neuralmagic
/

TinyLlama-1.1B-Chat-v0.4-pruned50-quant-ds

Text Generation

text-generation-inference

Model card Files Files and versions Community

mwitiderrick commited on Dec 5, 2023

Commit

d1bb00e

•

1 Parent(s): 133c04d

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -27,7 +27,7 @@ from deepsparse import TextGeneration
 prompt = "How to make banana bread?"
 formatted_prompt =  f"<|im_start|>user\n{prompt}<|im_end|>\n<|im_start|>assistant\n"
-model = TextGeneration(model="hf:neuralmagic/TinyLlama-1.1B-Chat-v0.4-pruned50-quant")
 print(model(formatted_prompt, max_new_tokens=500).generations[0].text)
 """

 prompt = "How to make banana bread?"
 formatted_prompt =  f"<|im_start|>user\n{prompt}<|im_end|>\n<|im_start|>assistant\n"
+model = TextGeneration(model="hf:neuralmagic/TinyLlama-1.1B-Chat-v0.4-pruned50-quant-ds")
 print(model(formatted_prompt, max_new_tokens=500).generations[0].text)
 """