Update README.md

README.md

@@ -18,6 +18,16 @@ tags:
 - **License:** apache-2.0
 - **Finetuned from model :** cognitivecomputations/dolphin-2.9.3-llama-3-8b
 
-This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
+```
+from transformers import AutoTokenizer, LlamaForCausalLM
 
-[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
+model = LlamaForCausalLM.from_pretrained("AashishKumar/Cn_2_9_3_Hinglish_llama3_7b_8k")
+tokenizer = AutoTokenizer.from_pretrained("AashishKumar/Cn_2_9_3_Hinglish_llama3_7b_8k")
+
+prompt = "ky tumhe la la land pasand hai?"
+inputs = tokenizer(prompt, return_tensors="pt")
+
+# Generate
+generate_ids = model.generate(inputs.input_ids, max_length=30)
+tokenizer.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]
+```