cxllin-StableHermes-3b-gguf

⚠️ ARCHIVED / LEGACY MODEL NOTICE
This repository is part of a legacy collection quantized around 2023. To manage storage quotas and maintain active community projects, some rarely used quantization formats (e.g., Q2_K, Q3_K, Q4_1, Q5_1) have been permanently removed.

Only the most popular and stable formats (Q4_0, Q4_K_M, Q5_K_M, Q6_K, and Q8_0) remain available.

💡 Looking for something modern? If you are starting a new project, we highly recommend using newer architectures (like Llama 3, Mistral, or Qwen) provided by official maintainers or active community members (e.g., Bartowski, TheBloke legacy files, or official organization handles).

⚠️ This repository is no longer actively maintained. Existing files are provided "as is" for archival and legacy hardware purposes.

I'm constantly enhancing these model descriptions to provide you with the most relevant and comprehensive information

StableHermes-3b - GGUF

• Model creator: cxllin
• Original model: 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 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 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

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:

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

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.

<center>

</center>