Update README.md

README.md

@@ -77,14 +77,13 @@ Any model can provide inaccurate or incomplete information, and should be used i
 
 The fastest way to get started with BLING is through direct import in transformers:
 
-from transformers import AutoTokenizer, AutoModelForCausalLM  
-tokenizer = AutoTokenizer.from_pretrained("llmware/bling-sheared-llama-2.7b-0.1")  
-model = AutoModelForCausalLM.from_pretrained("llmware/bling-sheared-llama-2.7b-0.1")  
-
+   from transformers import AutoTokenizer, AutoModelForCausalLM  
+   tokenizer = AutoTokenizer.from_pretrained("llmware/bling-sheared-llama-2.7b-0.1")  
+   model = AutoModelForCausalLM.from_pretrained("llmware/bling-sheared-llama-2.7b-0.1")  
 
 The BLING 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>\:"
+   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:
 
@@ -93,7 +92,35 @@ The BLING model was fine-tuned with closed-context samples, which assume general
 
 To get the best results, package "my_prompt" as follows:
 
-my_prompt = {{text_passage}} + "\n" + {{question/instruction}}
+    my_prompt = {{text_passage}} + "\n" + {{question/instruction}}
+
+If you are using a HuggingFace generation script:
+
+    # prepare prompt packaging used in fine-tuning process
+    new_prompt = "<human>: " + entries["context"] + "\n" + entries["query"] + "\n" + "<bot>:"
+
+    inputs = tokenizer(new_prompt, return_tensors="pt")  
+    start_of_output = len(inputs.input_ids[0])
+
+    #   temperature: set at 0.3 for consistency of output
+    #   max_new_tokens:  set at 100 - may prematurely stop a few of the summaries
+
+    outputs = model.generate(
+            inputs.input_ids.to(device),
+            eos_token_id=tokenizer.eos_token_id,
+            pad_token_id=tokenizer.eos_token_id,
+            do_sample=True,
+            temperature=0.3,
+            max_new_tokens=100,
+            )
+
+    output_only = tokenizer.decode(outputs[0][start_of_output:],skip_special_tokens=True)  
+
+    #   note: due to artifact of the fine-tuning, use this post-processing with HF generation 
+
+    eot = output_only.find("<|endoftext|>")
+    if eot > -1:
+        output_only = output_only[:eot]
 
 
 ## Citation [optional]
@@ -110,7 +137,3 @@ This BLING model was built on top of a Sheared Llama model base - for more infor
 
 Darren Oberst & llmware team
 
-Please reach out anytime if you are interested in this project and would like to participate and work with us!
-
-
-