Upload README.md

README.md

@@ -8,22 +8,19 @@ license: apache-2.0
 
 BLING-1.4b-0.1 is the first model release in the BLING ("Best Little Instruction-following No-GPU-required") model series.
 
-BLING models are designed as custom instruct-following laptop-effective GPT decoder-based models (~1B-2.7B parameters). BLING models are currently built on top of Pythia (GPTNeox architecture) base models and other Apache 2.0-licensed GPT-compatible models with primary focus on 'little' models in the range of 1B, 1.3-1.4B, and 2.7B parameters. (Note: in our testing, we have seen relatively limited success with instruct-following models below <1B parameters.)
-
-BLING models are fine-tuned with distilled high-quality custom instruct datasets, targeted at a specific subset of instruct tasks with the objective of providing a high-quality Instruct model that can be run entirely without a GPU server, with good quality instruct-following capability that can be loaded and run locally on a laptop.
-
-## Model Details
+BLING models are fine-tuned with distilled high-quality custom instruct datasets, targeted at a specific subset of instruct tasks with 
+the objective of providing a high-quality Instruct model that is 'inference-ready' on a CPU laptop even 
+without using any advanced quantization optimizations.
 
 ### Model Description
 
 <!-- Provide a longer summary of what this model is. -->
 
 - **Developed by:** llmware
-- **Shared by [optional]:** Darren Oberst
 - **Model type:** GPTNeoX instruct-trained decoder
 - **Language(s) (NLP):** English
 - **License:** Apache 2.0
-- **Finetuned from model [optional]:** EleutherAI/Pythia-1b-deduped
+- **Finetuned from model [optional]:** EleutherAI/Pythia-1.4b-v0
 
 ## Uses
 
@@ -31,10 +28,11 @@ BLING models are fine-tuned with distilled high-quality custom instruct datasets
 
 The intended use of BLING models is two-fold:
 
-1.  Provide a high-quality Instruct models that can run on a laptop for local testing.  We have found it extremely useful when building a
+1.  Provide high-quality Instruct models that can run on a laptop for local testing.  We have found it extremely useful when building a
    proof-of-concept, or working with sensitive enterprise data that must be closely guarded, especially in RAG use cases.
 
-2.  Push the state of the art for smaller Instruct-following models in the 1B - 7B range through improved fine-tuning datasets and targeted "instruction" tasks.
+2.  Push the state of the art for smaller Instruct-following models in the sub-7B parameter range, especially 1B-3B, as single-purpose
+    automation tools for specific tasks through targeted fine-tuning datasets and focused "instruction" tasks.
 
 
 ### Direct Use
@@ -42,23 +40,14 @@ The intended use of BLING models is two-fold:
 <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
 
 BLING is designed for enterprise automation use cases, especially in knowledge-intensive industries, such as financial services,
-legal and regulatory industries.   BLING is intended to be an experimental series of little instruct models targeted as specific
-RAG automation tasks with complex information sources.   Rather than try to be "all things to all people," BLING models try to focus
-on a narrower set of Instructions more suitable to a ~1B parameter GPT model.
+legal and regulatory industries with complex information sources.  Rather than try to be "all things to all people," BLING models try to focus on a narrower set of Instructions more suitable to a ~1B parameter GPT model.
 
 BLING is ideal for rapid prototyping, testing, and the ability to perform an end-to-end workflow locally on a laptop without
 having to send sensitive information over an Internet-based API.
 
-The first BLING models have been trained on question-answering, key-value extraction, and basic summarization as the core instruction types.
-
-
-[More Information Needed]
-
-### Downstream Use [optional]
-
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+The first BLING models have been trained for common RAG scenarios, specifically:   question-answering, key-value extraction, and basic summarization as the core instruction types
+without the need for a lot of complex instruction verbiage - provide a text passage context, ask questions, and get clear fact-based responses.
 
-[More Information Needed]
 
 ### Out-of-Scope Use
 
@@ -69,31 +58,27 @@ The first BLING models have been trained on question-answering, key-value extrac
 2.  BLING is not optimal for most production applications, other than simple and highly specific use cases.
 
 
-[More Information Needed]
-
 ## Bias, Risks, and Limitations
 
 <!-- This section is meant to convey both technical and sociotechnical limitations. -->
 
-BLING has not been designed for end consumer-oriented applications, and there has been any focus in training on important safeguards to
-mitigate potential bias and safety.    We would strongly discourage any use of BLING for any 'chatbot' use case.
-
-[More Information Needed]
+BLING has not been designed for end consumer-oriented applications, and there has not been any focus in training on safeguards to mitigate potential bias.  We would strongly discourage any use of BLING for any 'chatbot' use case.
 
 
 ## How to Get Started with the Model
 
 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-1.4b-0.1")
-model = AutoModelForCausalLM.from_pretrained("llmware/bling-1.4b-0.1")
+from transformers import AutoTokenizer, AutoModelForCausalLM  
+tokenizer = AutoTokenizer.from_pretrained("llmware/bling-1.4b-0.1")  
+model = AutoModelForCausalLM.from_pretrained("llmware/bling-1.4b-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:
+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 sub-parts:
+The BLING model was fine-tuned with closed-context samples, which assume generally that the prompt consists of two sub-parts:
 
 1.  Text Passage Context, and
 2.  Specific question or instruction based on the text passage
@@ -105,13 +90,23 @@ my_prompt = {{text_passage}} + "\n" + {{question/instruction}}
 
 ## Citation [optional]
 
-<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+BLING models are built on top of EleutherAI/Pythia base - please see citation for Pythia below:
+
+@misc{biderman2023pythia,
+      title={Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling}, 
+      author={Stella Biderman and Hailey Schoelkopf and Quentin Anthony and Herbie Bradley and Kyle O'Brien and Eric Hallahan and Mohammad Aflah Khan and Shivanshu Purohit and USVSN Sai Prashanth and Edward Raff and Aviya Skowron and Lintang Sutawika and Oskar van der Wal},
+      year={2023},
+      eprint={2304.01373},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL}
+}
+
 
 ## Model Card Contact
 
 Darren Oberst & llmware team
 
-Please reach out anytime if you are interested in this research program and would like to participate and work with us!
+Please reach out anytime if you are interested in this project and would like to participate and work with us!