metadata

base_model: HuggingFaceH4/zephyr-7b-beta
inference: false
license: mit
model_creator: HuggingFaceH4
model_name: Zephyr 7B Beta
model_type: mistral
prompt_template: '<|system|> </s> <|user|> {prompt}</s> <|assistant|> '
quantized_by: Semantically AI
pruned_by: Semantically AI

Zephyr 7B Beta - GGUF

Model creator: Hugging Face H4
Original model: Zephyr 7B Beta

Description

This repo contains GGUF format model files for Hugging Face H4's Zephyr 7B Beta.

GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp.

Prompt template: Zephyr

<|system|>
</s>
<|user|>
{prompt}</s>
<|assistant|>

Explanation of quantisation methods

Click to see details

The GGUF model is pruned to 50% using sparseGPT method sparseGPT

from llama_cpp import Llama

llm = Llama(model_path="zephyr-7b-beta-pruned50-Q8_0.gguf")

output = llm("""
<|system|>
You are a friendly chatbot who always responds in the style of a pirate.</s>
<|user|>
How many helicopters can a human eat in one sitting?</s>
<|assistant|>""")

print(output)
#