saheedniyi
/

Llama3-8b-Naija_v1

Text Generation

text-generation-inference

Inference Endpoints

4-bit precision

Model card Files Files and versions Community

saheedniyi commited on Jun 1

Commit

8282088

•

1 Parent(s): 39b30c9

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -43,7 +43,7 @@ from transformers import AutoModelForCausalLM, AutoTokenizer
 tokenizer = AutoTokenizer.from_pretrained("saheedniyi/Llama3-8b-Naija_v1")
 model = AutoModelForCausalLM.from_pretrained("saheedniyi/Llama3-8b-Naija_v1")
-input_text = "What are the top locations for tourism in Nigeria?"
 formatted_prompt=input_text=f"### BEGIN CONVERSATION ###\n\n## User: ##\n{input_text}\n\n## Assistant: ##\n"
 inputs = tokenizer(input_text, return_tensors="pt")
 outputs = model.generate(**inputs.to("cuda"), max_new_tokens=512,pad_token_id=tokenizer.pad_token_id,do_sample=True,temperature=0.6,top_p=0.9,)

 tokenizer = AutoTokenizer.from_pretrained("saheedniyi/Llama3-8b-Naija_v1")
 model = AutoModelForCausalLM.from_pretrained("saheedniyi/Llama3-8b-Naija_v1")
+input_text = "What are the top places for tourism in Nigeria?"
 formatted_prompt=input_text=f"### BEGIN CONVERSATION ###\n\n## User: ##\n{input_text}\n\n## Assistant: ##\n"
 inputs = tokenizer(input_text, return_tensors="pt")
 outputs = model.generate(**inputs.to("cuda"), max_new_tokens=512,pad_token_id=tokenizer.pad_token_id,do_sample=True,temperature=0.6,top_p=0.9,)