Update README.md
Browse files
README.md
CHANGED
|
@@ -86,6 +86,8 @@ The fastest way to get started with BLING is through direct import in transforme
|
|
| 86 |
tokenizer = AutoTokenizer.from_pretrained("llmware/bling-1.4b-0.1")
|
| 87 |
model = AutoModelForCausalLM.from_pretrained("llmware/bling-1.4b-0.1")
|
| 88 |
|
|
|
|
|
|
|
| 89 |
|
| 90 |
The BLING model was fine-tuned with a simple "\<human> and \<bot> wrapper", so to get the best results, wrap inference entries as:
|
| 91 |
|
|
|
|
| 86 |
tokenizer = AutoTokenizer.from_pretrained("llmware/bling-1.4b-0.1")
|
| 87 |
model = AutoModelForCausalLM.from_pretrained("llmware/bling-1.4b-0.1")
|
| 88 |
|
| 89 |
+
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.
|
| 90 |
+
|
| 91 |
|
| 92 |
The BLING model was fine-tuned with a simple "\<human> and \<bot> wrapper", so to get the best results, wrap inference entries as:
|
| 93 |
|