llmware
/

dragon-yi-6b-v0

Text Generation

Inference Endpoints

Model card Files Files and versions Community

doberst commited on Nov 12, 2023

Commit

c8319d6

•

1 Parent(s): c2902b7

Update README.md

Files changed (1) hide show

README.md +2 -1

README.md CHANGED Viewed

@@ -82,10 +82,11 @@ The fastest way to get started with BLING is through direct import in transforme
     tokenizer = AutoTokenizer.from_pretrained("dragon-yi-6b-0.1")
     model = AutoModelForCausalLM.from_pretrained("dragon-yi-6b-0.1")
 The DRAGON model was fine-tuned with a simple "\<human> and \<bot> wrapper", so to get the best results, wrap inference entries as:
-    full_prompt = "\<human>\: " + my_prompt + "\n" + "\<bot>\:"
 The BLING model was fine-tuned with closed-context samples, which assume generally that the prompt consists of two sub-parts:

     tokenizer = AutoTokenizer.from_pretrained("dragon-yi-6b-0.1")
     model = AutoModelForCausalLM.from_pretrained("dragon-yi-6b-0.1")
+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.
 The DRAGON model was fine-tuned with a simple "\<human> and \<bot> wrapper", so to get the best results, wrap inference entries as:
+    full_prompt = "<human>: " + my_prompt + "\n" + "<bot>:"
 The BLING model was fine-tuned with closed-context samples, which assume generally that the prompt consists of two sub-parts: