Update README.md

README.md

@@ -3,16 +3,17 @@ license: apache-2.0
 inference: false  
 ---
 
-# Model Card for Model ID
+# BLING-PHI-2-GGUF
 
 <!-- Provide a quick summary of what the model is/does. -->
 
-bling-phi-2-v0 is part of the BLING ("Best Little Instruct No GPU Required ...") model series, RAG-instruct trained on top of a Microsoft Phi-2B base model.
+**bling-phi-2-gguf** is part of the BLING model series, RAG-instruct trained on top of a Microsoft Phi-2B base model.  
 
-BLING models are fine-tuned with high-quality custom instruct datasets, designed for rapid prototyping in RAG scenarios.
+BLING models are fine-tuned with high-quality custom instruct datasets, designed for rapid prototyping in RAG scenarios.  
 
-For models with comparable size and performance in RAG deployments, please see:  
+For other similar models with comparable size and performance in RAG deployments, please see:  
 
+[**bling-phi-3-gguf**](https://huggingface.co/llmware/bling-phi-3-gguf)  
 [**bling-stable-lm-3b-4e1t-v0**](https://huggingface.co/llmware/bling-stable-lm-3b-4e1t-v0)  
 [**bling-sheared-llama-2.7b-0.1**](https://huggingface.co/llmware/bling-sheared-llama-2.7b-0.1)  
 [**bling-red-pajamas-3b-0.1**](https://huggingface.co/llmware/bling-red-pajamas-3b-0.1)  
@@ -64,24 +65,24 @@ BLING models have been trained for common RAG scenarios, specifically:   questio
 without the need for a lot of complex instruction verbiage - provide a text passage context, ask questions, and get clear fact-based responses.
 
 
-## Bias, Risks, and Limitations
-
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+## How to Get Started with the Model
 
-Any model can provide inaccurate or incomplete information, and should be used in conjunction with appropriate safeguards and fact-checking mechanisms.
+To pull the model via API:  
 
+    from huggingface_hub import snapshot_download           
+    snapshot_download("llmware/dragon-yi-answer-tool", local_dir="/path/on/your/machine/", local_dir_use_symlinks=False)  
+    
 
-## How to Get Started with the Model
+Load in your favorite GGUF inference engine, or try with llmware as follows:
 
-The fastest way to get started with BLING is through direct import in transformers:
+    from llmware.models import ModelCatalog  
+    model = ModelCatalog().load_model("bling-phi-2-gguf")            
+    response = model.inference(query, add_context=text_sample)  
 
-    from transformers import AutoTokenizer, AutoModelForCausalLM  
-    tokenizer = AutoTokenizer.from_pretrained("bling-phi-2-v0", trust_remote_code=True)  
-    model = AutoModelForCausalLM.from_pretrained("bling-phi-2-v0", trust_remote_code=True)  
+Note: please review [**config.json**](https://huggingface.co/llmware/bling-phi-2-gguf/blob/main/config.json) in the repository for prompt wrapping information, details on the model, and full test set.  
 
-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:
+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>:"
 
@@ -95,29 +96,6 @@ To get the best results, package "my_prompt" as follows:
     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)  
-
-
 ## Model Card Contact
 
 Darren Oberst & llmware team