MaziyarPanahi commited on
Commit
1964dbb
1 Parent(s): 6e5b3ca

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +30 -0
README.md CHANGED
@@ -108,6 +108,36 @@ This model is a fine-tuned version of [google/gemma-7b](https://huggingface.co/g
108
  It achieves the following results on the evaluation set:
109
  - Loss: 1.4456
110
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
111
  ## Model description
112
 
113
  More information needed
 
108
  It achieves the following results on the evaluation set:
109
  - Loss: 1.4456
110
 
111
+ ## How to use
112
+
113
+ **PEFT**
114
+ ```python
115
+ from peft import PeftModel, PeftConfig
116
+ from transformers import AutoModelForCausalLM
117
+
118
+ model_id = "MaziyarPanahi/gemma-7b-Open-Hermes-v0.1"
119
+
120
+ config = PeftConfig.from_pretrained(model_id)
121
+ model = AutoModelForCausalLM.from_pretrained("google/gemma-7b")
122
+ model = PeftModel.from_pretrained(model, model_id)
123
+ ```
124
+
125
+ **Transformers**
126
+ ```python
127
+ # Use a pipeline as a high-level helper
128
+ from transformers import pipeline
129
+
130
+ model_id = "MaziyarPanahi/gemma-7b-Open-Hermes-v0.1"
131
+
132
+ pipe = pipeline("text-generation", model=model_id)
133
+
134
+ # Load model directly
135
+ from transformers import AutoTokenizer, AutoModelForCausalLM
136
+
137
+ tokenizer = AutoTokenizer.from_pretrained(model_id)
138
+ model = AutoModelForCausalLM.from_pretrained(model_id)
139
+ ```
140
+
141
  ## Model description
142
 
143
  More information needed