Update README.md
Browse files
README.md
CHANGED
@@ -75,6 +75,8 @@ The fastest way to get started with dRAGon is through direct import in transform
|
|
75 |
tokenizer = AutoTokenizer.from_pretrained("dragon-stablelm-7b-v0")
|
76 |
model = AutoModelForCausalLM.from_pretrained("dragon-stablelm-7b-v0")
|
77 |
|
|
|
|
|
78 |
The BLING model was fine-tuned with a simple "\<human> and \<bot> wrapper", so to get the best results, wrap inference entries as:
|
79 |
|
80 |
full_prompt = "\<human>\: " + my_prompt + "\n" + "\<bot>\:"
|
@@ -115,5 +117,3 @@ If you are using a HuggingFace generation script:
|
|
115 |
## Model Card Contact
|
116 |
|
117 |
Darren Oberst & llmware team
|
118 |
-
|
119 |
-
Please reach out anytime if you are interested in this project!
|
|
|
75 |
tokenizer = AutoTokenizer.from_pretrained("dragon-stablelm-7b-v0")
|
76 |
model = AutoModelForCausalLM.from_pretrained("dragon-stablelm-7b-v0")
|
77 |
|
78 |
+
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.
|
79 |
+
|
80 |
The BLING model was fine-tuned with a simple "\<human> and \<bot> wrapper", so to get the best results, wrap inference entries as:
|
81 |
|
82 |
full_prompt = "\<human>\: " + my_prompt + "\n" + "\<bot>\:"
|
|
|
117 |
## Model Card Contact
|
118 |
|
119 |
Darren Oberst & llmware team
|
|
|
|