NexaAIDev
/

Octopus-v2

Text Generation

function calling

on-device language model

text-generation-inference

Model card Files Files and versions Community

Zack Li commited on Apr 5

Commit

1f09c6d

•

1 Parent(s): 7f2687d

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -64,7 +64,7 @@ def inference(input_text):
     end_time = time.time()
     return {"output": res, "latency": end_time - start_time}
-model_id = "NexaAIDev/android_API_10k_data"
 tokenizer = AutoTokenizer.from_pretrained(model_id)
 model = GemmaForCausalLM.from_pretrained(
     model_id, torch_dtype=torch.bfloat16, device_map="auto"

     end_time = time.time()
     return {"output": res, "latency": end_time - start_time}
+model_id = "NexaAIDev/Octopus-v2"
 tokenizer = AutoTokenizer.from_pretrained(model_id)
 model = GemmaForCausalLM.from_pretrained(
     model_id, torch_dtype=torch.bfloat16, device_map="auto"