets/lmg-anon/VNTL-v3.1-1k).
+Trained on ~150k sentences from [VNTL-v3.1-1k](https://huggingface.co/datasets/lmg-anon/VNTL-v3.1-1k).
 
 The model was trained on just the sentences in random order to make it more flexible and useful outside of just VN translation.
 
@@ -26,7 +26,8 @@ The model was trained on just the sentences in random order to make it more flex
 
 ### Ollama
 
-`ollama run technobyte/Qwen2.5-7B-VNTL-JP-EN:q4_k_m`
+1. `ollama run technobyte/Qwen2.5-7B-VNTL-JP-EN:q4_k_m`
+2. Input just the Japanese sentence.
 
 ### Llama.cpp
 
@@ -34,7 +35,8 @@ The model was trained on just the sentences in random order to make it more flex
 2. `llama-cli -m Qwen2.5-7B-VNTL-JP-EN-Q4_K_M.gguf -no-cnv -p "A Japanese sentence along with a proper English equivalent.\nJapanese: 放課後はマンガ喫茶でまったり〜♡ おすすめのマンガ教えて！ \nEnglish: "`
 
 ### Transformers
-```
+
+```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
 model_name = "TechnoByte/Qwen2.5-7B-VNTL-JP-EN"
@@ -79,7 +81,7 @@ English:
 
 ### Jinja (HF Transformers)
 
-```
+```jinja
 {% for i in range(0, messages|length, 2) %}A Japanese sentence along with a proper English equivalent.
 Japanese: {{ messages[i].content }}
 English:{% if i+1 < messages|length %} {{ messages[i+1].content }}<|endoftext|>{{ "