Hugging Face's logo

RedHatAI
/
MiniChat-3B-pruned50-quant-ds

Text Generation
Transformers
ONNX
llama
deepsparse
Model card Files
xet
Community
mwitiderrick commited on
Commit
507bf37
·
1 Parent(s): 2ee5da2

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -10,7 +10,7 @@ from deepsparse import TextGeneration
10
  prompt = "How to get in a good university?"
11
  formatted_prompt = f"<s> [|User|]\n{prompt}</s>[|Assistant|]\n"
12
 
13
- model = TextGeneration(model="deployment")
14
 
15
  print(model(formatted_prompt, max_new_tokens=500).generations[0].text)
16
  """
@@ -29,7 +29,7 @@ from deepsparse import TextGeneration
29
  prompt = "How to become a great software engineer?"
30
  formatted_prompt = f"<s> [|User|]\n{prompt}</s>[|Assistant|]\n"
31
 
32
- model = TextGeneration(model="deployment")
33
 
34
  print(model(formatted_prompt, max_new_tokens=500).generations[0].text)
35
  """
 
10
  prompt = "How to get in a good university?"
11
  formatted_prompt = f"<s> [|User|]\n{prompt}</s>[|Assistant|]\n"
12
 
13
+ model = TextGeneration(model="hf:nm-testing/MiniChat-3B-pruned-quant-50")
14
 
15
  print(model(formatted_prompt, max_new_tokens=500).generations[0].text)
16
  """
 
29
  prompt = "How to become a great software engineer?"
30
  formatted_prompt = f"<s> [|User|]\n{prompt}</s>[|Assistant|]\n"
31
 
32
+ model = TextGeneration(model="hf:nm-testing/MiniChat-3B-pruned-quant-50")
33
 
34
  print(model(formatted_prompt, max_new_tokens=500).generations[0].text)
35
  """