Chronos-Hermes LLM: Versions, Prompt Templates & Hardware Requirements

Updated: 2023-08-31 |
SuperHOT
8K

Explore all versions of the model, their file formats like GGML, GPTQ, and HF, and understand the hardware requirements for local inference.

The Chronos-Hermes model merges together two LLaMa-based language models - Chronos and Nous-Hermes. It uses mostly Chronos, at a 75/25 ratio with Nous-Hermes. Chronos is really good at making long, descriptive outputs for storytelling. But the addition of Nous-Hermes brings in better coherence and ability to follow instructions. So idea behind this combo is to get the best of both worlds. The Chronos part provides vivid scene-setting and flair. The Nous-Hermes infusion keeps it more grounded and on-track with prompts.

The Llama-2 version of the model is using a gradient merge technic. Starting with higher ratio (90%) of Nous-Hermes at the beginning and completely phasing it out at layer 25.

Hardware requirements

The performance of an Chronos-Hermes model depends heavily on the hardware it's running on. For recommendations on the best computer hardware configurations to handle Chronos-Hermes models smoothly, check out this guide: Best Computer for Running LLaMA and LLama-2 Models.

Below are the Chronos-Hermes hardware requirements for 4-bit quantization:

For 13B Parameter Models

For beefier models like the Chronos-Hermes-13B-SuperHOT-8K-fp16, you'll need more powerful hardware. If you're using the GPTQ version, you'll want a strong GPU with at least 10 gigs of VRAM. AMD 6900 XT, RTX 2060 12GB, RTX 3060 12GB, or RTX 3080 would do the trick. For the CPU infgerence (GGML / GGUF) format, having enough RAM is key. You'll want your system to have around 8 gigs available to run it smoothly.

Format RAM Requirements VRAM Requirements
GPTQ (GPU inference) 12GB (Swap to Load*) 10GB
GGML / GGUF (CPU inference) 8GB 500MB
Combination of GPTQ and GGML / GGUF (offloading) 10GB 10GB

*RAM needed to load the model initially. Not required for inference. If your system doesn't have quite enough RAM to fully load the model at startup, you can create a swap file to help with the loading.

Memory speed

When running Chronos-Hermes AI models, you gotta pay attention to how RAM bandwidth and mdodel size impact inference speed. These large language models need to load completely into RAM or VRAM each time they generate a new token (piece of text). For example, a 4-bit 7B billion parameter Chronos-Hermes model takes up around 4.0GB of RAM.

Suppose your have Ryzen 5 5600X processor and DDR4-3200 RAM with theoretical max bandwidth of 50 GBps. In this scenario, you can expect to generate approximately 9 tokens per second. Typically, this performance is about 70% of your theoretical maximum speed due to several limiting factors such as inference sofware, latency, system overhead, and workload characteristics, which prevent reaching the peak speed. To achieve a higher inference speed, say 16 tokens per second, you would need more bandwidth. For example, a system with DDR5-5600 offering around 90 GBps could be enough.

For comparison, high-end GPUs like the Nvidia RTX 3090 boast nearly 930 GBps of bandwidth for their VRAM. The DDR5-6400 RAM can provide up to 100 GB/s. Therefore, understanding and optimizing bandwidth is crucial for running models like Chronos-Hermes efficiently

Recommendations:

  1. For Best Performance: Opt for a machine with a high-end GPU (like NVIDIA's latest RTX 3090 or RTX 4090) or dual GPU setup to accommodate the largest models (65B and 70B). A system with adequate RAM (minimum 16 GB, but 64 GB best) would be optimal.
  2. For Budget Constraints: If you're limited by budget, focus on Chronos-Hermes GGML/GGUF models that fit within the sytem RAM. Remember, while you can offload some weights to the system RAM, it will come at a performance cost.

Remember, these are recommendations, and the actual performance will depend on several factors, including the specific task, model implementation, and other system processes.

CPU requirements

For best performance, a modern multi-core CPU is recommended. An Intel Core i7 from 8th gen onward or AMD Ryzen 5 from 3rd gen onward will work well. CPU with 6-core or 8-core is ideal. Higher clock speeds also improve prompt processing, so aim for 3.6GHz or more.

Having CPU instruction sets like AVX, AVX2, AVX-512 can further improve performance if available. The key is to have a reasonably modern consumer-level CPU with decent core count and clocks, along with baseline vector processing (required for CPU inference with llama.cpp) through AVX2. With those specs, the CPU should handle Chronos-Hermes model size.