Update README.md

README.md

@@ -9,17 +9,16 @@ pipeline_tag: translation
 
 This is a merge of lora trained on English to Hinglish translation dataset by NATERAW on llama2-7b and OPENHATHI-7B-BASE. Since openHathi has more hindi data in it's pretraining compared to llama2 the translation is significantly better.
 
-
+## Prompting
 You can use the prompt template provided by nateraw
 "Translate from english to hinglish:\n{{en}}\n---\nTranslation:\n"
 
 
-Sample code:
-
+**Sample code**:
+```
 from transformers import LlamaForCausalLM, AutoTokenizer
 import torch
 
-
 device = "cuda:0"
 tokenizer = AutoTokenizer.from_pretrained('akashgoel-id/OpenHathi-7B-English-to-Hinglish')
 model = LlamaForCausalLM.from_pretrained('akashgoel-id/OpenHathi-7B-English-to-Hinglish', torch_dtype=torch.bfloat16).to(device)
@@ -34,10 +33,12 @@ while True:
     generate_ids = model.generate(inputs.input_ids, max_length=500)
     print(tokenizer.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0])
 
+```
+
 
 
 
-Limitations:
+## Limitations
 The model is still not that good when it comes to idioms
 
 1) Input : When it rains, it pours
@@ -71,6 +72,6 @@ The model is still not that good when it comes to idioms
    Evaluation : This is a literal translation and doesn't quite capture the idiomatic meaning of avoiding the main point or not speaking directly about a subject. The phrase "Ghumaphira ke baat karna" would be more appropriate.
 
 
-Next steps:
+## Next steps
 1) The model seems to be highly censored given it used llama2. Next step would be to remove some of censorship by finetuning on more uncensored data. (What WizardLM has done for llama2)
 2) Finetune on idioms