--- license: mit datasets: - teknium/openhermes language: - en metrics: - accuracy library_name: transformers pipeline_tag: question-answering tags: - General --- [![banner](https://maddes8cht.github.io/assets/buttons/Huggingface-banner.jpg)]() I'm constantly enhancing these model descriptions to provide you with the most relevant and comprehensive information # StableHermes-3b - GGUF - Model creator: [cxllin](https://huggingface.co/cxllin) - Original model: [StableHermes-3b](https://huggingface.co/cxllin/StableHermes-3b) # StableLM This is a Model based on StableLM. Stablelm is a familiy of Language Models by Stability AI. ## Note: Current (as of 2023-11-15) implementations of Llama.cpp only support GPU offloading up to 34 Layers with these StableLM Models. The model will crash immediately if -ngl is larger than 34. The model works fine however without any gpu acceleration. # About GGUF format `gguf` is the current file format used by the [`ggml`](https://github.com/ggerganov/ggml) library. A growing list of Software is using it and can therefore use this model. The core project making use of the ggml library is the [llama.cpp](https://github.com/ggerganov/llama.cpp) project by Georgi Gerganov # Quantization variants There is a bunch of quantized files available to cater to your specific needs. Here's how to choose the best option for you: # Legacy quants Q4_0, Q4_1, Q5_0, Q5_1 and Q8 are `legacy` quantization types. Nevertheless, they are fully supported, as there are several circumstances that cause certain model not to be compatible with the modern K-quants. ## Note: Now there's a new option to use K-quants even for previously 'incompatible' models, although this involves some fallback solution that makes them not *real* K-quants. More details can be found in affected model descriptions. (This mainly refers to Falcon 7b and Starcoder models) # K-quants K-quants are designed with the idea that different levels of quantization in specific parts of the model can optimize performance, file size, and memory load. So, if possible, use K-quants. With a Q6_K, you'll likely find it challenging to discern a quality difference from the original model - ask your model two times the same question and you may encounter bigger quality differences. --- # Original Model Card: # StableHermes-3b by cxllin ![StableHermes-3b Model Image](https://files.oaiusercontent.com/file-0vo6R0dT0BoAbKSFLTR0Xj5y?se=2023-10-31T16%3A43%3A57Z&sp=r&sv=2021-08-06&sr=b&rscc=max-age%3D31536000%2C%20immutable&rscd=attachment%3B%20filename%3Ddaec119b-4177-442c-beab-b75992106ec6.webp&sig=4q/al9442fQZFLR4CC99/pvdY9A42hcOQqGsOUgbiiE%3D) ## Overview StableHermes-3b is an advanced 3 billion parameter language model fine-tuned on the expansive OpenHermes dataset. This dataset boasts 242,000 entries primarily sourced from GPT-4 generated data, encompassing a variety of open datasets from the broader AI landscape. As an enhancement of the GPT-NeoX family, StableHermes-3b is specifically designed to provide accurate and detailed insights across a myriad of domains. ## Key Features - **3 Billion Parameters:** State-of-the-art architecture emphasizing precision and detail. - **Diverse Training Data:** Benefits from entries like GPTeacher datasets, WizardLM, Airoboros GPT-4, Camel-AI's domain expert datasets, and more. - **Open Source Dataset:** OpenHermes is one of the first fine-tunes of the Hermes dataset that has an entirely open-source dataset. - **Advanced Transformer Decoder Architecture:** Based on the GPT-NeoX's decoder-only language model structure. ## Usage To leverage StableHermes-3b for generating insights or responses, you can use the following code snippet: ```python from transformers import AutoModelForCausalLM, AutoTokenizer tokenizer = AutoTokenizer.from_pretrained("cxllin/StableHermes-3b") model = AutoModelForCausalLM.from_pretrained( "cxllin/StableHermes-3b", trust_remote_code=True, torch_dtype="auto", ) model.cuda() inputs = tokenizer("Describe the potential implications of quantum computing on the future of cybersecurity.", return_tensors="pt").to("cuda") tokens = model.generate( **inputs, max_new_tokens=64, temperature=0.75, top_p=0.95, do_sample=True, ) print(tokenizer.decode(tokens[0], skip_special_tokens=True)) ``` # Training Eval ![StableHermes](https://cdn.discordapp.com/attachments/1168701768876695603/1168954926639091825/tl.jpg?ex=6553a51c&is=6541301c&hm=0e23e7fbffdc3825f6eb9180a33c0999a1c0d15da6b6ee991892f60b946a7db0&) ***End of original Model File*** --- ## Please consider to support my work **Coming Soon:** I'm in the process of launching a sponsorship/crowdfunding campaign for my work. I'm evaluating Kickstarter, Patreon, or the new GitHub Sponsors platform, and I am hoping for some support and contribution to the continued availability of these kind of models. Your support will enable me to provide even more valuable resources and maintain the models you rely on. Your patience and ongoing support are greatly appreciated as I work to make this page an even more valuable resource for the community.
[![GitHub](https://maddes8cht.github.io/assets/buttons/github-io-button.png)](https://maddes8cht.github.io) [![Stack Exchange](https://stackexchange.com/users/flair/26485911.png)](https://stackexchange.com/users/26485911) [![GitHub](https://maddes8cht.github.io/assets/buttons/github-button.png)](https://github.com/maddes8cht) [![HuggingFace](https://maddes8cht.github.io/assets/buttons/huggingface-button.png)](https://huggingface.co/maddes8cht) [![Twitter](https://maddes8cht.github.io/assets/buttons/twitter-button.png)](https://twitter.com/maddes1966)