Update README.md

README.md

@@ -6,30 +6,12 @@ license: apache-2.0
 
 <!-- Provide a quick summary of what the model is/does. -->
 
-bling-falcon-1b-0.1 is part of the BLING ("Best Little Instruction-following No-GPU-required") model series, instruct trained on top of a falcon-rw-1b base model.
+bling-sheared-llama-1.3b-0.1 is part of the BLING ("Best Little Instruction-following No-GPU-required") model series, instruct trained on top of a falcon-rw-1b base model.
 
 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.
 
-### **PERFORMANCE on BASIC RAG TEST DATASET** 
-							
-| Model                 |  Params (B) |	Sourcing |	GPU/CPU	 | Output Tokens | Out as % of Input | Process Time (secs) | Score (0-100) |
-| :----------           | :--------:  |  :----:  | :-----:   | :---------:   | :-------:         | :--------:          | :-------:     |
-| gpt-4	                |   <=1000	  | Closed   | Multi-GPU | 2665	         | 10.53%	         | 183.8	           |    100        |
-| gpt-3.5-turbo-instruct|	<=175	  | Closed	 | Multi-GPU |	2621	     | 11.49%	         | 62.7	               |    100        |
-| claude-instant-v1	    |   <=50	  | Closed	 | Multi-GPU |	6337	     | 26.50%	         |  154	               |    100        |
-| aib-read-gpt	        |   7	      | Closed   | GPU	     |  1964	     |  9.30%            |	114	               |     96        |
-| **bling_falcon-1b-0.1**	|   **1.3**	      | **Open**	 | **CPU**	     |  **3204**	     | **14.55%**         |  **696**               |     **77**        |
-| bling_pythia-1.4b-0.1	|   1.4	      | Open	 | CPU	     |  2589	     | 11.75%	         |  593.5	           |     65        |
-| bling_pythia-1b-0.1	|   1.0	      | Open     |	CPU	     | 2753	         | 12.49%	         |  428	               |     59        |
-| bling_cerebras-1.3b   |	1.3	      | Open     |	CPU	     | 3202	         | 20.01%	         |  690.1	           |     52        |
-| bling_pythia_410m	    |  0.41	      |  NA	     |  CPU	     |  2349	     |  10.66%	         |  189	               |     36        |
-| bling_cerebras_590m	|  0.59	      |  NA	     |  CPU	     |  4407	     |   20.01%	         |  400.8	           |     30        |  
-
-For more details on this evaluation, please see the dataset: **llmware/rag_instruct_test_dataset_0.1** and [BLOG](https://medium.com/@darrenoberst/evaluating-llm-performance-in-rag-instruct-use-cases-083dc272a31d)  
-
-
 ### Model Description
 
 <!-- Provide a longer summary of what this model is. -->
@@ -38,8 +20,8 @@ For more details on this evaluation, please see the dataset: **llmware/rag_instr
 - **Model type:** GPTNeoX instruct-trained decoder
 - **Language(s) (NLP):** English
 - **License:** Apache 2.0
-- **Finetuned from model [optional]:** tiiuae/falcon-rw-1b
-
+- **Finetuned from model [optional]:** princeton-nlp/Sheared-LLaMA-1.3B
+- 
 ## Uses
 
 <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
@@ -67,15 +49,6 @@ The first BLING models have been trained for common RAG scenarios, specifically:
 without the need for a lot of complex instruction verbiage - provide a text passage context, ask questions, and get clear fact-based responses.
 
 
-### Out-of-Scope Use
-
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
-
-1.  BLING is not designed for 'chat-bot' or 'consumer-oriented' applications. 
-
-2.  BLING is not optimal for most production applications, other than simple and highly specific use cases.
-
-
 ## Bias, Risks, and Limitations
 
 <!-- This section is meant to convey both technical and sociotechnical limitations. -->
@@ -88,8 +61,8 @@ BLING has not been designed for end consumer-oriented applications, and there ha
 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-falcon-1b-0.1")  
-model = AutoModelForCausalLM.from_pretrained("llmware/bling-falcon-1b-0.1")  
+tokenizer = AutoTokenizer.from_pretrained("llmware/bling-sheared-llama-1.3b-0.1")  
+model = AutoModelForCausalLM.from_pretrained("llmware/bling-sheared-llama-1.3b-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:
@@ -108,19 +81,14 @@ my_prompt = {{text_passage}} + "\n" + {{question/instruction}}
 
 ## Citation [optional]
 
-This BLING model was built on top of a Falcon model base - for more information about the Falcon model, please see the paper referenced below:
+This BLING model was built on top of a "Sheared Llama" model base - for more information about the "Sheared Llama" model, please see the paper referenced below:
 
-@article{refinedweb,
-  title={The {R}efined{W}eb dataset for {F}alcon {LLM}: outperforming curated corpora with web data, and web data only},
-  author={Guilherme Penedo and Quentin Malartic and Daniel Hesslow and Ruxandra Cojocaru and Alessandro Cappelli and Hamza Alobeidli and Baptiste Pannier and Ebtesam Almazrouei and Julien Launay},
-  journal={arXiv preprint arXiv:2306.01116},
-  eprint={2306.01116},
-  eprinttype = {arXiv},
-  url={https://arxiv.org/abs/2306.01116},
-  year={2023}
+@article{xia2023sheared,
+   title={Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning},
+   author={Xia, Mengzhou and Gao, Tianyu, and Zeng Zhiyuan, and Chen Danqi},
+   year={2023}
 }
 
-
 ## Model Card Contact
 
 Darren Oberst & llmware team