Update README.md
Browse files
README.md
CHANGED
@@ -59,8 +59,8 @@ Any model can provide inaccurate or incomplete information, and should be used i
|
|
59 |
The fastest way to get started with BLING is through direct import in transformers:
|
60 |
|
61 |
from transformers import AutoTokenizer, AutoModelForCausalLM
|
62 |
-
tokenizer = AutoTokenizer.from_pretrained("bling-tiny-llama-v0"
|
63 |
-
model = AutoModelForCausalLM.from_pretrained("bling-tiny-llama-v0"
|
64 |
|
65 |
Please refer to the generation_test .py files in the Files repository, which includes 200 samples and script to test the model. The **generation_test_llmware_script.py** includes built-in llmware capabilities for fact-checking, as well as easy integration with document parsing and actual retrieval to swap out the test set for RAG workflow consisting of business documents.
|
66 |
|
|
|
59 |
The fastest way to get started with BLING is through direct import in transformers:
|
60 |
|
61 |
from transformers import AutoTokenizer, AutoModelForCausalLM
|
62 |
+
tokenizer = AutoTokenizer.from_pretrained("bling-tiny-llama-v0")
|
63 |
+
model = AutoModelForCausalLM.from_pretrained("bling-tiny-llama-v0")
|
64 |
|
65 |
Please refer to the generation_test .py files in the Files repository, which includes 200 samples and script to test the model. The **generation_test_llmware_script.py** includes built-in llmware capabilities for fact-checking, as well as easy integration with document parsing and actual retrieval to swap out the test set for RAG workflow consisting of business documents.
|
66 |
|