Update README.md
Browse files
README.md
CHANGED
@@ -70,7 +70,7 @@ tokenizer = AutoTokenizer.from_pretrained("llmware/bling-1.4b-0.1")
|
|
70 |
model = AutoModelForCausalLM.from_pretrained("llmware/bling-1.4b-0.1")
|
71 |
|
72 |
|
73 |
-
The BLING model was fine-tuned with a simple "\<human
|
74 |
|
75 |
full_prompt = "\<human>\: " + my_prompt + "\n" + "\<bot>\: "
|
76 |
|
|
|
70 |
model = AutoModelForCausalLM.from_pretrained("llmware/bling-1.4b-0.1")
|
71 |
|
72 |
|
73 |
+
The BLING model was fine-tuned with a simple "\<human> and \<bot> wrapper", so to get the best results, wrap inference entries as:
|
74 |
|
75 |
full_prompt = "\<human>\: " + my_prompt + "\n" + "\<bot>\: "
|
76 |
|