--- base_model: llmware/bling-sheared-llama-1.3b-0.1 inference: false license: apache-2.0 model_creator: llmware model_name: bling-sheared-llama-1.3b-0.1 pipeline_tag: text-generation quantized_by: afrideva tags: - gguf - ggml - quantized - q2_k - q3_k_m - q4_k_m - q5_k_m - q6_k - q8_0 --- # llmware/bling-sheared-llama-1.3b-0.1-GGUF Quantized GGUF model files for [bling-sheared-llama-1.3b-0.1](https://huggingface.co/llmware/bling-sheared-llama-1.3b-0.1) from [llmware](https://huggingface.co/llmware) | Name | Quant method | Size | | ---- | ---- | ---- | | [bling-sheared-llama-1.3b-0.1.q2_k.gguf](https://huggingface.co/afrideva/bling-sheared-llama-1.3b-0.1-GGUF/resolve/main/bling-sheared-llama-1.3b-0.1.q2_k.gguf) | q2_k | 630.54 MB | | [bling-sheared-llama-1.3b-0.1.q3_k_m.gguf](https://huggingface.co/afrideva/bling-sheared-llama-1.3b-0.1-GGUF/resolve/main/bling-sheared-llama-1.3b-0.1.q3_k_m.gguf) | q3_k_m | 703.75 MB | | [bling-sheared-llama-1.3b-0.1.q4_k_m.gguf](https://huggingface.co/afrideva/bling-sheared-llama-1.3b-0.1-GGUF/resolve/main/bling-sheared-llama-1.3b-0.1.q4_k_m.gguf) | q4_k_m | 872.30 MB | | [bling-sheared-llama-1.3b-0.1.q5_k_m.gguf](https://huggingface.co/afrideva/bling-sheared-llama-1.3b-0.1-GGUF/resolve/main/bling-sheared-llama-1.3b-0.1.q5_k_m.gguf) | q5_k_m | 1.00 GB | | [bling-sheared-llama-1.3b-0.1.q6_k.gguf](https://huggingface.co/afrideva/bling-sheared-llama-1.3b-0.1-GGUF/resolve/main/bling-sheared-llama-1.3b-0.1.q6_k.gguf) | q6_k | 1.17 GB | | [bling-sheared-llama-1.3b-0.1.q8_0.gguf](https://huggingface.co/afrideva/bling-sheared-llama-1.3b-0.1-GGUF/resolve/main/bling-sheared-llama-1.3b-0.1.q8_0.gguf) | q8_0 | 1.43 GB | ## Original Model Card: # Model Card for Model ID 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 Sheared-LLaMA-1.3B 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. ### Benchmark Tests Evaluated against the benchmark test: [RAG-Instruct-Benchmark-Tester](https://www.huggingface.co/datasets/llmware/rag_instruct_benchmark_tester) Average of 2 Test Runs with 1 point for correct answer, 0.5 point for partial correct or blank / NF, 0.0 points for incorrect, and -1 points for hallucinations. --**Accuracy Score**: **84.50** correct out of 100 --Not Found Classification: 20.0% --Boolean: 66.25% --Math/Logic: 9.4% --Complex Questions (1-5): 1 (Low) --Summarization Quality (1-5): 3 (Coherent, extractive) --Hallucinations: No hallucinations observed in test runs. For test run results (and good indicator of target use cases), please see the files ("core_rag_test" and "answer_sheet" in this repo). ### Model Description - **Developed by:** llmware - **Model type:** Instruct-trained decoder - **Language(s) (NLP):** English - **License:** Apache 2.0 - **Finetuned from model [optional]:** princeton-nlp/Sheared-LLaMA-1.3B ## Uses The intended use of BLING models is two-fold: 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 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 BLING is designed for enterprise automation use cases, especially in knowledge-intensive industries, such as financial services, 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 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. ## Bias, Risks, and Limitations Any model can provide inaccurate or incomplete information, and should be used in conjunction with appropriate safeguards and fact-checking mechanisms. ## 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-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 "\ and \ wrapper", so to get the best results, wrap inference entries as: full_prompt = "\\: " + my_prompt + "\n" + "\\:" 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 To get the best results, package "my_prompt" as follows: my_prompt = {{text_passage}} + "\n" + {{question/instruction}} ## Citation [optional] 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{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 Please reach out anytime if you are interested in this project!